Publications

@conference{nokey,

title = {Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation},

author = {Jiajun Wang and Morteza Ghahremani and Yitong Li and Björn Ommer and Christian Wachinger},

url = {https://neurips.cc/virtual/2024/poster/95747

https://arxiv.org/abs/2406.02485},

year  = {2024},

date = {2024-01-01},

booktitle = {Neural Information Processing Systems (NeurIPS) (Poster)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {High-Resolution Image Synthesis with Latent Diffusion Models},

author = {Robin Rombach and Andreas Blattmann and Dominik Lorenz and Patrick Esser and Björn Ommer},

url = {https://ommer-lab.com/research/latent-diffusion-models/

https://github.com/CompVis/latent-diffusion

https://arxiv.org/abs/2112.10752},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Wright2022,

title = {ArtFID: Quantitative Evaluation of Neural Style Transfer},

author = {Matthias Wright and Björn Ommer},

url = {https://github.com/matthias-wright/art-fid

https://arxiv.org/abs/2207.12280},

doi = {10.48550/arXiv.2207.12280},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

booktitle = {Proceedings of the German Conference on Pattern Recognition (GCPR '22) (Oral)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models},

author = {Robin Rombach and Andreas Blattmann and Björn Ommer},

url = {https://arxiv.org/abs/2207.13038},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

booktitle = {Proceedings of the European Conference on Computer Vision (ECCV) Workshop on Visart},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {Retrieval-Augmented Diffusion Models},

author = {Andreas Blattmann and Robin Rombach and Kaan Oktay and Björn Ommer},

url = {https://arxiv.org/abs/2204.11824},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

booktitle = {Neural Information Processing Systems (NeurIPS), 2022.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Milbich2021,

title = {Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning},

author = {Timo Milbich and Karsten Roth and Samarth Sinha and Ludwig Schmidt and Marzyeh Ghassemi and Björn Ommer},

url = {https://github.com/CompVis/Characterizing_Generalization_in_DML

https://arxiv.org/abs/2107.09562},

year  = {2021},

date = {2021-12-10},

urldate = {2021-12-10},

booktitle = {Neural Information Processing Systems (NeurIPS)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis},

author = {Patrick Esser and Robin Rombach and Andreas Blattmann and Björn Ommer},

url = {https://compvis.github.io/imagebart/

https://arxiv.org/abs/2108.08827},

year  = {2021},

date = {2021-12-10},

urldate = {2021-12-10},

booktitle = {Neural Information Processing Systems (NeurIPS)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {Unsupervised View-Invariant Human Posture Representation},

author = {Faegheh Sardari and Björn Ommer and Majid Mirmehdi},

url = {https://arxiv.org/abs/2109.08730},

year  = {2021},

date = {2021-10-18},

urldate = {2021-10-18},

booktitle = {British Machine Vision Conference (BMVC)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Blattmann2021,

title = {iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis},

author = {Andreas Blattmann and Timo Milbich and Michael Dorkenwald and Björn Ommer},

url = {https://compvis.github.io/ipoke/

https://arxiv.org/abs/2107.02790},

year  = {2021},

date = {2021-10-01},

urldate = {2021-10-01},

booktitle = {Proceedings of the International Conference on Computer Vision (ICCV)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6992,

title = {Learning Multi-Scale Photo Exposure Correction},

author = {Mahmoud Afifi and Konstantinos G Derpanis and Björn Ommer and Michael S Brown},

url = {https://github.com/mahmoudnafifi/Exposure_Correction

https://arxiv.org/abs/2003.11596},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{7028,

title = {Taming Transformers for High-Resolution Image Synthesis},

author = {Patrick Esser and Robin Rombach and Björn Ommer},

url = {https://compvis.github.io/taming-transformers/

https://arxiv.org/abs/2012.09841},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{7031,

title = {Shape or Texture: Understanding Discriminative Features in CNNs},

author = {Md Amirul Islam and Matthew Kowal and Patrick Esser and Sen Jia and Björn Ommer and Konstantinos G Derpanis and Neil Bruce},

url = {https://arxiv.org/abs/2101.11604

},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

booktitle = {International Conference on Learning Representations (ICLR)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{7041,

title = {Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes},

author = {Dmytro Kotovenko and Matthias Wright and Arthur Heimbrecht and Björn Ommer},

url = {https://compvis.github.io/brushstroke-parameterized-style-transfer/

https://arxiv.org/abs/2103.17185},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},

abstract = {There have been many successful implementations of 

neural style transfer in recent years. In most of these works, 

the stylization process is confined to the pixel domain. How- 

ever, we argue that this representation is unnatural because 

paintings usually consist of brushstrokes rather than pixels. 

We propose a method to stylize images by optimizing parameterized brushstrokes instead of pixels and further introduce 

a simple differentiable rendering mechanism. 

Our approach significantly improves visual quality and en- 

ables additional control over the stylization process such as 

controlling the flow of brushstrokes through user input. 

We provide qualitative and quantitative evaluations that 

show the efficacy of the proposed parameterized representation.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{7044,

title = {Behavior-Driven Synthesis of Human Dynamics},

author = {Andreas Blattmann and Timo Milbich and Michael Dorkenwald and Björn Ommer},

url = {https://compvis.github.io/behavior-driven-video-synthesis/

https://arxiv.org/abs/2103.04677},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{7051,

title = {S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learning},

author = {Karsten Roth and Timo Milbich and Björn Ommer and Joseph Paul Cohen and Marzyeh Ghassemi},

url = {https://github.com/MLforHealth/S2SD

https://arxiv.org/abs/2009.08348},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

booktitle = {Proceedings of International Conference on Machine Learning (ICML)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{7053,

title = {Stochastic Image-to-Video Synthesis using cINNs},

author = {Michael Dorkenwald and Timo Milbich and Andreas Blattmann and Robin Rombach and Konstantinos G. Derpanis and Björn Ommer},

url = {https://compvis.github.io/image2video-synthesis-using-cINNs/

https://arxiv.org/abs/2105.04551},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{7054,

title = {High-Resolution Complex Scene Synthesis with Transformers},

author = {Manuel Jahn and Robin Rombach and Björn Ommer},

url = {https://compvis.github.io/taming-transformers/

https://arxiv.org/abs/2105.06458},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

booktitle = {CVPR 2021, AI for Content Creation Workshop},

abstract = {The use of coarse-grained layouts for controllable synthesis of complex scene images via deep generative models has recently gained popularity. However, results of current approaches still fall short of their promise of high-resolution synthesis. We hypothesize that this is mostly due to the highly engineered nature of these approaches which often rely on auxiliary losses and intermediate steps such as mask generators. In this note, we present an orthogonal approach to this task, where the generative model is based on pure likelihood training without additional objectives. To do so, we first optimize a powerful compression model with adversarial training which learns to reconstruct its inputs via a discrete latent bottleneck and thereby effectively strips the latent representation of high-frequency details such as texture. Subsequently, we train an autoregressive transformer model to learn the distribution of the discrete image representations conditioned on a tokenized version of the layouts. Our experiments show that the resulting system is able to synthesize high-quality images consistent with the given layouts. In particular, we improve the state-of-the-art FID score on COCO-Stuff and on Visual Genome by up to 19% and 53% and demonstrate the synthesis of images up to 512 x 512 px on COCO and Open Images.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{7063,

