Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Ruizhe, Fan, Zhiting, Luo, Tianze, Zou, Heqing, Feng, Zhaopeng, Xie, Guiyang, Zhang, Hansheng, Wang, Zhuochen, Liu, Zuozhu, Zhang, Huaijian
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2507.18100
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908464107749376
author Chen, Ruizhe
Fan, Zhiting
Luo, Tianze
Zou, Heqing
Feng, Zhaopeng
Xie, Guiyang
Zhang, Hansheng
Wang, Zhuochen
Liu, Zuozhu
Zhang, Huaijian
author_facet Chen, Ruizhe
Fan, Zhiting
Luo, Tianze
Zou, Heqing
Feng, Zhaopeng
Xie, Guiyang
Zhang, Hansheng
Wang, Zhuochen
Liu, Zuozhu
Zhang, Huaijian
contents Video Temporal Grounding (VTG) aims to localize relevant temporal segments in videos given natural language queries. Despite recent progress with large vision-language models (LVLMs) and instruction-tuning, existing approaches often suffer from limited temporal awareness and poor generalization. In this work, we introduce a two-stage training framework that integrates supervised fine-tuning with reinforcement learning (RL) to improve both the accuracy and robustness of VTG models. Our approach first leverages high-quality curated cold start data for SFT initialization, followed by difficulty-controlled RL to further enhance temporal localization and reasoning abilities. Comprehensive experiments on multiple VTG benchmarks demonstrate that our method consistently outperforms existing models, particularly in challenging and open-domain scenarios. We conduct an in-depth analysis of training strategies and dataset curation, highlighting the importance of both high-quality cold start data and difficulty-controlled RL. To facilitate further research and industrial adoption, we release all intermediate datasets, models, and code to the community.
format Preprint
id arxiv_https___arxiv_org_abs_2507_18100
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning
Chen, Ruizhe
Fan, Zhiting
Luo, Tianze
Zou, Heqing
Feng, Zhaopeng
Xie, Guiyang
Zhang, Hansheng
Wang, Zhuochen
Liu, Zuozhu
Zhang, Huaijian
Computer Vision and Pattern Recognition
Artificial Intelligence
Video Temporal Grounding (VTG) aims to localize relevant temporal segments in videos given natural language queries. Despite recent progress with large vision-language models (LVLMs) and instruction-tuning, existing approaches often suffer from limited temporal awareness and poor generalization. In this work, we introduce a two-stage training framework that integrates supervised fine-tuning with reinforcement learning (RL) to improve both the accuracy and robustness of VTG models. Our approach first leverages high-quality curated cold start data for SFT initialization, followed by difficulty-controlled RL to further enhance temporal localization and reasoning abilities. Comprehensive experiments on multiple VTG benchmarks demonstrate that our method consistently outperforms existing models, particularly in challenging and open-domain scenarios. We conduct an in-depth analysis of training strategies and dataset curation, highlighting the importance of both high-quality cold start data and difficulty-controlled RL. To facilitate further research and industrial adoption, we release all intermediate datasets, models, and code to the community.
title Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2507.18100