Publications
inproceedings
T. Milbich, Roth, K., Sinha, S., Schmidt, L., Ghassemi, M., and Ommer, B.,
“Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning”. 2021.
Conference Proceedings
M. Dorkenwald, Milbich, T., Blattmann, A., Rombach, R., Derpanis, K. G., and Ommer, B.,
“Stochastic Image-to-Video Synthesis usin cINNs”,
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2021.
K. Roth, Milbich, T., Ommer, B., Cohen, J. Paul, and Ghassemi, M.,
“S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learning”,
Proceedings of International Conference on Machine Learning (ICML). 2021.
K. Roth, Milbich, T., Sinha, S., Gupta, P., Ommer, B., and Cohen, J. Paul,
“Revisiting Training Strategies and Generalization Performance in Deep Metric Learning”,
International Conference on Machine Learning (ICML). 2020.
T. Milbich, Roth, K., Bharadhwaj, H., Sinha, S., Bengio, Y., Ommer, B., and Cohen, J. Paul,
“DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning”,
IEEE European Conference on Computer Vision (ECCV). 2020.
A. Blattmann, Milbich, T., Dorkenwald, M., and Ommer, B.,
“Behavior-Driven Synthesis of Human Dynamics”,
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2021.
Conference Paper
D. Lorenz, Bereska, L., Milbich, T., and Ommer, B.,
“Unsupervised Part-Based Disentangling of Object Shape and Appearance”, in
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (Oral + Best paper finalist: top 45 / 5160 submissions), 2019.
T. Milbich, Roth, K., and Ommer, B.,
“PADS: Policy-Adapted Sampling for Visual Similarity Learning”, in
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020, vol. 1, no. 1.
B. Antic, Milbich, T., and Ommer, B.,
“Less is More: Video Trimming for Action Recognition”, in
Proceedings of the IEEE International Conference on Computer Vision, Workshop on Understanding Human Activities: Context and Interaction, 2013, p. 515--521.
Technical Report (984.89 KB)