Enhancing Weakly Supervised Video Grounding via Diverse Inference Strategies for Boundary and Prediction Selection
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912300750864384 |
|---|---|
| author | Kim, Sunoh Um, Daeho |
| author_facet | Kim, Sunoh Um, Daeho |
| contents | Weakly supervised video grounding aims to localize temporal boundaries relevant to a given query without explicit ground-truth temporal boundaries. While existing methods primarily use Gaussian-based proposals, they overlook the importance of (1) boundary prediction and (2) top-1 prediction selection during inference. In their boundary prediction, boundaries are simply set at half a standard deviation away from a Gaussian mean on both sides, which may not accurately capture the optimal boundaries. In the top-1 prediction process, these existing methods rely heavily on intersections with other proposals, without considering the varying quality of each proposal. To address these issues, we explore various inference strategies by introducing (1) novel boundary prediction methods to capture diverse boundaries from multiple Gaussians and (2) new selection methods that take proposal quality into account. Extensive experiments on the ActivityNet Captions and Charades-STA datasets validate the effectiveness of our inference strategies, demonstrating performance improvements without requiring additional training. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23181 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Weakly Supervised Video Grounding via Diverse Inference Strategies for Boundary and Prediction Selection Kim, Sunoh Um, Daeho Computer Vision and Pattern Recognition Weakly supervised video grounding aims to localize temporal boundaries relevant to a given query without explicit ground-truth temporal boundaries. While existing methods primarily use Gaussian-based proposals, they overlook the importance of (1) boundary prediction and (2) top-1 prediction selection during inference. In their boundary prediction, boundaries are simply set at half a standard deviation away from a Gaussian mean on both sides, which may not accurately capture the optimal boundaries. In the top-1 prediction process, these existing methods rely heavily on intersections with other proposals, without considering the varying quality of each proposal. To address these issues, we explore various inference strategies by introducing (1) novel boundary prediction methods to capture diverse boundaries from multiple Gaussians and (2) new selection methods that take proposal quality into account. Extensive experiments on the ActivityNet Captions and Charades-STA datasets validate the effectiveness of our inference strategies, demonstrating performance improvements without requiring additional training. |
| title | Enhancing Weakly Supervised Video Grounding via Diverse Inference Strategies for Boundary and Prediction Selection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.23181 |