中文
相关论文

相关论文: TimeLoc: A Unified End-to-End Framework for Precis…

200 篇论文

Large video-language models (LVLMs) have shown remarkable performance across various video-language tasks. However, they encounter significant challenges when processing long videos because of the large number of video frames involved.…

计算机视觉与模式识别 · 计算机科学 2025-12-03 Junwen Pan , Rui Zhang , Xin Wan , Yuan Zhang , Ming Lu , Qi She

Timestamp prediction aims to determine when an image was captured using only visual information, supporting applications such as metadata correction, retrieval, and digital forensics. In outdoor scenarios, hourly estimates rely on cues like…

计算机视觉与模式识别 · 计算机科学 2025-07-29 David G. Shatwell , Ishan Rajendrakumar Dave , Sirnam Swetha , Mubarak Shah

Temporal Action Localization (TAL) is a challenging task in video understanding that aims to identify and localize actions within a video sequence. Recent studies have emphasized the importance of applying long-term temporal context…

计算机视觉与模式识别 · 计算机科学 2023-03-17 Tuan N. Tang , Kwonyoung Kim , Kwanghoon Sohn

Video Temporal Grounding (VTG) aims to precisely identify video event segments in response to textual queries. The outputs of VTG tasks manifest as sequences of events, each defined by precise timestamps, saliency scores, and textual…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Zuhao Yang , Yingchen Yu , Yunqing Zhao , Shijian Lu , Song Bai

Detecting activities in untrimmed videos is an important but challenging task. The performance of existing methods remains unsatisfactory, e.g., they often meet difficulties in locating the beginning and end of a long complex action. In…

计算机视觉与模式识别 · 计算机科学 2017-03-09 Yuanjun Xiong , Yue Zhao , Limin Wang , Dahua Lin , Xiaoou Tang

This paper presents a computational model for universal video temporal grounding, which accurately localizes temporal moments in videos based on natural language queries (e.g., questions or descriptions). Unlike existing methods that are…

计算机视觉与模式识别 · 计算机科学 2025-11-24 Zeqian Li , Shangzhe Di , Zhonghua Zhai , Weilin Huang , Yanfeng Wang , Weidi Xie

Recently, Weakly-supervised Temporal Action Localization (WTAL) has been densely studied but there is still a large gap between weakly-supervised models and fully-supervised models. It is practical and intuitive to annotate temporal…

计算机视觉与模式识别 · 计算机科学 2020-03-24 Xudong Lin , Zheng Shou , Shih-Fu Chang

While Video Large Language Models (Video-LLMs) have demonstrated remarkable performance across general video understanding benchmarks-particularly in video captioning and descriptive tasks-they consistently underperform on tasks that…

计算机视觉与模式识别 · 计算机科学 2025-10-07 Sameep Vani , Shreyas Jena , Maitreya Patel , Chitta Baral , Somak Aditya , Yezhou Yang

Temporal action localization is a recently-emerging task, aiming to localize video segments from untrimmed videos that contain specific actions. Despite the remarkable recent progress, most two-stage action localization methods still suffer…

计算机视觉与模式识别 · 计算机科学 2019-08-05 Guoqiang Gong , Liangfeng Zheng , Kun Bai , Yadong Mu

Machine learning techniques, namely convolutional neural networks (CNN) and regression forests, have recently shown great promise in performing 6-DoF localization of monocular images. However, in most cases image-sequences, rather only…

计算机视觉与模式识别 · 计算机科学 2017-08-01 Ronald Clark , Sen Wang , Andrew Markham , Niki Trigoni , Hongkai Wen

Due to the large memory footprint of untrimmed videos, current state-of-the-art video localization methods operate atop precomputed video clip features. These features are extracted from video encoders typically trained for trimmed action…

计算机视觉与模式识别 · 计算机科学 2021-08-18 Humam Alwassel , Silvio Giancola , Bernard Ghanem

Recognising actions in videos relies on labelled supervision during training, typically the start and end times of each action instance. This supervision is not only subjective, but also expensive to acquire. Weak video-level supervision…

计算机视觉与模式识别 · 计算机科学 2019-04-10 Davide Moltisanti , Sanja Fidler , Dima Damen

We address the problem of temporal action localization in videos. We pose action localization as a structured prediction over arbitrary-length temporal windows, where each window is scored as the sum of frame-wise classification scores.…

计算机视觉与模式识别 · 计算机科学 2017-04-18 Zehuan Yuan , Jonathan C. Stroud , Tong Lu , Jia Deng

The rapid growth of video content on platforms such as TikTok and YouTube has intensified the spread of multimodal hate speech, where harmful cues emerge subtly and asynchronously across visual, acoustic, and textual streams. Existing…

计算机视觉与模式识别 · 计算机科学 2026-01-30 Qiyue Sun , Tailin Chen , Yinghui Zhang , Yuchen Zhang , Jiangbei Yue , Jianbo Jiao , Zeyu Fu

We propose a novel framework for video understanding, called Temporally Contextualized CLIP (TC-CLIP), which leverages essential temporal information through global interactions in a spatio-temporal domain within a video. To be specific, we…

计算机视觉与模式识别 · 计算机科学 2024-07-25 Minji Kim , Dongyoon Han , Taekyung Kim , Bohyung Han

Video Temporal Grounding (VTG), which aims to ground target clips from videos (such as consecutive intervals or disjoint shots) according to custom language queries (e.g., sentences or words), is key for video browsing on social media. Most…

计算机视觉与模式识别 · 计算机科学 2023-08-21 Kevin Qinghong Lin , Pengchuan Zhang , Joya Chen , Shraman Pramanick , Difei Gao , Alex Jinpeng Wang , Rui Yan , Mike Zheng Shou

Localizing moments in a longer video via natural language queries is a new, challenging task at the intersection of language and video understanding. Though moment localization with natural language is similar to other language and vision…

计算机视觉与模式识别 · 计算机科学 2018-09-06 Lisa Anne Hendricks , Oliver Wang , Eli Shechtman , Josef Sivic , Trevor Darrell , Bryan Russell

The core challenge in video understanding lies in perceiving dynamic content changes over time. However, multimodal large language models struggle with temporal-sensitive video tasks, which requires generating timestamps to mark the…

计算机视觉与模式识别 · 计算机科学 2025-04-11 Henghao Zhao , Ge-Peng Ji , Rui Yan , Huan Xiong , Zechao Li

Temporal grounding of activities, the identification of specific time intervals of actions within a larger event context, is a critical task in video understanding. Recent advancements in multimodal large language models (LLMs) offer new…

计算机视觉与模式识别 · 计算机科学 2024-07-09 Young Chol Song

Prior works on text-based video moment localization focus on temporally grounding the textual query in an untrimmed video. These works assume that the relevant video is already known and attempt to localize the moment on that relevant video…

计算机视觉与模式识别 · 计算机科学 2021-11-10 Sudipta Paul , Niluthpol Chowdhury Mithun , Amit K. Roy-Chowdhury