Mingqi Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mingqi Li has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Changji Wen
College of Information Technology, Jilin Agricultural University, Changchun 130118, China
1 shared publication - Chenshuang Li
College of Information and Technology, JiLin Agricultural University, Changchun 130118, China
1 shared publication - Hengqiang Su
College of Information and Technology, JiLin Agricultural University, Changchun 130118, China
1 shared publication - Hongbing Chen
College of Information Technology, Jilin Agricultural University, Changchun 130118, China
1 shared publication - Hongrui Chen
College of Information and Technology, JiLin Agricultural University, Changchun 130118, China
1 shared publication - Patrick Sun
Letter and Science, University of Wisconsin, Madison, WI 53707, USA
1 shared publication
Latest Publications
- Open Access
- 23 March 2026
- Published by MDPI AG in Electronics
- Vol. 15 (6) , 1338
ETMamba: An Effective Temporal Model for Video Action Recognition
Video action recognition faces persistent challenges in balancing accuracy with computational efficiency. While state space models, such as Mamba, have emerged with linear complexity advantages, they exhibit inefficiency in capturing critical spatiotemporal dependencies within video data. To address this core limitation, this paper proposes ETMamba, an enhanced architecture built upon the Mamba baseline. The ETMamba achieve performance breakthroughs via three core innovation modules: (1) the Spatiotemporal Feature Preservation module retains complete original spatiotemporal correlations before data flattening, solving the problem of spatiotemporal feature loss; (2) the Efficient Bidirectional Sharing strategy accurately models bidirectional temporal dependencies, enhancing key temporal dynamic information; and (3) the Spatiotemporal Collaborative Modulation mechanism combines global temporal and local spatial information to achieve collaborative capture of long-short term dependencies and fine-grained features. We conduct experiments on multiple benchmark datasets, achieving recognition accuracies of 88.3%, 74.6%, 75.7%, and 98.1% on Kinetics-400, Something-Something V2, HMDB-51, and Breakfast datasets, respectively, while maintaining low to medium computational complexity.
- 23 March 2026
- Published by MDPI AG in Electronics
- Vol. 15 (6) , 1338
Open AccessETMamba: An Effective Temporal Model for Video Action Recognition
Video action recognition faces persistent challenges in balancing accuracy with computational efficiency. While state space models, such as Mamba, have emerged with linear complexity advantages, they exhibit inefficiency in capturing critical spatiotemporal dependencies within video data. To address this core limitation, this paper proposes ETMamba, an enhanced architecture built upon the Mamba baseline. The ETMamba achieve performance breakthroughs via three core innovation modules: (1) the Spatiotemporal Feature Preservation module retains complete original spatiotemporal correlations before data flattening, solving the problem of spatiotemporal feature loss; (2) the Efficient Bidirectional Sharing strategy accurately models bidirectional temporal dependencies, enhancing key temporal dynamic information; and (3) the Spatiotemporal Collaborative Modulation mechanism combines global temporal and local spatial information to achieve collaborative capture of long-short term dependencies and fine-grained features. We conduct experiments on multiple benchmark datasets, achieving recognition accuracies of 88.3%, 74.6%, 75.7%, and 98.1% on Kinetics-400, Something-Something V2, HMDB-51, and Breakfast datasets, respectively, while maintaining low to medium computational complexity.