Saved in:
Bibliographic Details
Main Authors: Fan, Rong, Xiao, Kaiyan, Zhu, Minghao, Wang, Liuyi, Dai, Kai, Yang, Zhao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.02093
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908933568856064
author Fan, Rong
Xiao, Kaiyan
Zhu, Minghao
Wang, Liuyi
Dai, Kai
Yang, Zhao
author_facet Fan, Rong
Xiao, Kaiyan
Zhu, Minghao
Wang, Liuyi
Dai, Kai
Yang, Zhao
contents Video temporal grounding (VTG) is a critical task in video understanding and a key capability for extending video large language models (Vid-LLMs) to broader applications. However, existing Vid-LLMs rely on uniform frame sampling to extract video information, resulting in a sparse distribution of key frames and the loss of crucial temporal cues. To address this limitation, we propose Grounded Visual Token Sampling (GroundVTS), a Vid-LLM architecture that focuses on the most informative temporal segments. GroundVTS employs a fine-grained, query-guided mechanism to filter visual tokens before feeding them into the LLM, thereby preserving essential spatio-temporal information and maintaining temporal coherence. Futhermore, we introduce a progressive optimization strategy that enables the LLM to effectively adapt to the non-uniform distribution of visual features, enhancing its ability to model temporal dependencies and achieve precise video localization. We comprehensively evaluate GroundVTS on three standard VTG benchmarks, where it outperforms existing methods, achieving a 7.7-point improvement in mIoU for moment retrieval and 12.0-point improvement in mAP for highlight detection. Code is available at https://github.com/Florence365/GroundVTS.
format Preprint
id arxiv_https___arxiv_org_abs_2604_02093
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GroundVTS: Visual Token Sampling in Multimodal Large Language Models for Video Temporal Grounding
Fan, Rong
Xiao, Kaiyan
Zhu, Minghao
Wang, Liuyi
Dai, Kai
Yang, Zhao
Computer Vision and Pattern Recognition
Video temporal grounding (VTG) is a critical task in video understanding and a key capability for extending video large language models (Vid-LLMs) to broader applications. However, existing Vid-LLMs rely on uniform frame sampling to extract video information, resulting in a sparse distribution of key frames and the loss of crucial temporal cues. To address this limitation, we propose Grounded Visual Token Sampling (GroundVTS), a Vid-LLM architecture that focuses on the most informative temporal segments. GroundVTS employs a fine-grained, query-guided mechanism to filter visual tokens before feeding them into the LLM, thereby preserving essential spatio-temporal information and maintaining temporal coherence. Futhermore, we introduce a progressive optimization strategy that enables the LLM to effectively adapt to the non-uniform distribution of visual features, enhancing its ability to model temporal dependencies and achieve precise video localization. We comprehensively evaluate GroundVTS on three standard VTG benchmarks, where it outperforms existing methods, achieving a 7.7-point improvement in mIoU for moment retrieval and 12.0-point improvement in mAP for highlight detection. Code is available at https://github.com/Florence365/GroundVTS.
title GroundVTS: Visual Token Sampling in Multimodal Large Language Models for Video Temporal Grounding
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.02093