BROWSE
Detail
Conference Paper
Probabilistic Vision-Language Representation for Weakly Supervised Temporal Action Localization
Cited 1 time in 
Share 
Share
- Authors
- Geuntaek Lim, Hyunwoo Kim, Joonsoo Kim, Yukyung Choi
- Issue Date
- 2024-10
- Citation
- International Conference on Multimedia (MM) 2024, pp.5507-5516
- Language
- English
- Type
- Conference Paper
- Abstract
- Weakly supervised temporal action localization (WTAL) aims to detect action instances in untrimmed videos using only video-level annotations. Since many existing works optimize WTAL models based on action classification labels, they encounter the task discrepancy problem (i.e., localization-by-classification). To tackle this issue, recent studies have attempted to utilize action category names as auxiliary semantic knowledge through vision-language pre-training (VLP). However, there are still areas where existing research falls short. Previous approaches primarily focused on leveraging textual information from language models but overlooked the alignment of dynamic human action and VLP knowledge in a joint space. Furthermore, the deterministic representation employed in previous studies struggles to capture fine-grained human motions. To address these problems, we propose a novel framework that aligns human action knowledge and VLP knowledge in a probabilistic embedding space. Moreover, we propose intra- and inter-distribution contrastive learning to enhance the probabilistic embedding space based on statistical similarities. Extensive experiments and ablation studies reveal that our method significantly outperforms all previous state-of-the-art methods. Code is available at https://github.com/sejong-rcv/PVLR.
- KSP Keywords
- Action Classification, Action localization, Embedding space, Fine grained(FG), Human action, Human motion, Joint space, Language Model, Language representation, Pre-Training, Probabilistic embedding