Chao Zheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chao Zheng has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Bing Li
Wuhan University
2 shared publications - Jian Wang
School of Computer Science, Wuhan University, China
2 shared publications - Chong Wang
School of Computer Science Wuhan University Wuhan China
1 shared publication - Duantengchuan Li
School of Information Management, Wuhan University, Wuhan 430072, China
1 shared publication - Maodong Li
Wuhan University
1 shared publication - Rujian Cai
Wuhan University
1 shared publication
Latest Publications
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (5) , 4842-4850
Similar Modality Enhancement and Action Consistency Learning for Weakly Supervised Temporal Action Localization
Weakly-supervised temporal action localization (WTAL) aims to identify and localize action instances in untrimmed videos using only video-level labels. Existing methods typically rely on original features from frozen pre-trained encoders designed for trimmed action classification (TAC) tasks, which inevitably introduces task discrepancy. Additionally, these methods often overlook the importance of considering action consistency from multiple perspectives, specifically the consistency in action processes and action semantics, both of which are crucial for the model's understanding of actions. To address these issues, we propose a novel WTAL method based on similar modality enhancement and action consistency learning (SEAL). First, we construct global descriptors for each action category, and use the pseudo-labels generated based on these descriptors to guide the model in learning more consistent representations, thereby mitigating task discrepancy. Second, we design two types of losses to achieve action consistency learning: process consistency loss, which penalizes candidate proposals that deviate from the action center to ensure the completeness of the action process, and semantic consistency loss, which employs local descriptors to help proposals of the same action category (especially those with apparent semantic confusion) learn similar feature distributions. Extensive experiments on the THUMOS14 and ActivityNet datasets demonstrate the superior performance of the proposed method compared to state-of-the-art methods.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (5) , 4842-4850
Open AccessSimilar Modality Enhancement and Action Consistency Learning for Weakly Supervised Temporal Action Localization
Weakly-supervised temporal action localization (WTAL) aims to identify and localize action instances in untrimmed videos using only video-level labels. Existing methods typically rely on original features from frozen pre-trained encoders designed for trimmed action classification (TAC) tasks, which inevitably introduces task discrepancy. Additionally, these methods often overlook the importance of considering action consistency from multiple perspectives, specifically the consistency in action processes and action semantics, both of which are crucial for the model's understanding of actions. To address these issues, we propose a novel WTAL method based on similar modality enhancement and action consistency learning (SEAL). First, we construct global descriptors for each action category, and use the pseudo-labels generated based on these descriptors to guide the model in learning more consistent representations, thereby mitigating task discrepancy. Second, we design two types of losses to achieve action consistency learning: process consistency loss, which penalizes candidate proposals that deviate from the action center to ensure the completeness of the action process, and semantic consistency loss, which employs local descriptors to help proposals of the same action category (especially those with apparent semantic confusion) learn similar feature distributions. Extensive experiments on the THUMOS14 and ActivityNet datasets demonstrate the superior performance of the proposed method compared to state-of-the-art methods.
- 3 June 2024
- Published by Springer Nature
- p. 55-70
Reinforcement Learning-Based Streaming Process Discovery Under Concept Drift
- 3 June 2024
- Published by Springer Nature
- p. 55-70
Reinforcement Learning-Based Streaming Process Discovery Under Concept Drift