中文
相关论文

相关论文: VideoTG-R1: Boosting Video Temporal Grounding via …

200 篇论文

Reinforcement learning from verifiable rewards (RLVR) has demonstrated remarkable effectiveness in improving the reasoning capabilities of large language models. As models evolve into natively multimodal architectures, extending RLVR to…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Chuanyu Qin , Chenxu Yang , Qingyi Si , Naibin Gu , Dingyu Yao , Zheng Lin , Peng Fu , Nan Duan , Jiaqi Wang

Given a text description, Temporal Language Grounding (TLG) aims to localize temporal boundaries of the segments that contain the specified semantics in an untrimmed video. TLG is inherently a challenging task, as it requires comprehensive…

计算机视觉与模式识别 · 计算机科学 2021-12-07 Fan Luo , Shaoxiang Chen , Jingjing Chen , Zuxuan Wu , Yu-Gang Jiang

Complex video reasoning remains a significant challenge for Multimodal Large Language Models (MLLMs), as current R1-based methodologies often prioritize text-centric reasoning derived from text-based and image-based developments. In video…

计算机视觉与模式识别 · 计算机科学 2025-11-18 Bo Fang , Yuxin Song , Qiangqiang Wu , Haoyuan Sun , Wenhao Wu , Antoni B. Chan

Multi-image reasoning and grounding require understanding complex cross-image relationships at both object levels and image levels. Current Large Visual Language Models (LVLMs) face two critical challenges: the lack of cross-image reasoning…

计算机视觉与模式识别 · 计算机科学 2025-09-29 Lihao Zheng , Jiawei Chen , Xintian Shen , Hao Ma , Tao Wei

Video temporal grounding (VTG) aims to localize the start and end timestamps of the event described by a given query within an untrimmed video. Despite the strong open-world video understanding and recognition ability of video language…

多媒体 · 计算机科学 2026-05-05 Pengcheng Fang , Yuxia Chen , Xiaohao Cai

Multimodal large language models via reinforcement learning (RL) have demonstrated remarkable capabilities in complex visual reasoning tasks, yet they remain limited in long-horizon multimodal scenarios, often suffering from visual…

计算机视觉与模式识别 · 计算机科学 2026-05-26 Chenghao Li , Fusheng Hao , Xikai Zhang , Likang Xiao , Yanwei Ren , Fuxiang Wu , Quan Chen , Liu Liu

Reinforcement Learning with Verifiable Rewards (RLVR) has substantially advanced the video understanding capabilities of Multimodal Large Language Models (MLLMs). However, the rapid progress of MLLMs is outpacing the complexity of existing…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Zefeng He , Xiaoye Qu , Yafu Li , Siyuan Huang , Daizong Liu , Yu Cheng

Video Large Language Models (Vid-LLMs) have made remarkable advancements in comprehending video content for QA dialogue. However, they struggle to extend this visual understanding to tasks requiring precise temporal localization, known as…

计算机视觉与模式识别 · 计算机科学 2025-03-24 Yongliang Wu , Xinting Hu , Yuyang Sun , Yizhou Zhou , Wenbo Zhu , Fengyun Rao , Bernt Schiele , Xu Yang

Multimodal large language models (MLLMs) have achieved remarkable progress in video understanding. However, seemingly plausible outputs often suffer from poor visual and temporal grounding: a model may fabricate object existence, assign…

计算机视觉与模式识别 · 计算机科学 2026-04-03 Yihao Quan , Zeru Shi , Jinman Zhao , Ruixiang Tang

Reinforcement fine-tuning (RFT) has shown great promise in achieving humanlevel reasoning capabilities of Large Language Models (LLMs), and has recently been extended to MLLMs. Nevertheless, reasoning about videos, which is a fundamental…

计算机视觉与模式识别 · 计算机科学 2025-10-15 Qi Wang , Yanrui Yu , Ye Yuan , Rui Mao , Tianfei Zhou

