Moment Quantization for Video Temporal Grounding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917975646273536 |
|---|---|
| author | Sun, Xiaolong Wang, Le Zhou, Sanping Shi, Liushuai Xia, Kun Liu, Mengnan Wang, Yabing Hua, Gang |
| author_facet | Sun, Xiaolong Wang, Le Zhou, Sanping Shi, Liushuai Xia, Kun Liu, Mengnan Wang, Yabing Hua, Gang |
| contents | Video temporal grounding is a critical video understanding task, which aims to localize moments relevant to a language description. The challenge of this task lies in distinguishing relevant and irrelevant moments. Previous methods focused on learning continuous features exhibit weak differentiation between foreground and background features. In this paper, we propose a novel Moment-Quantization based Video Temporal Grounding method (MQVTG), which quantizes the input video into various discrete vectors to enhance the discrimination between relevant and irrelevant moments. Specifically, MQVTG maintains a learnable moment codebook, where each video moment matches a codeword. Considering the visual diversity, i.e., various visual expressions for the same moment, MQVTG treats moment-codeword matching as a clustering process without using discrete vectors, avoiding the loss of useful information from direct hard quantization. Additionally, we employ effective prior-initialization and joint-projection strategies to enhance the maintained moment codebook. With its simple implementation, the proposed method can be integrated into existing temporal grounding models as a plug-and-play component. Extensive experiments on six popular benchmarks demonstrate the effectiveness and generalizability of MQVTG, significantly outperforming state-of-the-art methods. Further qualitative analysis shows that our method effectively groups relevant features and separates irrelevant ones, aligning with our goal of enhancing discrimination. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_02286 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Moment Quantization for Video Temporal Grounding Sun, Xiaolong Wang, Le Zhou, Sanping Shi, Liushuai Xia, Kun Liu, Mengnan Wang, Yabing Hua, Gang Computer Vision and Pattern Recognition Video temporal grounding is a critical video understanding task, which aims to localize moments relevant to a language description. The challenge of this task lies in distinguishing relevant and irrelevant moments. Previous methods focused on learning continuous features exhibit weak differentiation between foreground and background features. In this paper, we propose a novel Moment-Quantization based Video Temporal Grounding method (MQVTG), which quantizes the input video into various discrete vectors to enhance the discrimination between relevant and irrelevant moments. Specifically, MQVTG maintains a learnable moment codebook, where each video moment matches a codeword. Considering the visual diversity, i.e., various visual expressions for the same moment, MQVTG treats moment-codeword matching as a clustering process without using discrete vectors, avoiding the loss of useful information from direct hard quantization. Additionally, we employ effective prior-initialization and joint-projection strategies to enhance the maintained moment codebook. With its simple implementation, the proposed method can be integrated into existing temporal grounding models as a plug-and-play component. Extensive experiments on six popular benchmarks demonstrate the effectiveness and generalizability of MQVTG, significantly outperforming state-of-the-art methods. Further qualitative analysis shows that our method effectively groups relevant features and separates irrelevant ones, aligning with our goal of enhancing discrimination. |
| title | Moment Quantization for Video Temporal Grounding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.02286 |