VideoWeave: A Data-Centric Approach for Efficient Video Understanding
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915719813267456 |
|---|---|
| author | Durante, Zane Singh, Silky Khatua, Arpandeep Agarwal, Shobhit Tan, Reuben Lee, Yong Jae Gao, Jianfeng Adeli, Ehsan Fei-Fei, Li |
| author_facet | Durante, Zane Singh, Silky Khatua, Arpandeep Agarwal, Shobhit Tan, Reuben Lee, Yong Jae Gao, Jianfeng Adeli, Ehsan Fei-Fei, Li |
| contents | Training video-language models is often prohibitively expensive due to the high cost of processing long frame sequences and the limited availability of annotated long videos. We present VideoWeave, a simple yet effective approach to improve data efficiency by constructing synthetic long-context training samples that splice together short, captioned videos from existing datasets. Rather than modifying model architectures or optimization objectives, VideoWeave reorganizes available video-text pairs to expand temporal diversity within fixed compute. We systematically study how different data composition strategies like random versus visually clustered splicing and caption enrichment affect downstream performance on downstream video question answering. Under identical compute constraints, models trained with VideoWeave achieve higher accuracy than conventional video finetuning. Our results highlight that reorganizing training data, rather than altering architectures, may offer a simple and scalable path for training video-language models. We link our code for all experiments here. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_06309 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VideoWeave: A Data-Centric Approach for Efficient Video Understanding Durante, Zane Singh, Silky Khatua, Arpandeep Agarwal, Shobhit Tan, Reuben Lee, Yong Jae Gao, Jianfeng Adeli, Ehsan Fei-Fei, Li Computer Vision and Pattern Recognition Artificial Intelligence Training video-language models is often prohibitively expensive due to the high cost of processing long frame sequences and the limited availability of annotated long videos. We present VideoWeave, a simple yet effective approach to improve data efficiency by constructing synthetic long-context training samples that splice together short, captioned videos from existing datasets. Rather than modifying model architectures or optimization objectives, VideoWeave reorganizes available video-text pairs to expand temporal diversity within fixed compute. We systematically study how different data composition strategies like random versus visually clustered splicing and caption enrichment affect downstream performance on downstream video question answering. Under identical compute constraints, models trained with VideoWeave achieve higher accuracy than conventional video finetuning. Our results highlight that reorganizing training data, rather than altering architectures, may offer a simple and scalable path for training video-language models. We link our code for all experiments here. |
| title | VideoWeave: A Data-Centric Approach for Efficient Video Understanding |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2601.06309 |