Wanlong Fang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Wanlong Fang has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Xiang Fang
Nanyang technological university, Singapore, Singapore
2 shared publications - Daizong Liu
Wuhan University, Wuhan, China
1 shared publication - Jianfeng Dong
Zhejiang Gongshang University, Hangzhou, China
1 shared publication - Lixing Chen
Shanghai Jiao Tong University
1 shared publication - Pan Zhou
Huazhong University of Science and Technology
1 shared publication - Panpan Zheng
Xinjiang University
1 shared publication
Latest Publications
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 12509-12518
Turing Patterns for Multimedia: Reaction-Diffusion Multi-Modal Fusion for Language-Guided Video Moment Retrieval
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 12509-12518
Open AccessTuring Patterns for Multimedia: Reaction-Diffusion Multi-Modal Fusion for Language-Guided Video Moment Retrieval
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 28-37
Not All Inputs Are Valid: Towards Open-Set Video Moment Retrieval using Language
Video Moment Retrieval (VMR) targets to retrieve the specific moment corresponding to a sentence query from an untrimmed video. Although recent respectable works have made remarkable progress in this task, they implicitly are rooted in the closed-set assumption that all the given queries as video-relevant. Given an OOD query in open-set scenarios, they still utilize it for wrong retrieval, which might lead to irrecoverable losses in high-risk scenarios, e.g., criminal activity detection. To this end, we creatively explore a brand-new VMR setting termed Open-Set Video Moment Retrieval (OS-VMR), where we should not only retrieve the precise moments based on ID query, but also reject OOD queries. In this paper, we make the first attempt to step toward OS-VMR and propose a novel model OpenVMR, which first distinguishes ID and OOD queries based on the normalizing flow technology, and then conducts moment retrieval based on ID queries. Specifically, we first learn the ID distribution by constructing a normalizing flow, and assume the ID query distribution obeys the multi-variate Gaussian distribution. Then, we introduce an uncertainty score to search the ID-OOD separating boundary. After that, we refine the ID-OOD boundary by pulling together ID query features. Besides, video-query matching and frame-query matching are designed for coarse-grained and fine-grained cross-modal interaction, respectively. Finally, a positive-unlabeled learning module is introduced for moment retrieval. Experimental results on three VMR datasets show the effectiveness of our OpenVMR.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 28-37
Open AccessNot All Inputs Are Valid: Towards Open-Set Video Moment Retrieval using Language
Video Moment Retrieval (VMR) targets to retrieve the specific moment corresponding to a sentence query from an untrimmed video. Although recent respectable works have made remarkable progress in this task, they implicitly are rooted in the closed-set assumption that all the given queries as video-relevant. Given an OOD query in open-set scenarios, they still utilize it for wrong retrieval, which might lead to irrecoverable losses in high-risk scenarios, e.g., criminal activity detection. To this end, we creatively explore a brand-new VMR setting termed Open-Set Video Moment Retrieval (OS-VMR), where we should not only retrieve the precise moments based on ID query, but also reject OOD queries. In this paper, we make the first attempt to step toward OS-VMR and propose a novel model OpenVMR, which first distinguishes ID and OOD queries based on the normalizing flow technology, and then conducts moment retrieval based on ID queries. Specifically, we first learn the ID distribution by constructing a normalizing flow, and assume the ID query distribution obeys the multi-variate Gaussian distribution. Then, we introduce an uncertainty score to search the ID-OOD separating boundary. After that, we refine the ID-OOD boundary by pulling together ID query features. Besides, video-query matching and frame-query matching are designed for coarse-grained and fine-grained cross-modal interaction, respectively. Finally, a positive-unlabeled learning module is introduced for moment retrieval. Experimental results on three VMR datasets show the effectiveness of our OpenVMR.