title = {Understanding Object Dynamics for Interactive Image-to-Video Synthesis},

author = {Andreas Blattmann and Timo Milbich and Michael Dorkenwald and Björn Ommer},

url = {https://compvis.github.io/interactive-image2video-synthesis/

https://arxiv.org/abs/2106.11303v1},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},

abstract = {What would be the effect of locally poking a static scene? We present an approach that learns naturally-looking global articulations caused by a local manipulation at a pixel level. Training requires only videos of moving objects but no information of the underlying manipulation of the physical scene. Our generative model learns to infer natural object dynamics as a response to user interaction and learns about the interrelations between different object body regions. Given a static image of an object and a local poking of a pixel, the approach then predicts how the object would deform over time. In contrast to existing work on video prediction, we do not synthesize arbitrary realistic videos but enable local interactive control of the deformation. Our model is not restricted to particular object categories and can transfer dynamics onto novel unseen object instances. Extensive experiments on diverse objects demonstrate the effectiveness of our approach compared to common video prediction frameworks.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{7067,

title = {Geometry-Free View Synthesis: Transformers and no 3D Priors},

author = {Robin Rombach and Patrick Esser and Björn Ommer},

url = {https://compvis.github.io/geometry-free-view-synthesis/

https://arxiv.org/abs/2104.07652},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

booktitle = {Proceedings of the Intl. Conf. on Computer Vision (ICCV)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6386,

title = {PADS: Policy-Adapted Sampling for Visual Similarity Learning},

author = {Timo Milbich and Karsten Roth and Björn Ommer},

url = {https://github.com/Confusezius/CVPR2020_PADS

https://arxiv.org/abs/2003.11113},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},

volume = {1},

chapter = {1},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6390,

title = {Revisiting Training Strategies and Generalization Performance in Deep Metric Learning},

author = {Karsten Roth and Timo Milbich and Samarth Sinha and Prateek Gupta and Björn Ommer and Joseph Paul Cohen},

url = {https://arxiv.org/abs/2002.08473},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

booktitle = {International Conference on Machine Learning (ICML)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6932,

title = {A Disentangling Invertible Interpretation Network for Explaining Latent Representations},

author = {Patrick Esser and Robin Rombach and Björn Ommer},

url = {https://compvis.github.io/iin/

https://arxiv.org/abs/2004.13166},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},

abstract = {Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations are lacking interpretability: Since distributed coding is optimal for latent layers to improve their robustness, attributing meaning to parts of a hidden feature vector or to individual neurons is hindered. We formulate interpretation as a translation of hidden representations onto semantic concepts that are comprehensible to the user. The mapping between both domains has to be bijective so that semantic modifications in the target domain correctly alter the original representation. The proposed invertible interpretation network can be transparently applied on top of existing architectures with no need to modify or retrain them. Consequently, we translate an original representation to an equivalent yet interpretable one and backwards without affecting the expressiveness and performance of the original. The invertible interpretation network disentangles the hidden representation into separate, semantically meaningful concepts. Moreover, we present an efficient approach to define semantic concepts by only sketching two images and also an unsupervised strategy. Experimental evaluation demonstrates the wide applicability to interpretation of existing classification and image generation networks as well as to semantically guided image manipulation.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6934,

title = {DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning},

author = {Timo Milbich and Karsten Roth and Homanga Bharadhwaj and Samarth Sinha and Yoshua Bengio and Björn Ommer and Joseph Paul Cohen},

url = {https://arxiv.org/abs/2004.13458},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

booktitle = {IEEE European Conference on Computer Vision (ECCV)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6997,

title = {Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with INNs},

author = {Robin Rombach and Patrick Esser and Björn Ommer},

url = {https://compvis.github.io/invariances/

https://arxiv.org/pdf/2008.01777.pdf},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

booktitle = {IEEE European Conference on Computer Vision (ECCV)},

abstract = {To tackle increasingly complex tasks, it has become an essential ability of neural networks to learn abstract representations. These task-specific representations and, particularly, the invariances they capture turn neural networks into black box models that lack interpretability. To open such a black box, it is, therefore, crucial to uncover the different semantic concepts a model has learned as well as those that it has learned to be invariant to. We present an approach based on INNs that (i) recovers the task-specific, learned invariances by disentangling the remaining factor of variation in the data and that (ii) invertibly transforms these recovered invariances combined with the model representation into an equally expressive one with accessible semantic concepts. As a consequence, neural network representations become understandable by providing the means to (i) expose their semantic meaning, (ii) semantically modify a representation, and (iii) visualize individual learned semantic concepts and invariances. Our invertible approach significantly extends the abilities to understand black box models by enabling post-hoc interpretations of state-of-the-art networks without compromising their performance.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{7004,

title = {Unsupervised Part Discovery by Unsupervised Disentanglement},

author = {Sandro Braun and Patrick Esser and Björn Ommer},

url = {https://compvis.github.io/unsupervised-part-segmentation/

https://arxiv.org/abs/2009.04264},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

booktitle = {Proceedings of the German Conference on Pattern Recognition (GCPR) (Oral)},

address = {Tübingen},

abstract = {We address the problem of discovering part segmentations of articulated objects without supervision. In contrast to keypoints, part segmentations provide information about part localizations on the level of individual pixels. Capturing both locations and semantics, they are an attractive target for supervised learning approaches. However, large annotation costs limit the scalability of supervised algorithms to other object categories than humans. Unsupervised approaches potentially allow to use much more data at a lower cost. Most existing unsupervised approaches focus on learning abstract representations to be refined with supervision into the final representation. Our approach leverages a generative model consisting of two disentangled representations for an objecttextquoterights shape and appearance and a latent variable for the part segmentation. From a single image, the trained model infers a semantic part segmentation map. In experiments, we compare our approach to previous state-of-the-art approaches and observe significant gains in segmentation accuracy and shape consistency. Our work demonstrates the feasibility to discover semantic part segmentations without supervision.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{7011,

title = {Network-to-Network Translation with Conditional Invertible Neural Networks},

author = {Robin Rombach and Patrick Esser and Björn Ommer},

url = {https://compvis.github.io/net2net/

https://arxiv.org/abs/2005.13580},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

booktitle = {Neural Information Processing Systems (NeurIPS) (Oral)},

abstract = {Combining stimuli from diverse modalities into a coherent perception is a striking feat of intelligence of evolved brains. This work seeks its analogy in deep learning models and aims to establish relations between existing networks by faithfully combining the representations of these different domains. Therefore, we seek a model that can relate between different existing representations by learning a conditionally invertible mapping between them. The network demonstrates this capability by (i) providing generic transfer between diverse domains, (ii) enabling controlled content synthesis by allowing modification in other domains, and (iii) facilitating diagnosis of existing representations by translating them into an easily accessible domain. Our domain transfer network can translate between fixed representations without having to learn or finetune them. This allows users to utilize various existing domain-specific expert models from the literature that had been trained with extensive computational resources. Experiments on diverse conditional image synthesis tasks, competitive image modification results and experiments on image-to-image and text-to-image generation demonstrate the generic applicability of our approach. In particular, we translate between BERT and BigGAN, state-of-the-art text and image models to provide text-to-image generation, which neither of both experts can perform on their own.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{7012,

title = {Network Fusion for Content Creation with Conditional INNs},

author = {Robin Rombach and Patrick Esser and Björn Ommer},

url = {https://compvis.github.io/network-fusion/

https://arxiv.org/abs/2005.13580},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

