3 citations · 8 across the 5 of their papers we have counts for
5 papers
Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems
David T. Hoffmann, Simon Schrodi, Jelena Bratulić +3
In this work, we study rapid improvements of the training loss in transformers when being confronted with multi-step decision tasks. We found that transformers struggle to learn th…
Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation
Nadine Behrmann, S. Alireza Golestaneh, Zico Kolter +2
This paper introduces a unified framework for video action segmentation via sequence to sequence (seq2seq) translation in a fully and timestamp supervised setup. In contrast to cur…
Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives
David T. Hoffmann, Nadine Behrmann, Juergen Gall +2
This paper introduces Ranking Info Noise Contrastive Estimation (RINCE), a new member in the family of InfoNCE losses that preserves a ranked ordering of positive samples. In contr…
Long Short View Feature Decomposition via Contrastive Video Representation Learning
Nadine Behrmann, Mohsen Fayyaz, Juergen Gall +1
Self-supervised video representation methods typically focus on the representation of temporal attributes in videos. However, the role of stationary versus non-stationary attribute…
Unsupervised Video Representation Learning by Bidirectional Feature Prediction
Nadine Behrmann, Juergen Gall, Mehdi Noroozi
This paper introduces a novel method for self-supervised video representation learning via feature prediction. In contrast to the previous methods that focus on future feature pred…