中文
相关论文

相关论文: E.M.Ground: A Temporal Grounding Vid-LLM with Holi…

200 篇论文

Vision-language models (VLMs) have shown remarkable progress in offline tasks such as image captioning and video question answering. However, real-time interactive environments impose new demands on VLMs, requiring them to generate…

计算机视觉与模式识别 · 计算机科学 2025-05-19 Keunwoo Peter Yu , Joyce Chai

Video grounding aims to localize a spatio-temporal section in a video corresponding to an input text query. This paper addresses a critical limitation in current video grounding methodologies by introducing an Open-Vocabulary…

计算机视觉与模式识别 · 计算机科学 2024-04-02 Syed Talal Wasim , Muzammal Naseer , Salman Khan , Ming-Hsuan Yang , Fahad Shahbaz Khan

Real-world robots localize objects from natural-language instructions while scenes around them keep changing. Yet most of the existing 3D visual grounding (3DVG) method still assumes a reconstructed and up-to-date point cloud, an assumption…

计算机视觉与模式识别 · 计算机科学 2025-10-17 Miao Hu , Zhiwei Huang , Tai Wang , Jiangmiao Pang , Dahua Lin , Nanning Zheng , Runsen Xu

How are we able to learn about complex current events just from short snippets of video? While natural language enables straightforward ways to represent under-specified, partially observable events, visual data does not facilitate…

Temporally localizing user-queried events through natural language is a crucial capability for video models. Recent methods predominantly adapt video LLMs to generate event boundary timestamps for temporal localization tasks, which struggle…

计算机视觉与模式识别 · 计算机科学 2026-02-17 Zongshang Pang , Mayu Otani , Yuta Nakashima

Rapid development of large language models (LLMs) has significantly advanced multimodal large language models (LMMs), particularly in vision-language tasks. However, existing video-language models often overlook precise temporal…

计算机视觉与模式识别 · 计算机科学 2024-11-28 Shimin Chen , Xiaohan Lan , Yitian Yuan , Zequn Jie , Lin Ma

Can Video-LLMs achieve consistent temporal understanding when videos capture the same event from different viewpoints? To study this, we introduce EgoExo-Con (Consistency), a benchmark of comprehensively synchronized egocentric and…

计算机视觉与模式识别 · 计算机科学 2025-10-31 Minjoon Jung , Junbin Xiao , Junghyun Kim , Byoung-Tak Zhang , Angela Yao

Text-guided 3D visual grounding (T-3DVG), which aims to locate a specific object that semantically corresponds to a language query from a complicated 3D scene, has drawn increasing attention in the 3D research community over the past few…

计算机视觉与模式识别 · 计算机科学 2024-07-23 Daizong Liu , Yang Liu , Wencan Huang , Wei Hu

Recent advancements in event-based recognition have demonstrated significant promise, yet most existing approaches rely on extensive training, limiting their adaptability for efficient processing of event-driven visual content. Meanwhile,…

计算机视觉与模式识别 · 计算机科学 2025-02-21 Zongyou Yu , Qiang Qu , Qian Zhang , Nan Zhang , Xiaoming Chen

Video Paragraph Grounding (VPG) is an emerging task in video-language understanding, which aims at localizing multiple sentences with semantic relations and temporal order from an untrimmed video. However, existing VPG approaches are…

计算机视觉与模式识别 · 计算机科学 2024-05-15 Chaolei Tan , Jianhuang Lai , Wei-Shi Zheng , Jian-Fang Hu

Existing Video Temporal Grounding (VTG) models excel in accuracy but often overlook open-world challenges posed by open-vocabulary queries and untrimmed videos. This leads to unreliable predictions for noisy, corrupted, and…

计算机视觉与模式识别 · 计算机科学 2024-08-30 Kaijing Ma , Haojian Huang , Jin Chen , Haodong Chen , Pengliang Ji , Xianghao Zang , Han Fang , Chao Ban , Hao Sun , Mulin Chen , Xuelong Li

This technical report presents the 3rd winning solution for MTVG, a new task introduced in the 4-th Person in Context (PIC) Challenge at ACM MM 2022. MTVG aims at localizing the temporal boundary of the step in an untrimmed video based on a…

计算机视觉与模式识别 · 计算机科学 2022-08-15 Xiujun Shu , Wei Wen , Taian Guo , Sunan He , Chen Wu , Ruizhi Qiao

Long-form video question answering remains challenging for modern vision-language models, which struggle to reason over hour-scale footage without exceeding practical token and compute budgets. Existing systems typically downsample frames…

计算机视觉与模式识别 · 计算机科学 2026-01-13 Aradhya Dixit , Tianxi Liang

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

Visual grounding is a common vision task that involves grounding descriptive sentences to the corresponding regions of an image. Most existing methods use independent image-text encoding and apply complex hand-crafted modules or…

计算机视觉与模式识别 · 计算机科学 2024-10-29 Ming Dai , Lingfeng Yang , Yihao Xu , Zhenhua Feng , Wankou Yang

Given an untrimmed video and natural language query, video sentence grounding aims to localize the target temporal moment in the video. Existing methods mainly tackle this task by matching and aligning semantics of the descriptive sentence…

计算机视觉与模式识别 · 计算机科学 2022-12-29 Wei Ji , Long Chen , Yinwei Wei , Yiming Wu , Tat-Seng Chua

Video frame interpolation (VFI) in scenarios with large motion remains challenging due to motion ambiguity between frames. While event cameras can capture high temporal resolution motion information, existing event-based VFI methods…

计算机视觉与模式识别 · 计算机科学 2025-03-27 Ziran Zhang , Xiaohui Li , Yihao Liu , Yujin Wang , Yueting Chen , Tianfan Xue , Shi Guo

We propose a novel framework for open-ended video question answering that enhances reasoning depth and robustness in complex real-world scenarios, as benchmarked on the CVRR-ES dataset. Existing Video-Large Multimodal Models (Video-LMMs)…

计算机视觉与模式识别 · 计算机科学 2025-07-21 Jun Xie , Zhaoran Zhao , Xiongjun Guan , Yingjian Zhu , Hongzhu Yi , Xinming Wang , Feng Chen , Zhepeng Wang

Video grounding is a fundamental problem in multimodal content understanding, aiming to localize specific natural language queries in an untrimmed video. However, current video grounding datasets merely focus on simple events and are either…

计算机视觉与模式识别 · 计算机科学 2024-08-20 Chaolei Tan , Zihang Lin , Junfu Pu , Zhongang Qi , Wei-Yi Pei , Zhi Qu , Yexin Wang , Ying Shan , Wei-Shi Zheng , Jian-Fang Hu

Video Moment Retrieval (VMR) aims to localize a specific temporal segment within an untrimmed long video given a natural language query. Existing methods often suffer from inadequate training annotations, i.e., the sentence typically…

计算机视觉与模式识别 · 计算机科学 2024-06-27 Weitong Cai , Jiabo Huang , Shaogang Gong , Hailin Jin , Yang Liu