中文
相关论文

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

200 篇论文

Recently, there is a surge in interest surrounding video large language models (Video LLMs). However, existing benchmarks fail to provide a comprehensive feedback on the temporal perception ability of Video LLMs. On the one hand, most of…

计算机视觉与模式识别 · 计算机科学 2024-06-04 Yuanxin Liu , Shicheng Li , Yi Liu , Yuxiang Wang , Shuhuai Ren , Lei Li , Sishuo Chen , Xu Sun , Lu Hou

Efficient video tokenization remains a key bottleneck in learning general purpose vision models that are capable of processing long video sequences. Prevailing approaches are restricted to encoding videos to a fixed number of tokens, where…

机器学习 · 计算机科学 2025-02-04 Wilson Yan , Volodymyr Mnih , Aleksandra Faust , Matei Zaharia , Pieter Abbeel , Hao Liu

Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in short video understanding. However, understanding long-form videos still remains challenging for MLLMs. This paper proposes TimeSuite, a collection of new…

计算机视觉与模式识别 · 计算机科学 2025-02-13 Xiangyu Zeng , Kunchang Li , Chenting Wang , Xinhao Li , Tianxiang Jiang , Ziang Yan , Songze Li , Yansong Shi , Zhengrong Yue , Yi Wang , Yali Wang , Yu Qiao , Limin Wang

Temporal Video Grounding (TVG), which requires pinpointing relevant temporal segments from video based on language query, has always been a highly challenging task in the field of video understanding. Videos often have a larger volume of…

计算机视觉与模式识别 · 计算机科学 2025-07-08 Feng Yue , Zhaoxing Zhang , Junming Jiao , Zhengyu Liang , Shiwen Cao , Feifei Zhang , Rong Shen

The task of video geolocalization aims to determine the precise GPS coordinates of a video's origin and map its trajectory; with applications in forensics, social media, and exploration. Existing classification-based approaches operate at a…

计算机视觉与模式识别 · 计算机科学 2026-04-15 Parth Parag Kulkarni , Rohit Gupta , Prakash Chandra Chhipa , Mubarak Shah

We address temporal action localization in untrimmed long videos. This is important because videos in real applications are usually unconstrained and contain multiple action instances plus video content of background scenes or other…

计算机视觉与模式识别 · 计算机科学 2016-04-25 Zheng Shou , Dongang Wang , Shih-Fu Chang

Temporal awareness is essential for video large language models (LLMs) to understand and reason about events within long videos, enabling applications like dense video captioning and temporal video grounding in a unified system. However,…

计算机视觉与模式识别 · 计算机科学 2024-11-27 Andong Deng , Zhongpai Gao , Anwesa Choudhuri , Benjamin Planche , Meng Zheng , Bin Wang , Terrence Chen , Chen Chen , Ziyan Wu

Many methods have been developed to help people find the video contents they want efficiently. However, there are still some unsolved problems in this area. For example, given a query video and a reference video, how to accurately localize…

计算机视觉与模式识别 · 计算机科学 2018-08-07 Yang Feng , Lin Ma , Wei Liu , Tong Zhang , Jiebo Luo

Temporal moment localization aims to retrieve the best video segment matching a moment specified by a query. The existing methods generate the visual and semantic embeddings independently and fuse them without full consideration of the…

计算机视觉与模式识别 · 计算机科学 2021-09-08 Jungkyoo Shin , Jinyoung Moon

Multimodal large language models (MLLMs) have made remarkable progress in either temporal or spatial localization. However, they struggle to perform spatio-temporal video grounding. This limitation stems from two major challenges. Firstly,…

计算机视觉与模式识别 · 计算机科学 2025-04-14 Jiankang Wang , Zhihan Zhang , Zhihang Liu , Yang Li , Jiannan Ge , Hongtao Xie , Yongdong Zhang

In long-video understanding, conventional uniform frame sampling often fails to capture key visual evidence, leading to degraded performance and increased hallucinations. To address this, recent agentic thinking-with-videos paradigms have…

We propose LocFormer, a Transformer-based model for video grounding which operates at a constant memory footprint regardless of the video length, i.e. number of frames. LocFormer is designed for tasks where it is necessary to process the…

计算机视觉与模式识别 · 计算机科学 2021-12-21 Cristian Rodriguez-Opazo , Edison Marrese-Taylor , Basura Fernando , Hiroya Takamura , Qi Wu

This paper studies the joint learning of action recognition and temporal localization in long, untrimmed videos. We employ a multi-task learning framework that performs the three highly related steps of action proposal, action recognition,…

计算机视觉与模式识别 · 计算机科学 2017-04-05 Yi Zhu , Shawn Newsam

Temporal action localization aims to identify the boundaries and categories of actions in videos, such as scoring a goal in a football match. Single-frame supervision has emerged as a labor-efficient way to train action localizers as it…

Despite significant advances in Multimodal Large Language Models (MLLMs), understanding complex temporal dynamics in videos remains a major challenge. Our experiments show that current Video Large Language Model (Video-LLM) architectures…

计算机视觉与模式识别 · 计算机科学 2025-10-31 Ali Rasekh , Erfan Bagheri Soula , Omid Daliran , Simon Gottschalk , Mohsen Fayyaz

Locating actions in long untrimmed videos has been a challenging problem in video content analysis. The performances of existing action localization approaches remain unsatisfactory in precisely determining the beginning and the end of an…

计算机视觉与模式识别 · 计算机科学 2018-06-27 Haonan Qiu , Yingbin Zheng , Hao Ye , Yao Lu , Feng Wang , Liang He

Temporal action localization is an important yet challenging problem. Given a long, untrimmed video consisting of multiple action instances and complex background contents, we need not only to recognize their action categories, but also to…

计算机视觉与模式识别 · 计算机科学 2017-06-14 Zheng Shou , Jonathan Chan , Alireza Zareian , Kazuyuki Miyazawa , Shih-Fu Chang

We propose UnLoc, an efficient data-driven solution for sequential camera localization within floorplans. Floorplan data is readily available, long-term persistent, and robust to changes in visual appearance. We address key limitations of…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Matthias Wüest , Francis Engelmann , Ondrej Miksik , Marc Pollefeys , Daniel Barath

Temporal action localization plays an important role in video analysis, which aims to localize and classify actions in untrimmed videos. The previous methods often predict actions on a feature space of a single-temporal scale. However, the…

计算机视觉与模式识别 · 计算机科学 2022-08-17 Zan Gao , Xinglei Cui , Tao Zhuo , Zhiyong Cheng , An-An Liu , Meng Wang , Shenyong Chen

We present a general approach to video understanding, inspired by semantic transfer techniques that have been successfully used for 2D image analysis. Our method considers a video to be a 1D sequence of clips, each one associated with its…

计算机视觉与模式识别 · 计算机科学 2017-04-18 Dotan Kaufman , Gil Levi , Tal Hassner , Lior Wolf