中文
相关论文

相关论文: VideoGEM: Training-free Action Grounding in Videos

200 篇论文

Vision-language foundation models have shown remarkable performance in various zero-shot settings such as image retrieval, classification, or captioning. But so far, those models seem to fall behind when it comes to zero-shot localization…

计算机视觉与模式识别 · 计算机科学 2023-12-15 Walid Bousselham , Felix Petersen , Vittorio Ferrari , Hilde Kuehne

Given an untrimmed video and a language query depicting a specific temporal moment in the video, video grounding aims to localize the time interval by understanding the text and video simultaneously. One of the most challenging issues is an…

计算机视觉与模式识别 · 计算机科学 2022-10-25 Dahye Kim , Jungin Park , Jiyoung Lee , Seongheon Park , Kwanghoon Sohn

Video temporal grounding aims to identify video segments within untrimmed videos that are most relevant to a given natural language query. Existing video temporal localization models rely on specific datasets for training and have high data…

计算机视觉与模式识别 · 计算机科学 2024-08-30 Minghang Zheng , Xinhao Cai , Qingchao Chen , Yuxin Peng , Yang Liu

Given a task and a set of steps composing it, Video Step Grounding (VSG) aims to detect which steps are performed in a video. Standard approaches for this task require a labeled training set (e.g., with step-level annotations or…

计算机视觉与模式识别 · 计算机科学 2025-10-21 Luca Zanella , Massimiliano Mancini , Yiming Wang , Alessio Tonioni , Elisa Ricci

In this paper, we explore a novel task named visual Relation Grounding in Videos (vRGV). The task aims at spatio-temporally localizing the given relations in the form of subject-predicate-object in the videos, so as to provide supportive…

计算机视觉与模式识别 · 计算机科学 2020-07-22 Junbin Xiao , Xindi Shang , Xun Yang , Sheng Tang , Tat-Seng Chua

Video Large Language Models (VideoLLMs) have recently demonstrated remarkable progress in general video understanding. However, existing models primarily focus on high-level comprehension and are limited to text-only responses, restricting…

计算机视觉与模式识别 · 计算机科学 2025-07-29 Haochen Wang , Qirui Chen , Cilin Yan , Jiayin Cai , Xiaolong Jiang , Yao Hu , Weidi Xie , Stratis Gavves

Temporal Video Grounding (TVG) aims to localize a moment from an untrimmed video given the language description. Since the annotation of TVG is labor-intensive, TVG under limited supervision has accepted attention in recent years. The great…

计算机视觉与模式识别 · 计算机科学 2024-06-12 Xing Zhang , Jiaxi Gu , Haoyu Zhao , Shicong Wang , Hang Xu , Renjing Pei , Songcen Xu , Zuxuan Wu , Yu-Gang Jiang

Vision-Language Models (VLMs) encode knowledge and reasoning capabilities for robotic manipulation within high-dimensional representation spaces. However, current approaches often project them into compressed intermediate representations,…

机器人学 · 计算机科学 2025-06-25 Wenbo Li , Shiyi Wang , Yiteng Chen , Huiping Zhuang , Qingyao Wu

We present SpatialMem, a memory-centric system for long-horizon, language-grounded retrieval and QA from egocentric video, where metric 3D serves as an interpretable indexing scaffold rather than an explicit mapping objective. Starting from…

计算机视觉与模式识别 · 计算机科学 2026-03-09 Xinyi Zheng , Yunze Liu , Chi-Hao Wu , Fan Zhang , Hao Zheng , Wenqi Zhou , Walterio W. Mayol-Cuevas , Junxiao Shen

Fine-grained alignment between videos and text is challenging due to complex spatial and temporal dynamics in videos. Existing video-based Large Multimodal Models (LMMs) handle basic conversations but struggle with precise pixel-level…

计算机视觉与模式识别 · 计算机科学 2025-03-26 Shehan Munasinghe , Hanan Gani , Wenqi Zhu , Jiale Cao , Eric Xing , Fahad Shahbaz Khan , Salman Khan

Joint video-language learning has received increasing attention in recent years. However, existing works mainly focus on single or multiple trimmed video clips (events), which makes human-annotated event boundaries necessary during…

计算机视觉与模式识别 · 计算机科学 2023-05-18 Teng Wang , Jinrui Zhang , Feng Zheng , Wenhao Jiang , Ran Cheng , Ping Luo

Video reasoning segmentation requires localizing objects across video frames from natural language expressions, often involving spatial reasoning and implicit references. Recent approaches leverage frozen large vision-language models…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Ali Cheraghian , Hamidreza Dastmalchi , Abdelwahed Khamis , Morteza Saberi , Aijun An , Lars Petersson

We introduce the task of spatially localizing narrated interactions in videos. Key to our approach is the ability to learn to spatially localize interactions with self-supervision on a large corpus of videos with accompanying transcribed…

计算机视觉与模式识别 · 计算机科学 2021-12-03 Reuben Tan , Bryan A. Plummer , Kate Saenko , Hailin Jin , Bryan Russell

Recent advances in legged locomotion learning are still dominated by the utilization of geometric representations of the environment, limiting the robot's capability to respond to higher-level semantics such as human instructions. To…

机器人学 · 计算机科学 2026-02-12 I Made Aswin Nahrendra , Seunghyun Lee , Dongkyu Lee , Hyun Myung

Video action localization aims to find the timings of specific actions from a long video. Although existing learning-based approaches have been successful, they require annotating videos, which comes with a considerable labor cost. This…

计算机视觉与模式识别 · 计算机科学 2025-04-08 Naoki Wake , Atsushi Kanehira , Kazuhiro Sasabuchi , Jun Takamatsu , Katsushi Ikeuchi

Visual grounding seeks to localize the image region corresponding to a free-form text description. Recently, the strong multimodal capabilities of Large Vision-Language Models (LVLMs) have driven substantial improvements in visual…

计算机视觉与模式识别 · 计算机科学 2025-03-11 Seil Kang , Jinyeong Kim , Junhyeok Kim , Seong Jae Hwang

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

Visual grounding tasks aim to localize image regions based on natural language references. In this work, we explore whether generative VLMs predominantly trained on image-text data could be leveraged to scale up the text annotation of…

计算机视觉与模式识别 · 计算机科学 2024-07-23 Shijie Wang , Dahun Kim , Ali Taalimi , Chen Sun , Weicheng Kuo

Vision-language models (VLMs) like CLIP have been cherished for their ability to perform zero-shot visual recognition on open-vocabulary concepts. This is achieved by selecting the object category whose textual representation bears the…

计算机视觉与模式识别 · 计算机科学 2024-12-06 Shaunak Halbe , Junjiao Tian , K J Joseph , James Seale Smith , Katherine Stevo , Vineeth N Balasubramanian , Zsolt Kira

Video grounding aims to localize a moment from an untrimmed video for a given textual query. Existing approaches focus more on the alignment of visual and language stimuli with various likelihood-based matching or regression strategies,…

计算机视觉与模式识别 · 计算机科学 2021-07-08 Guoshun Nan , Rui Qiao , Yao Xiao , Jun Liu , Sicong Leng , Hao Zhang , Wei Lu
‹ 上一页 1 2 3 10 下一页 ›