booktitle = {CVPRW 2020 (AI for Content Creation)},

abstract = {Artificial Intelligence for Content Creation has the potential to reduce the amount of manual content creation work significantly. While automation of laborious work is welcome, it is only useful if it allows users to control aspects of the creative process when desired. Furthermore, widespread adoption of semi-automatic content creation depends on low barriers regarding the expertise, computational budget and time required to obtain results and experiment with new techniques. With state-of-the-art approaches relying on task-specific models, multi-GPU setups and weeks of training time, we must find ways to reuse and recombine them to meet these requirements. Instead of designing and training methods for controllable content creation from scratch, we thus present a method to repurpose powerful, existing models for new tasks, even though they have never been designed for them. We formulate this problem as a translation between expert models, which includes common content creation scenarios, such as text-to-image and image-to-image translation, as a special case. As this translation is ambiguous, we learn a generative model of hidden representations of one expert conditioned on hidden representations of the other expert. Working on the level of hidden representations makes optimal use of the computational effort that went into the training of the expert model to produce these efficient, low-dimensional representations. Experiments demonstrate that our approach can translate from BERT, a state-of-the-art expert for text, to BigGAN, a state-of-the-art expert for images, to enable text-to-image generation, which neither of the experts can perform on its own. Additional experiments show the wide applicability of our approach across different conditional image synthesis tasks and improvements over existing methods for image modifications.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{7025,

title = {A Note on Data Biases in Generative Models},

author = {Patrick Esser and Robin Rombach and Björn Ommer},

url = {https://neurips2020creativity.github.io/

https://arxiv.org/abs/2012.02516},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

booktitle = {NeurIPS 2020 Workshop on Machine Learning for Creativity and Design},

abstract = {It is tempting to think that machines are less prone to unfairness and prejudice. However, machine learning approaches compute their outputs based on data. While biases can enter at any stage of the development pipeline, models are particularly receptive to mirror biases of the datasets they are trained on and therefore do not necessarily reflect truths about the world but, primarily, truths about the data. To raise awareness about the relationship between modern algorithms and the data that shape them, we use a conditional invertible neural network to disentangle the dataset-specific information from the information which is shared across different datasets. In this way, we can project the same image onto different datasets, thereby revealing their inherent biases. We use this methodology to (i) investigate the impact of dataset quality on the performance of generative models, (ii) show how societal biases of datasets are replicated by generative models, and (iii) present creative applications through unpaired transfer between diverse datasets such as photographs, oil portraits, and animes.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{7038,

title = {Das Objekt jenseits der Digitalisierung},

author = {Sabine Lang and Björn Ommer},

url = {https://www.youtube.com/watch?v=QqupZYCTl98

https://www.deutsches-museum.de/assets/Verlag/Download/Studies/studies-7-download.pdf

},

isbn = {978-3-948808-00-6},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

booktitle = {Das digitale Objekt},

volume = {7},

abstract = {Der technische Fortschritt der letzten Jahrzehnte hat disruptive Veränderungen für Gesellschaft, Wirtschaft und Wissenschaft gebracht: Die Digitalisierung ist ein Resultat dessen und beeinflusst, wie wir auf Daten zugreifen, diese verarbeiten, analysieren und Ergebnisse verbreiten. Obwohl dadurch bereits ein Wandel eingeleitet worden ist, kann das Digitalisieren von Textdokumenten oder Bildern nicht das endgültige Ziel sein. Der Fokus aktueller Bestrebungen sollte vielmehr auf der Möglichkeit der Weiterverarbeitung von Digitalisaten liegen – dies schließt eine intelligente Informationsverarbeitung ein. Der Wert der Digitalisierung besteht nicht in der bloßen Anhäufung digitaler Sammlun- gen, sondern in der Tatsache, dass sie weitaus mehr ermöglicht als das Analoge und dafür die notwendigen Grundvoraussetzungen schafft. 

Die Problematik besteht nun darin, dass die meisten Verarbeitungs- und Analyse- methoden für digitale Daten noch analog oder diesen nachempfunden sind: So werden digitale Sammlungen und darin enthaltene Bilder häufig noch mit den eigenen Augen, in traditionell komparativer Weise betrachtet und evaluiert. Dass dies aufgrund der Fülle an Daten nicht effizient ist, muss an dieser Stelle nicht betont werden. Obwohl das ana- loge und das digitale Bild den gleichen Inhalt zeigen können, haben beide doch ganz unterschiedliche Substrate. Ein Unterschied besteht zum Beispiel darin, dass digitale Bilder im Gegensatz zu analogen einfach manipuliert und dupliziert werden können. Das Digitale ist nicht das Analoge in neuer Form, und so bedarf es genuin digitaler Methoden für die Verarbeitung digitaler Daten. Durch die Entwicklung computerge- stützter Verfahren entstehen neue Möglichkeiten, Inhalte zu erschließen: Dazu gehören Ansätze zur Objektsuche oder das Gruppieren und Sortieren der Daten entsprechend benutzerdefinierter Dimensionen; dies schließt übergeordnete Kategorien wie Stil oder Genre, aber auch nuancierte Begriffe wie Alter oder Gewichtung der Bildkomposition ein. Doch das Digitale und entsprechende Verfahren können noch weitaus mehr leisten: Generative Verfahren, wie die Bildsynthese und Stilisierung eines Bildes, ermöglichen eine Blickänderung auf das Artefakt und schließlich die Modifizierung des Objekts selbst. Wie hätte ein Künstler eine uns sichtbare Szene gemalt und dargestellt? Und wie sieht ein Mensch in der Pose eines anderen aus? Dies sind Fragen, die durch die Anwendung com- putergestützter Methoden beantwortet werden können. Für das Museum haben diese Ansätze eine besondere Relevanz, da sie neue Arten des Betrachtens und Vermittelns von Kunstwerken oder zum Beispiel die Rekonstruktion verlorener Artefakte erlauben. In Zusammenarbeit von Mensch und Maschine entstehen so neue effektive Verfahren, die Inhalte erschließen, Verbindungen etablieren und neues Wissen generieren.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{7042,

title = {Unsupervised Magnification of Posture Deviations Across Subjects},

author = {Michael Dorkenwald and Uta Büchler and Björn Ommer},

url = {https://compvis.github.io/magnify-posture-deviations/

https://openaccess.thecvf.com/content_CVPR_2020/papers/Dorkenwald_Unsupervised_Magnification_of_Posture_Deviations_Across_Subjects_CVPR_2020_paper.pdf},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{7064,

title = {Object Retrieval and Localization in Large Art Collections Using Deep Multi-style Feature Fusion and Iterative Voting},

author = {Nikolai Ufer and Sabine Lang and Björn Ommer},

url = {https://arxiv.org/abs/2107.06935

},

doi = {https://doi.org/10.1007/978-3-030-66096-3_12},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

booktitle = {IEEE European Conference on Computer Vision (ECCV), VISART Workshop },

