Robust Action Segmentation from Timestamp Supervision
This work addresses the challenge of incomplete annotations in weakly supervised action segmentation for video analysis, representing an incremental improvement over prior timestamp-based methods.
The paper tackles the problem of action segmentation from timestamp supervision by relaxing the assumption that every action instance is annotated, addressing missing annotations. The result shows that their approach is more robust to missing annotations compared to other methods and baselines.
Action segmentation is the task of predicting an action label for each frame of an untrimmed video. As obtaining annotations to train an approach for action segmentation in a fully supervised way is expensive, various approaches have been proposed to train action segmentation models using different forms of weak supervision, e.g., action transcripts, action sets, or more recently timestamps. Timestamp supervision is a promising type of weak supervision as obtaining one timestamp per action is less expensive than annotating all frames, but it provides more information than other forms of weak supervision. However, previous works assume that every action instance is annotated with a timestamp, which is a restrictive assumption since it assumes that annotators do not miss any action. In this work, we relax this restrictive assumption and take missing annotations for some action instances into account. We show that our approach is more robust to missing annotations compared to other approaches and various baselines.