SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentation
This addresses the costly annotation problem in video analysis for researchers and practitioners, but it is incremental as it builds on existing weakly supervised methods.
The paper tackles the problem of weakly supervised temporal action segmentation by learning from videos with only a list of actions, without timing or order information, and achieves state-of-the-art results on three datasets.
Temporal action segmentation is a topic of increasing interest, however, annotating each frame in a video is cumbersome and costly. Weakly supervised approaches therefore aim at learning temporal action segmentation from videos that are only weakly labeled. In this work, we assume that for each training video only the list of actions is given that occur in the video, but not when, how often, and in which order they occur. In order to address this task, we propose an approach that can be trained end-to-end on such data. The approach divides the video into smaller temporal regions and predicts for each region the action label and its length. In addition, the network estimates the action labels for each frame. By measuring how consistent the frame-wise predictions are with respect to the temporal regions and the annotated action labels, the network learns to divide a video into class-consistent regions. We evaluate our approach on three datasets where the approach achieves state-of-the-art results.