Visual Self-paced Iterative Learning for Unsupervised Temporal Action Localization
This work addresses the need for more efficient unsupervised methods in temporal action localization, reducing reliance on extensive labeled data, but it is incremental as it builds on existing iterative clustering paradigms.
The paper tackled the problem of unsupervised temporal action localization by addressing issues with clustering confidence and pseudolabel reliability, resulting in improved performance over state-of-the-art methods on two public datasets.
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 have substantiated the superiority of our model over several state-of-the-art competitors.