abstract = {The search for specific objects or motifs is essential to art history as both assist in decoding the meaning of artworks. Digitization has produced large art collections, but manual methods prove to be insufficient to analyze them. In the following, we introduce an algorithm that allows users to search for image regions containing specific motifs or objects and find similar regions in an extensive dataset, helping art historians to analyze large digitized art collections. Computer vision has presented efficient methods for visual instance retrieval across photographs. However, applied to art collections, they reveal severe deficiencies because of diverse motifs and massive domain shifts induced by differences in techniques, materials, and styles. In this paper, we present a multi-style feature fusion approach that successfully reduces the domain gap and improves retrieval results without labelled data or curated image collections. Our region-based voting with GPU-accelerated approximate nearest-neighbour search allows us to find and localize even small motifs within an extensive dataset in a few seconds. We obtain state-of-the-art results on the Brueghel dataset and demonstrate its generalization to inhomogeneous collections with a large number of distractors.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6299,

title = {Divide and Conquer the Embedding Space for Metric Learning},

author = {A. Sanakoyeu and V. Tschernezki and Uta Büchler and Björn Ommer},

url = {https://github.com/CompVis/metric-learning-divide-and-conquer

https://arxiv.org/abs/1906.05990},

year  = {2019},

date = {2019-01-01},

urldate = {2019-01-01},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6300,

title = {Using a Transformation Content Block For Image Style Transfer},

author = {Dmytro Kotovenko and A. Sanakoyeu and Sabine Lang and P. Ma and Björn Ommer},

url = {https://compvis.github.io/content-targeted-style-transfer/

https://arxiv.org/abs/2003.08407},

year  = {2019},

date = {2019-01-01},

urldate = {2019-01-01},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6301,

title = {Unsupervised Part-Based Disentangling of Object Shape and Appearance},

author = {Dominik Lorenz and Leonard Bereska and Timo Milbich and Björn Ommer},

url = {https://compvis.github.io/unsupervised-disentangling/

https://arxiv.org/abs/1903.06946},

year  = {2019},

date = {2019-01-01},

urldate = {2019-01-01},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (Oral + Best paper finalist: top 45 / 5160 submissions)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6321,

title = {MIC: Mining Interclass Characteristics for Improved Metric Learning},

author = {Biagio Brattoli and Karsten Roth and Björn Ommer},

url = {https://github.com/Confusezius/ICCV2019_MIC

https://arxiv.org/abs/1909.11574},

year  = {2019},

date = {2019-01-01},

urldate = {2019-01-01},

booktitle = {Proceedings of the Intl. Conf. on Computer Vision (ICCV)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6322,

title = {Content and Style Disentanglement for Artistic Style Transfer},

author = {Dmytro Kotovenko and Artsiom Sanakoyeu and Sabine Lang and Björn Ommer},

url = {https://compvis.github.io/content-style-disentangled-ST/

https://compvis.github.io/content-style-disentangled-ST/paper.pdf},

year  = {2019},

date = {2019-01-01},

urldate = {2019-01-01},

booktitle = {Proceedings of the Intl. Conf. on Computer Vision (ICCV)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6323,

title = {Unsupervised Robust Disentangling of Latent Characteristics for Image Synthesis},

author = {Patrick Esser and Johannes Haux and Björn Ommer},

url = {https://compvis.github.io/robust-disentangling/

https://arxiv.org/abs/1910.10223},

year  = {2019},

date = {2019-01-01},

urldate = {2019-01-01},

booktitle = {Proceedings of the Intl. Conf. on Computer Vision (ICCV)},

abstract = {Deep generative models come with the promise to learn an explainable representation for visual objects that allows image sampling, synthesis, and selective modification. The main challenge is to learn to properly model the independent latent characteristics of an object, especially its appearance and pose. We present a novel approach that learns disentangled representations of these characteristics and explains them individually. Training requires only pairs of images depicting the same object appearance, but no pose annotations. We propose an additional classifier that estimates the minimal amount of regularization required to enforce disentanglement. Thus both representations together can completely explain an image while being independent of each other. Previous methods based on adversarial approaches fail to enforce this independence, while methods based on variational approaches lead to uninformative representations. In experiments on diverse object categories, the approach successfully recombines pose and appearance to reconstruct and retarget novel synthesized images. We achieve significant improvements over state-of-the-art methods which utilize the same level of supervision, and reach performances comparable to those of pose-supervised approaches. However, we can handle the vast body of articulated object classes for which no pose models/annotations are available.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6324,

title = {Weakly Supervised Learning of Dense SemanticCorrespondences and Segmentation},

author = {Nikolai Ufer and Kam To Lui and Katja Schwarz and Paul Warkentin and Björn Ommer},

url = {https://www.researchgate.net/publication/336816354_Weakly_Supervised_Learning_of_Dense_Semantic_Correspondences_and_Segmentation},

doi = {10.1007/978-3-030-33676-9_32},

year  = {2019},

date = {2019-01-01},

urldate = {2019-01-01},

booktitle = {German Conference on Pattern Recognition (GCPR)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6249,

title = {A Variational U-Net for Conditional Appearance and Shape Generation},

author = {Patrick Esser and Ekaterina Sutter and Björn Ommer},

url = {https://compvis.github.io/vunet/

https://arxiv.org/abs/1804.04694},

year  = {2018},

date = {2018-01-01},

urldate = {2018-01-02},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (short Oral)},

abstract = {Deep generative models have demonstrated great performance in image synthesis. However, results deteriorate in case of spatial deformations, since they generate images of objects directly, rather than modeling the intricate interplay of their inherent shape and appearance. We present a conditional U-Net for shape-guided image generation, conditioned on the output of a variational autoencoder for appearance. The approach is trained end-to-end on images, without requiring samples of the same object with varying pose or appearance. Experiments show that the model enables conditional image generation and transfer. Therefore, either shape or appearance can be retained from a query image, while freely altering the other. Moreover, appearance can be sampled due to its stochastic latent representation, while preserving shape. In quantitative and qualitative experiments on COCO, DeepFashion, shoes, Market-1501 and handbags, the approach demonstrates significant improvements over the state-of-the-art.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6250,

title = {Learning to Forecast Pedestrian Intention from Pose Dynamics},

author = {Omar Ghori and Radek Mackowiak and Miguel Bautista and Niklas Beuter and Lucas Drumond and Ferran Diego and Björn Ommer},

url = {https://www.researchgate.net/publication/328451374_Learning_to_Forecast_Pedestrian_Intention_from_Pose_Dynamics



},

year  = {2018},

date = {2018-01-01},

urldate = {2018-01-01},

booktitle = {Intelligent Vehicles, IEEE},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{buechler:ECCV:2018,

title = {Improving Spatiotemporal Self-Supervision by Deep Reinforcement Learning},

author = {Uta Büchler and Biagio Brattoli and Björn Ommer},

url = {https://arxiv.org/abs/1807.11293

https://hci.iwr.uni-heidelberg.de/sites/default/files/publications/files/1855931744/buechler_eccv18_poster.pdf},

year  = {2018},

date = {2018-01-01},

urldate = {2018-01-01},

booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},

publisher = {(UB and BB contributed equally)},

address = {Munich, Germany},

abstract = {Self-supervised learning of convolutional neural networks can harness large amounts of cheap unlabeled data to train powerful feature representations. As surrogate task, we jointly address ordering of visual data in the spatial and temporal domain. The permutations of training samples, which are at the core of self-supervision by ordering, have so far been sampled randomly from a fixed preselected set. Based on deep reinforcement learning we propose a sampling policy that adapts to the state of the network, which is being trained. Therefore, new permutations are sampled according to their expected utility for updating the convolutional feature representation. Experimental evaluation on unsupervised and transfer learning tasks demonstrates competitive performance on standard benchmarks for image and video classification and nearest neighbor retrieval.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{style_aware_content_loss_eccv18,

