Work

Visual transformer with depthwise separable convolution projections for video-based human action recognition

Year: 2025

Type: conference-paper

Abstract: Human action recognition is a task that utilizes algorithms to recognize human actions from videos. Transformer-based algorithms have attracted growing attention in recent years. However, transformer networks often suffer from slow convergence and require large amounts of training data, due to their inability to prioritize information from neighboring pixels. To address these issues, we propose a novel network architecture that combines a depthwise separable convolution layer with transformer modules. The proposed network has been evaluated on the medium-sized benchmark dataset UCF101 and the results have demonstrated that the proposed model converges quickly during training and achieves competitive performance compared with SOTA pure transformer network, while reducing approximately 7.4 million parameters.

Source: MATEC Web of Conferences

DOI: 10.1051/matecconf/202541306003

Authors: Yu Cao, Fang Wang, Qiusheng Zheng

Institutions: Zhongyuan University of Technology, Brunel University of London

Language: English

Topic: Human Pose and Action Recognition

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

Funder: Zhongyuan University of Technology

OpenAlex ID: W4414708809