Flow Dynamics Correction for Action Recognition
This work addresses the need for more accurate motion representation in action recognition, particularly for models relying on optical flow, but it is incremental as it builds on existing methods with a correction technique.
The paper tackled the problem of improving action recognition by correcting optical flow dynamics through power normalization to enhance subtle or dampen sudden motions, resulting in new state-of-the-art performance on benchmarks such as HMDB-51, YUP++, MPII Cooking Activities, and Charades.
Various research studies indicate that action recognition performance highly depends on the types of motions being extracted and how accurate the human actions are represented. In this paper, we investigate different optical flow, and features extracted from these optical flow that capturing both short-term and long-term motion dynamics. We perform power normalization on the magnitude component of optical flow for flow dynamics correction to boost subtle or dampen sudden motions. We show that existing action recognition models which rely on optical flow are able to get performance boosted with our corrected optical flow. To further improve performance, we integrate our corrected flow dynamics into popular models through a simple hallucination step by selecting only the best performing optical flow features, and we show that by 'translating' the CNN feature maps into these optical flow features with different scales of motions leads to the new state-of-the-art performance on several benchmarks including HMDB-51, YUP++, fine-grained action recognition on MPII Cooking Activities, and large-scale Charades.