Large-scale weakly-supervised pre-training for video action recognition
This addresses the bottleneck of data scarcity in video action recognition for researchers and practitioners, though it is incremental as it builds on existing weakly-supervised pre-training methods.
The paper tackled the problem of limited fully-supervised video datasets for action recognition by pre-training models on a large-scale weakly-supervised dataset of over 65 million noisy web videos, which substantially improved state-of-the-art results on three challenging public datasets.
Current fully-supervised video datasets consist of only a few hundred thousand videos and fewer than a thousand domain-specific labels. This hinders the progress towards advanced video architectures. This paper presents an in-depth study of using large volumes of web videos for pre-training video models for the task of action recognition. Our primary empirical finding is that pre-training at a very large scale (over 65 million videos), despite on noisy social-media videos and hashtags, substantially improves the state-of-the-art on three challenging public action recognition datasets. Further, we examine three questions in the construction of weakly-supervised video action datasets. First, given that actions involve interactions with objects, how should one construct a verb-object pre-training label space to benefit transfer learning the most? Second, frame-based models perform quite well on action recognition; is pre-training for good image features sufficient or is pre-training for spatio-temporal features valuable for optimal transfer learning? Finally, actions are generally less well-localized in long videos vs. short videos; since action labels are provided at a video level, how should one choose video clips for best performance, given some fixed budget of number or minutes of videos?