Temporal Difference Networks for Action Recognition

Temporal modeling still remains challenging for action recognition in videos. To mitigate this issue, this paper presents a new video architecture, termed as Temporal Difference Network (TDN), with a focus on capturing multi-scale temporal information for efficient action recognition. The core of our TDN is to devise an efficient temporal module (TDM) by explicitly leveraging a temporal difference operator, and systematically assess its effect on short-term and long-term motion modeling. To fully capture temporal information over the entire video, our TDN is established with a two-level difference modeling paradigm. Specifically, for local motion modeling, temporal difference over consecutive frames is used to supply 2D CNNs with finer motion pattern, while for global motion modeling, temporal difference across segments is incorporated to capture long-range structure for motion feature excitation. TDN provides a simple and principled temporal modeling framework, and could be instantiated with the existing CNNs at a small extra computational cost. Our TDN presents a new state of the art on the datasets of Something-Something V1 \& V2 and Kinetics-400 under the setting of using similar backbones. In addition, we present some visualization results on our TDN and try to provide new insights on temporal difference operation.