Video Large Language Models (Video-LLMs) have demonstrated remarkable capabilities in coarse-grained video understanding, however, they struggle with fine-grained temporal grounding. In this paper, we introduce Grounded-VideoLLM, a novel…

计算机视觉与模式识别 · 计算机科学 2025-08-22 Haibo Wang , Zhiyang Xu , Yu Cheng , Shizhe Diao , Yufan Zhou , Yixin Cao , Qifan Wang , Weifeng Ge , Lifu Huang

Long-form video understanding, characterized by long-range temporal dependencies and multiple events, remains a challenge. Existing methods often rely on static reasoning or external visual-language models (VLMs), which face issues like…

计算机视觉与模式识别 · 计算机科学 2025-08-29 Yuan Xie , Tianshui Chen , Zheng Ge , Lionel Ni

Despite progress in multimodal large language models (MLLMs), the challenge of interpreting long-form videos in response to linguistic queries persists, largely due to the inefficiency in temporal grounding and limited pre-trained context…

计算机视觉与模式识别 · 计算机科学 2024-10-04 Yuxuan Wang , Yueqian Wang , Pengfei Wu , Jianxin Liang , Dongyan Zhao , Yang Liu , Zilong Zheng

Video-LLMs often attend to irrelevant frames, which is especially detrimental for sports coaching tasks requiring precise temporal grounding. Yet obtaining frame-level supervision is challenging: expensive to collect from humans and…

计算机视觉与模式识别 · 计算机科学 2026-03-20 Arushi Rai , Adriana Kovashka

Recent advancements in video-language understanding have been established on the foundation of image-text models, resulting in promising outcomes due to the shared knowledge between images and videos. However, video-language understanding…

计算机视觉与模式识别 · 计算机科学 2023-12-19 Xiao Wang , Yaoyu Li , Tian Gan , Zheng Zhang , Jingjing Lv , Liqiang Nie

While Multimodal Large Language Models (MLLMs) have advanced Video Temporal Grounding (VTG), existing methods often couple output paradigms with different backbones, datasets, and training protocols. This makes it challenging to isolate the…

计算机视觉与模式识别 · 计算机科学 2026-04-13 Shengji Jin , Yuanhao Zou , Victor Zhu , Zhengping Ji , Chen Chen

Video reasoning requires a fine-grained understanding of the temporal dependencies and event-level relations between objects and events in videos. Current Multimodal Large Language Models (MLLMs) are prone to severe temporal hallucinations…

计算机视觉与模式识别 · 计算机科学 2026-05-14 Zixu Cheng , Da Li , Jian Hu , Yuhang Zang , Ziquan Liu , Shaogang Gong , Wei Li

In the field of multimodal chain-of-thought (CoT) reasoning, existing approaches predominantly rely on reasoning on pure language space, which inherently suffers from language bias and is largely confined to math or science domains. This…

计算机视觉与模式识别 · 计算机科学 2026-05-04 Jiacong Wang , Zijian Kang , Haochen Wang , Haiyong Jiang , Jiawen Li , Bohong Wu , Ya Wang , Jiao Ran , Xiao Liang , Chao Feng , Jun Xiao

Recent works have demonstrated the effectiveness of reinforcement learning (RL)-based post-training for enhancing the reasoning capabilities of large language models (LLMs). In particular, Group Relative Policy Optimization (GRPO) has shown…

计算机视觉与模式识别 · 计算机科学 2026-02-05 Jinyoung Park , Jeehye Na , Jinyoung Kim , Hyunwoo J. Kim

Video Temporal Grounding (VTG) is a crucial capability for video understanding models and plays a vital role in downstream tasks such as video browsing and editing. To effectively handle various tasks simultaneously and enable zero-shot…

计算机视觉与模式识别 · 计算机科学 2025-03-04 Yongxin Guo , Jingyu Liu , Mingda Li , Qingbin Liu , Xi Chen , Xiaoying Tang