Action Recognition from Single Timestamp Supervision in Untrimmed Videos
This addresses the labeling cost and subjectivity issue for researchers and practitioners in video analysis, though it is incremental as it builds on weak supervision methods.
The paper tackles the problem of action recognition in untrimmed videos by proposing a method supervised with single timestamps instead of expensive start-end labels, showing it performs comparably to full supervision and improves top-1 test accuracy by up to 5.4%.
Recognising actions in videos relies on labelled supervision during training, typically the start and end times of each action instance. This supervision is not only subjective, but also expensive to acquire. Weak video-level supervision has been successfully exploited for recognition in untrimmed videos, however it is challenged when the number of different actions in training videos increases. We propose a method that is supervised by single timestamps located around each action instance, in untrimmed videos. We replace expensive action bounds with sampling distributions initialised from these timestamps. We then use the classifier's response to iteratively update the sampling distributions. We demonstrate that these distributions converge to the location and extent of discriminative action segments. We evaluate our method on three datasets for fine-grained recognition, with increasing number of different actions per video, and show that single timestamps offer a reasonable compromise between recognition performance and labelling effort, performing comparably to full temporal supervision. Our update method improves top-1 test accuracy by up to 5.4%. across the evaluated datasets.