An empirical study of the effect of video encoders on Temporal Video Grounding
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_ | 1866911220411400192 |
|---|---|
| author | De la Jara, Ignacio M. Rodriguez-Opazo, Cristian Marrese-Taylor, Edison Bravo-Marquez, Felipe |
| author_facet | De la Jara, Ignacio M. Rodriguez-Opazo, Cristian Marrese-Taylor, Edison Bravo-Marquez, Felipe |
| contents | Temporal video grounding is a fundamental task in computer vision, aiming to localize a natural language query in a long, untrimmed video. It has a key role in the scientific community, in part due to the large amount of video generated every day. Although we find extensive work in this task, we note that research remains focused on a small selection of video representations, which may lead to architectural overfitting in the long run. To address this issue, we propose an empirical study to investigate the impact of different video features on a classical architecture. We extract features for three well-known benchmarks, Charades-STA, ActivityNet-Captions and YouCookII, using video encoders based on CNNs, temporal reasoning and transformers. Our results show significant differences in the performance of our model by simply changing the video encoder, while also revealing clear patterns and errors derived from the use of certain features, ultimately indicating potential feature complementarity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_17007 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An empirical study of the effect of video encoders on Temporal Video Grounding De la Jara, Ignacio M. Rodriguez-Opazo, Cristian Marrese-Taylor, Edison Bravo-Marquez, Felipe Computer Vision and Pattern Recognition Temporal video grounding is a fundamental task in computer vision, aiming to localize a natural language query in a long, untrimmed video. It has a key role in the scientific community, in part due to the large amount of video generated every day. Although we find extensive work in this task, we note that research remains focused on a small selection of video representations, which may lead to architectural overfitting in the long run. To address this issue, we propose an empirical study to investigate the impact of different video features on a classical architecture. We extract features for three well-known benchmarks, Charades-STA, ActivityNet-Captions and YouCookII, using video encoders based on CNNs, temporal reasoning and transformers. Our results show significant differences in the performance of our model by simply changing the video encoder, while also revealing clear patterns and errors derived from the use of certain features, ultimately indicating potential feature complementarity. |
| title | An empirical study of the effect of video encoders on Temporal Video Grounding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.17007 |