title = {A Style-Aware Content Loss for Real-time HD Style Transfer},

author = {A. Sanakoyeu and Dmytro Kotovenko and Sabine Lang and Björn Ommer},

url = {https://compvis.github.io/adaptive-style-transfer/

https://arxiv.org/abs/1807.10201},

year  = {2018},

date = {2018-01-01},

urldate = {2018-01-01},

booktitle = {Proceedings of the European Conference on Computer Vision (ECCV) (Oral)},

abstract = {Recently, style transfer has received a lot of attention. While much of this research has aimed at speeding up processing, the approaches are still lacking from a principled, art historical standpoint: a style is more than just a single image or an artist, but previous work is limited to only a single instance of a style or shows no benefit from more images. Moreover, previous work has relied on a direct comparison of art in the domain of RGB images or on CNNs pre-trained on ImageNet, which requires millions of labeled object bounding boxes and can introduce an extra bias, since it has been assembled without artistic consideration. To circumvent these issues, we propose a style-aware content loss, which is trained jointly with a deep encoder-decoder network for real-time, high-resolution stylization of images and videos. We propose a quantitative measure for evaluating the quality of a stylized image and also have art historians rank patches from our approach against those from previous work. These and our qualitative results ranging from small image patches to megapixel stylistic images and videos show that our approach better captures the subtle nature in which a style affects content.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{sayed:GCPR:2018,

title = {Cross and Learn: Cross-Modal Self-Supervision},

author = {N. Sayed and Biagio Brattoli and Björn Ommer},

url = {https://arxiv.org/abs/1811.03879v1

https://bbrattoli.github.io/publications/images/sayed_crossandlearn.pdf},

year  = {2018},

date = {2018-01-01},

urldate = {2018-01-01},

booktitle = {German Conference on Pattern Recognition (GCPR) (Oral)},

address = {Stuttgart, Germany},

abstract = {In this paper we present a self-supervised method to learn feature representations for different modalities. Based on the observation that cross-modal information has a high semantic meaning we propose a method to effectively exploit this signal. For our method we utilize video data since it is available on a large scale and provides easily accessible modalities given by RGB and optical flow. We demonstrate state-of-the-art performance on highly contested action recognition datasets in the context of self-supervised learning. We also show the transferability of our feature representations and conduct extensive ablation studies to validate our core contributions.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{blum:GCPR:2018,

title = {X-GAN: Improving Generative Adversarial Networks with ConveX Combinations},

author = {O. Blum and Biagio Brattoli and Björn Ommer},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/X-Gan_Improving-Generative-Adversarial-Networks-with-ConveX-Combinations.pdf

https://ommer-lab.com/wp-content/uploads/2021/10/xgan_supplementary.pdf

},

year  = {2018},

date = {2018-01-01},

urldate = {2018-01-01},

booktitle = {German Conference on Pattern Recognition (GCPR) (Oral)},

address = {Stuttgart, Germany},

abstract = {Even though recent neural architectures for image generation are capable of producing photo-realistic results, the overall distributions of real and faked images still differ a lot. While the lack of a structured latent representation for GANs often results in mode collapse, VAEs enforce a prior to the latent space that leads to an unnatural representation of the underlying real distribution. We introduce a method that preserves the natural structure of the latent manifold. By utilizing neighboring relations within the set of discrete real samples, we reproduce the full continuous latent manifold. We propose a novel image generation network X-GAN that creates latent input vectors from random convex combinations of adjacent real samples. This way we ensure a structured and natural latent space by not requiring prior assumptions. In our experiments, we show that our model outperforms recent approaches in terms of the missing mode problem while maintaining a high image quality.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6282,

title = {Towards Learning a Realistic Rendering of Human Behavior},

author = {Patrick Esser and Johannes Haux and Timo Milbich and Björn Ommer},

url = {https://compvis.github.io/hbugen2018/

https://compvis.github.io/hbugen2018/images/rerender.pdf

},

year  = {2018},

date = {2018-01-01},

urldate = {2018-01-01},

booktitle = {European Conference on Computer Vision (ECCV - HBUGEN)},

abstract = {Realistic rendering of human behavior is of great interest for applications such as video animations, virtual reality and more generally, gaming engines. Commonly animations of persons performing actions are rendered by articulating explicit 3D models based on sequences of coarse body shape representations simulating a certain behavior. While the simulation of natural behavior can be efficiently learned from common video data, the corresponding 3D models are typically designed in manual, laborious processes or reconstructed from costly (multi-)sensor data. In this work, we present an approach towards a holistic learning framework for rendering human behavior in which all components are learned from easily available data. We utilize motion capture data to generate realistic generations which can be controlled by a user and learn to render characters using only RGB camera data. Our experiments show that we can further improve data efficiency by training on multiple characters at the same time. Overall our approach shows a completely new path towards easily available, personalized avatar creation.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6284,

title = {Reflecting on How Artworks Are Processed and Analyzed by Computer Vision},

author = {Sabine Lang and Björn Ommer},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Reflecting-on-How-artworks-Are-Processed-and-Analyzed-by-Computer-Vision.pdf},

year  = {2018},

date = {2018-01-01},

urldate = {2018-01-01},

booktitle = {European Conference on Computer Vision (ECCV - VISART)},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6136,

title = {Deep Semantic Feature Matching},

author = {Nikolai Ufer and Björn Ommer},

url = {https://github.com/cl199443/Deep-Semantic-Feature-Matching

https://ommer-lab.com/wp-content/uploads/2021/10/Deep-Semantic-Feature-Matching.pdf},

year  = {2017},

date = {2017-01-01},

urldate = {2017-01-01},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{buechler:CVPR:2017,

title = {LSTM Self-Supervision for Detailed Behavior Analysis},

author = {Biagio Brattoli and Uta Büchler and Anna-Sophia Wahl and M. E. Schwab and Björn Ommer},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/LSTM-Self-Supervision-for-Detailed-Behavior-Analysis.pdf

},

year  = {2017},

date = {2017-01-01},

urldate = {2017-01-01},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},

publisher = {(BB and UB contributed equally)},

abstract = {Behavior analysis provides a crucial non-invasive and 

easily accessible diagnostic tool for biomedical research. 

