Abstract: Traditional video action detectors typically adopt the two-stage pipeline, where a person detector is first employed to generate actor boxes and then 3D RoIAlign is used to extract ...
Abstract: Directly recognizing action based on compressed video shows significant advantages, such as low storage demands, efficient decoding, and fast inference speeds. Existing methods on compressed ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results