Image and video classification are distinct tasks in computer vision. Three-dimensional
convolutional neural networks (3D CNNs) are commonly employed for video classification …

Structured data storage of surveillance video helps to reduce the time for information
retrieval. However, modern surveillance systems have to perform the compressing and …

Transformer-based models have achieved top performance on major video recognition
benchmarks. Benefiting from the self-attention mechanism, these models show stronger …

Automatically recognizing facial expressions in video sequences is a challenging task
because there is little direct correlation between facial features and subjective emotions in …

As an important research direction in image and video processing, set-based video
recognition requires speed and accuracy. However, the existing static modeling methods …

Patternrecognitionmodels are usually used in a variety of applications ranging from video
concept annotation to event detection. In this paper we propose a new framework called the …

Efficiency is an important issue in designing video architectures for action recognition. 3D
CNNs have witnessed remarkable progress in action recognition from videos. However …

VR video recognition in complex environment, a motion recognition algorithm based on two-
feature fusion and adaptive enhancement is proposed to solve the problems of inaccurate …

In recent years, vision Transformers and MLPs have demonstrated remarkable performance
in image understanding tasks. However, their inherently dense computational operators …

This supplementary material contains additional details of the main manuscript, and
provides more experiment analysis. In Sec. 1, we present the details of our proposed …