Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition
This work addresses the challenge of robust video action recognition in the wild, offering a novel motion representation that complements existing methods.
The paper tackled the problem of learning motion dynamics in videos by proposing a spatio-temporal self-similarity (STSS) representation, which achieved state-of-the-art results on action recognition benchmarks such as Something-Something-V1 & V2, Diving-48, and FineGym.
Spatio-temporal convolution often fails to learn motion dynamics in videos and thus an effective motion representation is required for video understanding in the wild. In this paper, we propose a rich and robust motion representation based on spatio-temporal self-similarity (STSS). Given a sequence of frames, STSS represents each local region as similarities to its neighbors in space and time. By converting appearance features into relational values, it enables the learner to better recognize structural patterns in space and time. We leverage the whole volume of STSS and let our model learn to extract an effective motion representation from it. The proposed neural block, dubbed SELFY, can be easily inserted into neural architectures and trained end-to-end without additional supervision. With a sufficient volume of the neighborhood in space and time, it effectively captures long-term interaction and fast motion in the video, leading to robust action recognition. Our experimental analysis demonstrates its superiority over previous methods for motion modeling as well as its complementarity to spatio-temporal features from direct convolution. On the standard action recognition benchmarks, Something-Something-V1 & V2, Diving-48, and FineGym, the proposed method achieves the state-of-the-art results.