Action Recognition in Unconstrained Videos
Action Recognition in videos is an active research field that is fueled by an acute need, spanning several application domains. Still, existing systems fall short of the applications' needs in real-world scenarios, where the quality of the video is less than optimal and the viewpoint is uncontrolled and often not static.
Over the years, we have developed multiple action recognition systems that acheived top-level performance. Currently, we are considering the key elements of motion encoding and focus on capturing local changes in motion directions. In addition, we decouple image edges from motion edges using a suppression mechanism, and compensate for global camera motion by using an especially fitted registration scheme.
Combined with various vectorization technique, our methods achieves state-of-the-art performance in the most recent and challenging benchmarks.