中文
相关论文

相关论文: EASG-Bench: Video Q&A Benchmark with Egocentric Ac…

200 篇论文

Proactive streaming video understanding requires Video-LLMs to decide when to respond as a video unfolds, a task where existing methods often fall short due to their implicit, query-agnostic modeling of visual evidence. We introduce…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Ke Ma , Jiaqi Tang , Bin Guo , Xueting Han , Ruonan Xu , Qingfeng He , Ziheng Wang , Xu Wang , Qifeng Chen , Zhiwen Yu , Yunhao Liu

Understanding 3D spatial relationships remains a major limitation of current Vision-Language Models (VLMs). Prior work has addressed this issue by creating spatial question-answering (QA) datasets based on single images or indoor videos.…

计算机视觉与模式识别 · 计算机科学 2025-10-01 Mohsen Gholami , Ahmad Rezaei , Zhou Weimin , Sitong Mao , Shunbo Zhou , Yong Zhang , Mohammad Akbari

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

Understanding video content is pivotal for advancing real-world applications like activity recognition, autonomous systems, and human-computer interaction. While scene graphs are adept at capturing spatial relationships between objects in…

计算机视觉与模式识别 · 计算机科学 2025-07-24 Raphael Ruschel , Md Awsafur Rahman , Hardik Prajapati , Suya You , B. S. Manjuanth

Despite recent progress in using Large Language Models (LLMs) for automatically generating 3D scenes, generated scenes often lack realistic spatial layouts and object attributes found in real-world environments. As this problem stems from…

计算与语言 · 计算机科学 2026-01-29 Gyeom Hwangbo , Hyungjoo Chae , Minseok Kang , Hyeonjong Ju , Soohyun Oh , Jinyoung Yeo

This work adapts a deep neural model for image saliency prediction to the temporal domain of egocentric video. We compute the saliency map for each video frame, firstly with an off-the-shelf model trained from static images, secondly by…

计算机视觉与模式识别 · 计算机科学 2018-09-06 Panagiotis Linardos , Eva Mohedano , Monica Cherto , Cathal Gurrin , Xavier Giro-i-Nieto

Existing video understanding benchmarks often conflate knowledge-based and purely image-based questions, rather than clearly isolating a model's temporal reasoning ability, which is the key aspect that distinguishes video understanding from…

计算机视觉与模式识别 · 计算机科学 2025-05-21 Bo Feng , Zhengfeng Lai , Shiyu Li , Zizhen Wang , Simon Wang , Ping Huang , Meng Cao

Video-language alignment is a crucial multi-modal task that benefits various downstream applications, e.g., video-text retrieval and video question answering. Existing methods either utilize multi-modal information in video-text pairs or…

计算机视觉与模式识别 · 计算机科学 2024-07-25 Shi-Xue Zhang , Hongfa Wang , Xiaobin Zhu , Weibo Gu , Tianjin Zhang , Chun Yang , Wei Liu , Xu-Cheng Yin

Recent advancements in Multi-modal Large Language Models (MLLMs) have opened new avenues for applications in Embodied AI. Building on previous work, EgoThink, we introduce VidEgoThink, a comprehensive benchmark for evaluating egocentric…

计算机视觉与模式识别 · 计算机科学 2024-10-16 Sijie Cheng , Kechen Fang , Yangyang Yu , Sicheng Zhou , Bohao Li , Ye Tian , Tingguang Li , Lei Han , Yang Liu

Video Question Answering (VideoQA) is a task that requires a model to analyze and understand both the visual content given by the input video and the textual part given by the question, and the interaction between them in order to produce a…

计算机视觉与模式识别 · 计算机科学 2020-08-25 Alex Falcon , Oswald Lanz , Giuseppe Serra

With the rapid growth of video generative models (VGMs), it is essential to develop reliable and comprehensive automatic metrics for AI-generated videos (AIGVs). Existing methods either use off-the-shelf models optimized for other tasks or…

计算机视觉与模式识别 · 计算机科学 2026-01-21 Yuanxin Liu , Rui Zhu , Shuhuai Ren , Jiacong Wang , Haoyuan Guo , Xu Sun , Lu Jiang

Educational question generation (EQG) is a crucial component of intelligent educational systems, significantly aiding self-assessment, active learning, and personalized education. While EQG systems have emerged, existing datasets typically…

计算与语言 · 计算机科学 2025-04-30 Mengxia Yu , Bang Nguyen , Olivia Zino , Meng Jiang

Children acquire language grounding with remarkable robustness from limited visuo-linguistic input in ways that surpass today's best large multimodal models. Recent research suggests current vision-language models (VLMs) trained on curated…

Understanding long-form egocentric videos remains challenging for multimodal large language models (MLLMs) due to limited context length and insufficient grounding of fine-grained visual details. The recently proposed HD-EPIC benchmark…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Yinsong Xu , Wei Jing , Liuxin Zhang , Wanjun Lv , Hui Li

Recent Video-Language Models (VLMs) achieve promising results on long-video understanding, but their performance still lags behind that achieved on tasks involving images or short videos. This has led to great interest in improving the long…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Lars Doorenbos , Federico Spurio , Juergen Gall

With the rapid development of Multimodal Large Language Models (MLLMs), their potential in Micro-Action understanding, a vital role in human emotion analysis, remains unexplored due to the absence of specialized benchmarks. To tackle this…

计算机视觉与模式识别 · 计算机科学 2026-03-30 Kun Li , Jihao Gu , Fei Wang , Zhiliang Wu , Hehe Fan , Dan Guo

Towards building comprehensive real-world visual perception systems, we propose and study a new problem called panoptic scene graph generation (PVSG). PVSG relates to the existing video scene graph generation (VidSGG) problem, which focuses…

计算机视觉与模式识别 · 计算机科学 2023-11-29 Jingkang Yang , Wenxuan Peng , Xiangtai Li , Zujin Guo , Liangyu Chen , Bo Li , Zheng Ma , Kaiyang Zhou , Wayne Zhang , Chen Change Loy , Ziwei Liu

Environment understanding in egocentric videos is an important step for applications like robotics, augmented reality and assistive technologies. These videos are characterized by dynamic interactions and a strong dependence on the wearer…

计算机视觉与模式识别 · 计算机科学 2025-03-12 Lorenzo Mur-Labadia , Josechu Guerrero , Ruben Martinez-Cantin

Current video benchmarks for multimodal large language models (MLLMs) focus on event recognition, temporal ordering, and long-context recall, but overlook a harder capability required for expert procedural judgment: tracking how ongoing…

计算机视觉与模式识别 · 计算机科学 2026-04-13 Xiyang Huang , Jiawei Lin , Keying Wu , Jiaxin Huang , Kailai Yang , Renxiong Wei , Cheng zeng , Jiayi Xiang , Ziyan Kuang , Min Peng , Qianqian Xie , Sophia Ananiadou

We propose a self-supervised method for learning representations based on spatial audio-visual correspondences in egocentric videos. Our method uses a masked auto-encoding framework to synthesize masked binaural (multi-channel) audio…

计算机视觉与模式识别 · 计算机科学 2024-05-07 Sagnik Majumder , Ziad Al-Halah , Kristen Grauman