A detailed analysis of posture changes during skilled mo- 

tor tasks can reveal distinct functional deficits and their 

restoration during recovery. Our specific scenario is based 

on a neuroscientific study of rodents recovering from a large 

sensorimotor cortex stroke and skilled forelimb grasping is 

being recorded. Given large amounts of unlabeled videos 

that are recorded during such long-term studies, we seek 

an approach that captures fine-grained details of posture 

and its change during rehabilitation without costly manual 

supervision. Therefore, we utilize self-supervision to au- 

tomatically learn accurate posture and behavior represen- 

tations for analyzing motor function. Learning our model 

depends on the following fundamental elements: (i) limb 

detection based on a fully convolutional network is ini- 

tialized solely using motion information, (ii) a novel self- 

supervised training of LSTMs using only temporal permu- 

tation yields a detailed representation of behavior, and (iii) 

back-propagation of this sequence representation also im- 

proves the description of individual postures. We establish a 

novel test dataset with expert annotations for evaluation of 

fine-grained behavior analysis. Moreover, we demonstrate 

the generality of our approach by successfully applying it to 

self-supervised learning of human posture on two standard 

benchmark datasets.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6183,

title = {Learning Where to Drive by Watching Others},

author = {Miguel Bautista and P. Fuchs and Björn Ommer},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Learning-Where-to-Drive-by-Watching-Others.pdf

https://ommer-lab.com/wp-content/uploads/2021/10/Supplementary-material_Learning-Where-to-Drive.pdf},

year  = {2017},

date = {2017-01-01},

urldate = {2017-01-01},

booktitle = {Proceedings of the German Conference Pattern Recognition},

volume = {1},

publisher = {Springer-Verlag},

address = {Basel},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6187,

title = {Unsupervised Video Understanding by Reconciliation of Posture Similarities},

author = {Timo Milbich and Miguel Bautista and Ekaterina Sutter and Björn Ommer},

url = {https://hci.iwr.uni-heidelberg.de/compvis/research/tmilbich_iccv17

https://arxiv.org/abs/1708.01191},

year  = {2017},

date = {2017-01-01},

urldate = {2017-01-01},

booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6193,

title = {Self-supervised Learning of Pose Embeddings from Spatiotemporal Relations in Videos},

author = {Ömer Sümer and Tobias Dencker and Björn Ommer},

url = {https://arxiv.org/abs/1708.02179

https://ommer-lab.com/wp-content/uploads/2021/10/Supplementary-Material_Self-Supervised-Learning-of-Pose-Embeddings-from-Spatiotemporal-Relations-in-Videos.pdf},

year  = {2017},

date = {2017-01-01},

urldate = {2017-01-01},

booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},

abstract = {Human pose analysis is presently dominated by deep convolutional networks trained with extensive manual annotations of joint locations and beyond. To avoid the need for expensive labeling, we exploit spatiotemporal relations in training videos for self-supervised learning of pose embeddings. The key idea is to combine temporal ordering and spatial placement estimation as auxiliary tasks for learning pose similarities in a Siamese convolutional network. Since the self-supervised sampling of both tasks from natural videos can result in ambiguous and incorrect training labels, our method employs a curriculum learning idea that starts training with the most reliable data samples and gradually increases the difficulty. To further refine the training process we mine repetitive poses in individual videos which provide reliable labels while removing inconsistencies. Our pose embeddings capture visual characteristics of human pose that can boost existing supervised representations in human pose estimation and retrieval. We report quantitative and qualitative results on these tasks in Olympic Sports, Leeds Pose Sports and MPII Human Pose datasets.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{6200,

title = {Deep Unsupervised Similarity Learning using Partially Ordered Sets},

author = {Miguel Bautista and A. Sanakoyeu and Björn Ommer},

url = {https://github.com/asanakoy/deep_unsupervised_posets

https://arxiv.org/abs/1704.02268},

year  = {2017},

date = {2017-01-01},

urldate = {2017-01-01},

booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{arXiv:1608.08792,

title = {CliqueCNN: Deep Unsupervised Exemplar Learning},

author = {Miguel Bautista and A. Sanakoyeu and E. Sutter and Björn Ommer},

url = {https://github.com/asanakoy/cliquecnn

https://arxiv.org/abs/1608.08792},

year  = {2016},

date = {2016-01-01},

urldate = {2016-01-01},

booktitle = {Proceedings of the Conference on Advances in Neural Information Processing Systems (NIPS)},

publisher = {MIT Press},

address = {Barcelona},

abstract = {Exemplar learning is a powerful paradigm for discovering visual similarities in 

an unsupervised manner. In this context, however, the recent breakthrough in 

deep learning could not yet unfold its full potential. With only a single positive 

sample, a great imbalance between one positive and many negatives, and unreliable 

relationships between most samples, training of Convolutional Neural networks is 

impaired. Given weak estimates of local distance we propose a single optimization 

problem to extract batches of samples with mutually consistent relations. Conflict- 

ing relations are distributed over different batches and similar samples are grouped 

into compact cliques. Learning exemplar similarities is framed as a sequence of 

clique categorization tasks. The CNN then consolidates transitivity relations within 

and between cliques and learns a single representation for all samples without 

the need for labels. The proposed unsupervised approach has shown competitive 

performance on detailed posture analysis and object classification.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{antic:MICCAI:2015,

title = {Spatiotemporal Parsing of Motor Kinematics for Assessing Stroke Recovery},

author = {B. Antic and Uta Büchler and Anna-Sophia Wahl and M. E. Schwab and Björn Ommer},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Spatiotemporal-Parsing-of-Motor-Kinemtaics-for-Assessing-Stroke-Recovery.pdf},

doi = {https://doi.org/10.1007/978-3-319-24574-4_56},

year  = {2015},

date = {2015-01-01},

urldate = {2015-01-01},

booktitle = {Medical Image Computing and Computer-Assisted Intervention},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{rubio:CVPR:2015,

title = {Regularizing Max-Margin Exemplars by Reconstruction and Generative Models},

author = {J. C. Rubio and Björn Ommer},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Regularizing-Max-Margin-Exemplars-by-Reconstruction-and-Generative-Models.pdf},

year  = {2015},

date = {2015-01-01},

urldate = {2015-01-01},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},

pages = {4213--4221},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{antic:ICCV:2015,

title = {Per-Sample Kernel Adaptation for Visual Recognition and Grouping},

author = {B. Antic and Björn Ommer},

url = {https://ieeexplore.ieee.org/document/7410505

https://ommer-lab.com/wp-content/uploads/2021/10/Per-Sample-Kernel-Adaptation-for-Visual-Recognition-and-Grouping.pdf},

year  = {2015},

date = {2015-01-01},

urldate = {2015-01-01},

booktitle = {Proceedings of the IEEE International Conference on Computer Vision},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{takami:GCH:2014,

title = {An Approach to Large Scale Interactive Retrieval of Cultural Heritage},

author = {M. Takami and P. Bell and Björn Ommer},

url = {https://hci.iwr.uni-heidelberg.de/compvis/projects/digihum

https://ommer-lab.com/wp-content/uploads/2021/10/An-Approach-to-Large-Scale-Interactive-Retrieval-of-Cultural-Heritage.pdf},

year  = {2014},

date = {2014-01-01},

urldate = {2014-01-01},

booktitle = {Eurographics Workshop on Graphics and Cultural Heritage},

publisher = {The Eurographics Association},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{takami:WACV:2014,

title = {Offline Learning of Prototypical Negatives for Efficient Online Exemplar SVM},

author = {M. Takami and P. Bell and Björn Ommer},

url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6836075},

year  = {2014},

date = {2014-01-01},

urldate = {2014-01-01},

booktitle = {Winter Conference on Applications of Computer Vision},

pages = {377--384},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{kandemir:MICCAI:2014,

title = {Event Detection by Feature Unpredictability in Phase-Contrast Videos of Cell Cultures},

author = {M Kandemir and J. C. Rubio and U. Schmidt and C. Wojek and J. Welbl and Björn Ommer and Fred A. Hamprecht},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Event-Detection-by-Feature-Unpredictability-in-Phase-Contrast-Videos.pdf},

year  = {2014},

date = {2014-01-01},

urldate = {2014-01-01},

booktitle = {Medical Image Computing and Computer-Assisted Intervention},

pages = {154--161},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{antic:ECCV:2014,

