Long-tailed Action Recognition
Long-Tailed Action Recognition is an action recognition paradigm that addresses the challenge of learning from imbalanced datasets by distinguishing actions under a long-tailed class distribution where a few categories dominate while the majority are underrepresented.
17
Publications
598
Citations
78
Authors
30
Institutions
Publications per year
2017–2026
17
Parents
17
A Survey on Long-Tailed Visual Recognition
Lu Yang, He Jiang, Qing Song et al. · International Journal of Computer Vision · 2022 · 145 citations · Full text
Learning Imbalanced Data with Vision Transformers
Zhengzhuo Xu, Ruikang Liu, Shuo Yang et al. · 2023 · 50 citations
Towards All-in-One Pre-Training via Maximizing Multi-Modal Mutual Information
Weijie Su, Xizhou Zhu, Chenxin Tao et al. · 2023 · 43 citations
Learning to Learn from Noisy Web Videos
Serena Yeung, Vignesh Ramanathan, Olga Russakovsky et al. · 2017 · 27 citations
1–5 of 17
78
2
h-index
2
h-index
2
h-index
1
h-index
1
h-index
1–5 of 78
30

Beijing University of Posts and Telecommunications
Beijing, China
3 h-index
10 publications
669 citations
Tsinghua University
Beijing, China
3 h-index
10 publications
436 citations
University of Washington
Seattle, United States
2 h-index
6 publications
429 citations
Beijing Academy of Artificial Intelligence
Beijing, China
2 h-index
6 publications
233 citations
University of Technology Sydney
Sydney, Australia
1 h-index
2 publications
40 citations
Cambridge Scientific (United States)
Watertown, United States
1 h-index
3 publications
69 citations
Baidu (China)
Beijing, China
1 h-index
1 publications
20 citations

Zhejiang University
Hangzhou, China
1 h-index
2 publications
40 citations
1–8 of 30
Repository · 3 publications · 39 citations
3
h-index
3 publications · 48 citations
3
h-index
Conference · 2 publications · 36 citations
2
h-index
1 publications · 145 citations
1
h-index
1 publications · 15 citations
1
h-index
1–5