I Know How You Move: Explicit Motion Estimation for Human Action Recognition

Enabled by hierarchical convolutions and nonlinear mappings, recent action recognition studies have continuously boosted performance with spatiotemporal modelling. In general, motion clues are essential in video-oriented tasks, while existing approaches aggregate the spatial and temporal signatures via specially designed modules in the middle or output stages. To highlight the privilege provided by temporal motions, in this paper, we propose a simple but effective
MOTion Estimator
(MOTE) to generate the motion patterns from every single frame, avoiding complex dense-frame input. In particular, MOTE follows an encoder-decoder structure, which takes the short-term motion features generated by the pretrained dense-frame network as the learning target. The spatial information of a single frame is utilized to estimate the instantaneous motion appearance. It can support the expression of vulnerable regions, such as the ‘hand’ in ‘waving hands’, which would otherwise be suppressed in the feature maps as the ‘hand’ suffers from motion blur. The training process of MOTE is independent of the action recognition system. Therefore, the trained MOTE can be transplanted to the input-end of existing action recognition methods to provide instantaneous motion estimation as feature enhancement according to practical requirements. Our experiments performed on Something-Something V1, V2, Kinetics-400, and Diving48 verify the effectiveness of the proposed method.