title = {Learning Latent Constituents for Recognition of Group Activities in Video},

author = {B. Antic and Björn Ommer},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Learning-Latent-Constituents-for-Recognition-of-Group-Activities-in-Video.pdf},

year  = {2014},

date = {2014-01-01},

urldate = {2014-01-01},

booktitle = {Proceedings of the European Conference on Computer Vision (ECCV) (Oral)},

pages = {33--47},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{eigenstetter:CVPR:2014,

title = {Randomized Max-Margin Compositions for Visual Recognition},

author = {A. Eigenstetter and M. Takami and Björn Ommer},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Randomized-Max-Margin-Compositions-for-Visual-Recognition.pdf},

year  = {2014},

date = {2014-01-01},

urldate = {2014-01-01},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},

pages = {3590--3597},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{antic:HACI:2013,

title = {Less is More: Video Trimming for Action Recognition},

author = {B. Antic and Timo Milbich and Björn Ommer},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Less-is-More_Video-Trimming-for-Action-Recognition.pdf},

year  = {2013},

date = {2013-01-01},

urldate = {2013-01-01},

booktitle = {Proceedings of the IEEE International Conference on Computer Vision, Workshop on Understanding Human Activities: Context and Interaction},

pages = {515--521},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{arnold:SCCH:2013,

title = {Automated Learning of Self-Similarity and Informative Structures in Architecture},

author = {M. Arnold and P. Bell and Björn Ommer},

year  = {2013},

date = {2013-01-01},

booktitle = {Scientific Computing & Cultural Heritage},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{monroy:SCCH:2013,

title = {A Morphometric Approach to Reception Analysis of Premodern Art},

author = {A. Monroy and P. Bell and Björn Ommer},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/A-Morphometric-Approach-to-Reception-Analysis-of-Premodern-Art.pdf},

year  = {2013},

date = {2013-01-01},

urldate = {2013-01-01},

booktitle = {Scientific Computing & Cultural Heritage},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{eigenstetter:NIPS:2012,

title = {Visual Recognition using Embedded Feature Selection for Curvature Self-Similarity},

author = {A. Eigenstetter and Björn Ommer},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Visual-Recognition-using-Embedded-Feature-Selection.pdf},

year  = {2012},

date = {2012-01-01},

urldate = {2012-01-01},

booktitle = {Proceedings of the Conference on Advances in Neural Information Processing Systems},

pages = {377--385},

publisher = {MIT Press},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{yarlagadda:ECCV:2012,

title = {From Meaningful Contours to Discriminative Object Shape},

author = {P. Yarlagadda and Björn Ommer},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/From-Meaningful-Contours-to-Discriminative-Object-Shape.pdf},

year  = {2012},

date = {2012-01-01},

urldate = {2012-01-01},

booktitle = {Proceedings of the European Conference on Computer Vision},

volume = {7572},

pages = {766--779},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{monroy:ECCV:2012,

title = {Shaping Art with Art: Morphological Analysis for Investigating Artistic Reproductions},

author = {A. Monroy and P. Bell and Björn Ommer},

url = {https://hci.iwr.uni-heidelberg.de/compvis/projects/digihum

https://ommer-lab.com/wp-content/uploads/2021/10/Shaping-Art-with-Art_Morphological-Analysis-for-Investigating-Artistic-Reproductions.pdf},

year  = {2012},

date = {2012-01-01},

urldate = {2012-01-01},

booktitle = {Proceedings of the European Conference on Computer Vision, Workshop on VISART},

volume = {7583},

pages = {571--580},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{eigenstetter:ACCV:2012,

title = {Max-Margin Regularization for Reducing Accidentalness in Chamfer Matching},

author = {A. Eigenstetter and P. Yarlagadda and Björn Ommer},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Max-margin-Regularization-for-Reducing-Accidentalness-in-Chamfer-Matching.pdf},

year  = {2012},

date = {2012-01-01},

urldate = {2012-01-01},

booktitle = {Proceedings of the Asian Conference on Computer Vision},

pages = {152--163},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{antic:ACCV:2012,

title = {Robust Multiple-Instance Learning with Superbags},

author = {B. Antic and Björn Ommer},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Robust-Multiple-Instance-Learning-with-Superbags.pdf},

year  = {2012},

date = {2012-01-01},

urldate = {2012-01-01},

booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV) (Oral)},

pages = {242--255},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{yarlagadda:BMVC:2012,

title = {Learning Discriminative Chamfer Regularization},

author = {P. Yarlagadda and A. Eigenstetter and Björn Ommer},

url = {https://hci.iwr.uni-heidelberg.de/content/max-margin-regularization-chamfer-matching

http://www.bmva.org/bmvc/2012/BMVC/paper020/paper020.pdf},

year  = {2012},

date = {2012-01-01},

urldate = {2012-01-01},

booktitle = {BMVC},

pages = {1--11},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{antic:ICCV:2011,

title = {Video Parsing for Abnormality Detection},

author = {B. Antic and Björn Ommer},

url = {https://hci.iwr.uni-heidelberg.de/content/video-parsing-abnormality-detection

https://ommer-lab.com/wp-content/uploads/2021/10/Video-Parsing-for-Abnormality-Detection.pdf},

year  = {2011},

date = {2011-01-01},

urldate = {2011-01-01},

booktitle = {Proceedings of the IEEE International Conference on Computer Vision},

pages = {2415--2422},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{schlecht:BMVC:2011,

title = {Contour-based Object Detection},

author = {J. Schlecht and Björn Ommer},

url = {https://hci.iwr.uni-heidelberg.de/content/contour-based-object-detection

https://ommer-lab.com/wp-content/uploads/2021/10/Contour-based-Object-Detection.pdf},

year  = {2011},

date = {2011-01-01},

urldate = {2011-01-01},

booktitle = {BMVC},

pages = {1--9},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{schlecht:ICIP:2011,

title = {Detecting Gestures in Medieval Images},

author = {J. Schlecht and Bernd Carque and Björn Ommer},

url = {https://hci.iwr.uni-heidelberg.de/compvis/projects/digihum

https://ommer-lab.com/wp-content/uploads/2021/10/Detecting-Gestures-in-Medieval-Images.pdf},

year  = {2011},

date = {2011-01-01},

urldate = {2011-01-01},

booktitle = {Proceedings of the International Conference on Image Processing},

pages = {1309--1312},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{monroy:ICIP:2011,

title = {Reconstructing the Drawing Process of Reproductions from Medieval Images},

author = {A. Monroy and Bernd Carque and Björn Ommer},

url = {https://hci.iwr.uni-heidelberg.de/content/reconstructing-drawing-process-reproductions-medieval-images

https://ommer-lab.com/wp-content/uploads/2021/10/Reconstructing-the-Drawing-Process-of-Reproductions-from-Medieval-Images.pdf

