We present a simple approach which can turn a ViT encoder into an efficient video model,
which can seamlessly work with both image and video inputs. By sparsely sampling the …

Transformers have become the primary backbone of the computer vision community due to
their impressive performance. However, the unfriendly computation cost impedes their …

Streaming video clips with large-scale video tokens impede vision transformers (ViTs) for
efficient recognition, especially in video action detection where sufficient spatiotemporal …

We present a new algorithm for the selection of informative frames in video action
recognition. Our approach is designed for aerial videos captured using a moving camera …

In the domain of video recognition, video transformers have demonstrated remarkable
performance, albeit at significant computational cost. This paper introduces TSNet, an …

Recently emerged Masked Video Modeling techniques demonstrated their potential by
significantly outperforming previous methods in self-supervised learning for video. However …

We present a new general learning approach, Prompt Learning for Action Recognition
(PLAR), which leverages the strengths of prompt learning to guide the learning process. Our …

Transformer has exhibited promising performance in various video recognition tasks but
brings a huge computational cost in modeling spatial-temporal cues. This work aims to boost …

Several efforts have been made to develop effective and robust vision-based solutions for
human action recognition in aerial videos. Generally, the existing methods rely on the …

视频特征包含了行为执行时的时间, 空间冗余信息. 该信息和行为类别无关, 会干扰行为识别,
造成行为类别的错误判断. 本文提出了一种基于时空采样的视频行为识别模型 …