Video understanding usually requires expensive computation that prohibits its deployment,
yet videos contain significant spatiotemporal redundancy that can be exploited. In particular …

Not all video frames are equally informative for recognizing an action. It is computationally
infeasible to train deep networks on all video frames when actions develop over hundreds of …

Although CNN has reached satisfactory performance in image-related tasks, using CNN to
process videos is much more challenging due to the enormous size of raw video streams. In …

Most existing action recognition models are large convolutional neural networks that work
only with raw RGB frames as input. However, practical applications require lightweight …

Motion has shown to be useful for video understanding, where motion is typically
represented by optical flow. However, computing flow from video frames is very …

In video action recognition, motion is a very crucial clue, which is usually represented by
optical flow. However, optical flow is computationally expensive to obtain, which becomes …

Training an effective video action recognition model poses significant computational
challenges, particularly under limited resource budgets. Current methods primarily aim to …

We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway,
operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, operating …

Though action recognition in videos has achieved great success recently, it remains a
challenging task due to the massive computational cost. Designing lightweight networks is a …

Frame sampling is a fundamental problem in video action recognition due to the essential
redundancy in time and limited computation resources. The existing sampling strategy often …