},

year  = {2011},

date = {2011-01-01},

urldate = {2011-01-01},

booktitle = {Proceedings of the International Conference on Image Processing},

pages = {2974--2977},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{monroy:SCCH:2011,

title = {Parametric Object Detection for Iconographic Analysis},

author = {A. Monroy and Thorben Kröger and M. Arnold and Björn Ommer},

url = {https://hci.iwr.uni-heidelberg.de/compvis/projects/digihum

http://www.academia.edu/9439693/Parametric_Object_Detection_for_Iconographic_Analysis},

year  = {2011},

date = {2011-01-01},

urldate = {2011-01-01},

booktitle = {Scientific Computing & Cultural Heritage},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{yarlagadda:_:2011,

title = {Top-down Analysis of Low-level Object Relatedness Leading to Semantic Understanding of Medieval Image Collections},

author = {P. Yarlagadda and A. Monroy and Bernd Carque and Björn Ommer},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Top-Down-Analysis-of-Low-Level-Object-Relatedness-Leading-to-Semantic-Understanding-of-Medieval-Image-Collections.pdf},

year  = {2011},

date = {2011-01-01},

urldate = {2011-01-01},

booktitle = {Conference on Computer Vision and Image Analysis of Art II},

volume = {7869},

pages = {61--69},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{monroy:ICIP:2011b,

title = {Beyond Straight Lines - Object Detection using Curvature},

author = {A. Monroy and A. Eigenstetter and Björn Ommer},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Beyond-Straight-Lines_Object-Detection-Using-Curvature.pdf},

doi = {10.1109/ICIP.2011.6116485},

year  = {2011},

date = {2011-01-01},

urldate = {2011-01-01},

booktitle = {International Conference on Image Processing (ICIP)},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{yarlagadda:ECCV:2010,

title = {Voting by Grouping Dependent Parts},

author = {P. Yarlagadda and A. Monroy and Björn Ommer},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Voting-by-Grouping-Dependent-Parts.pdf},

year  = {2010},

date = {2010-01-01},

urldate = {2010-01-01},

booktitle = {Proceedings of the European Conference on Computer Vision},

volume = {6315},

pages = {197--210},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{wagner:ACCV:2010,

title = {Efficiently Clustering Earth Mover's Distance},

author = {J. Wagner and Björn Ommer},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Efficiently-Clustering-Earth-Movers-Distance.pdf},

year  = {2010},

date = {2010-01-01},

urldate = {2010-01-01},

booktitle = {Proceedings of the Asian Conference on Computer Vision},

pages = {477--488},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{yarlagadda:ACCV:2010,

title = {Recognition and Analysis of Objects in Medieval Images},

author = {P. Yarlagadda and A. Monroy and Bernd Carque and Björn Ommer},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Recognition-and-Analysis-of-Objects-in-Medieval-Images.pdf},

year  = {2010},

date = {2010-01-01},

urldate = {2010-01-01},

booktitle = {Proceedings of the Asian Conference on Computer Vision, Workshop on e-Heritage},

pages = {296--305},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{ommer:ICCV:2009,

title = {Multi-scale Object Detection by Clustering Lines},

author = {Björn Ommer and J. Malik},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Multi-Scale-Object-Detection-by-Clustering-Lines.pdf},

year  = {2009},

date = {2009-01-01},

urldate = {2009-01-01},

booktitle = {Proceedings of the IEEE International Conference on Computer Vision},

pages = {484--491},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{yarlagadda:SCCH:2009,

title = {Towards a Computer-based Understanding of Medieval Images},

author = {P. Yarlagadda and A. Monroy and Bernd Carque and Björn Ommer},

url = {https://hci.iwr.uni-heidelberg.de/content/visual-object-recognition-datasets-pre-modern-images

https://link.springer.com/chapter/10.1007/978-3-642-28021-4_10},

year  = {2009},

date = {2009-01-01},

urldate = {2009-01-01},

booktitle = {Scientific Computing & Cultural Heritage},

pages = {89--97},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{keraenen:2009,

title = {Computational Analysis of Quantitative Changes in Gene Expression and Embryo Morphology between Species},

author = {S. V. E. Keränen and A. DePace and C. L. Luengo Hendriks and C. Fowlkes and P. Arbelaez and Björn Ommer and T. Brox and C. Henriquez and Z. Wunderlich and K. Eckenrode and B. Fischer and A. Hammonds and S. E. Celniker},

year  = {2009},

date = {2009-01-01},

urldate = {2009-01-01},

booktitle = {Evolution-The Molecular Landscape},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{ommer:EMMCVPR:2007,

title = {Compositional Object Recognition, Segmentation, and Tracking in Video},

author = {Björn Ommer and J. M. Buhmann},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Compositional-Object-Recognition_Segmentation_and-Tracking-in-Video.pdf},

year  = {2007},

date = {2007-01-01},

urldate = {2007-01-01},

booktitle = {Proceedings of the International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition},

volume = {4679},

pages = {318--333},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{sigg:MLSP:2007,

title = {Nonnegative CCA for Audiovisual Source Separation},

author = {C. Sigg and B. Fischer and Björn Ommer and V. Roth and J. M. Buhmann},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Nonnegative-CCA-for-Audiovisual-Source-Separation.pdf},

year  = {2007},

date = {2007-01-01},

urldate = {2007-01-01},

booktitle = {International Workshop on Machine Learning for Signal Processing},

pages = {253--258},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{ommer:CVPR:2007,

title = {Learning the Compositional Nature of Visual Objects},

author = {Björn Ommer and J. M. Buhmann},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Learning-the-Compositional-Nature-of-Visual-Objects.pdf},

year  = {2007},

date = {2007-01-01},

urldate = {2007-01-01},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},

pages = {1--8},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{roth:DAGM:2006,

title = {Exploiting Low-level Image Segmentation for Object Recognition},

author = {V. Roth and Björn Ommer},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Exploiting-Low-level-Image-Segmentation-for-Object-Recognition.pdf},

year  = {2006},

date = {2006-01-01},

urldate = {2006-01-01},

booktitle = {Pattern Recognition, Symposium of the DAGM},

volume = {4174},

pages = {11--20},

publisher = {Springer},

organization = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{ommer:CVPR:2006,

title = {Learning Top-Down Grouping of Compositional Hierarchies for Recognition},

author = {Björn Ommer and M. Sauter and Buhmann J. M.},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Learning-Top-Down-Grouping-of-Compositional-Hierarchies-for-Recognition.pdf},

year  = {2006},

date = {2006-01-01},

urldate = {2006-01-01},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Workshop on Perceptual Organization in Computer Vision},

pages = {194--194},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{ommer:ECCV:2006,

title = {Learning Compositional Categorization Models},

author = {Björn Ommer and J. M. Buhmann},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Learning-Compositional-Categorization-Models.pdf},

year  = {2006},

date = {2006-01-01},

urldate = {2006-01-01},

booktitle = {Proceedings of the European Conference on Computer Vision},

volume = {3953},

pages = {316--329},

publisher = {Springer},

organization = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{ommer:EMMCVPR:2005,

title = {Object Categorization by Compositional Graphical Models},

author = {Björn Ommer and J. M. Buhmann},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/Object-Categorization-by-Compositional-Graphical-Models.pdf},

year  = {2005},

date = {2005-01-01},

urldate = {2005-01-01},

booktitle = {Proceedings of the International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition},

volume = {3757},

pages = {235--250},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{ommer:EMMCVPR:2003,

title = {A Compositionality Architecture for Perceptual Feature Grouping},

author = {Björn Ommer and J. M. Buhmann},

url = {https://ommer-lab.com/wp-content/uploads/2021/10/A-Compositionality-Architecture-for-Perceptual-Feature-Grouping.pdf},

year  = {2003},

date = {2003-01-01},

urldate = {2003-01-01},

booktitle = {Proceedings of the International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition},

volume = {2683},

pages = {275--290},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}