Work

Visual Self-paced Iterative Learning for Unsupervised Temporal Action Localization

Year: 2026

Type: article

Abstract: Recently, Temporal Action Localization (TAL) has garnered significant interest in information retrieval community. However, existing supervised/weakly supervised methods are heavily dependent on extensive labeled temporal boundaries and action categories, which is labor-intensive and time-consuming. Although some unsupervised methods have utilized the “iteratively clustering and localization” paradigm for TAL, they still suffer from two pivotal impediments: (1) unsatisfactory video clustering confidence, and (2) unreliable video pseudolabels for model training. To address these limitations, we present a novel self-paced iterative learning model to enhance clustering and localization training simultaneously, thereby facilitating more effective unsupervised TAL. Concretely, we improve the clustering confidence through exploring the contextual feature-robust visual information. Thereafter, we design two (constant- and variable-speed) incremental instance learning strategies for easy-to-hard model training, thus ensuring the reliability of these video pseudolabels and further improving overall localization performance. Extensive experiments on two public datasets demonstrate the superiority of our model over several state-of-the-art competitors.

Source: ACM Transactions on Multimedia Computing Communications and Applications

DOI: 10.1145/3796708

Authors: Yupeng Hu, Han Jiang, Hao Liu, Kun Wang, Haoyu Tang, Liqiang Nie

Institutions: Shandong University, Xi'an Jiaotong University, Harbin Institute of Technology

Language: English

Topic: Human Pose and Action Recognition

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Natural Science Foundation of China

Award: G2770436304