中文
相关论文

相关论文: Minerva-Ego: Spatiotemporal Hints for Egocentric V…

200 篇论文

While video large language models (Video-LLMs) excel in understanding slow-paced, real-world egocentric videos, their capabilities in high-velocity, information-dense virtual environments remain under-explored. Existing benchmarks focus on…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Jianzhe Ma , Zhonghao Cao , Shangkui Chen , Yichen Xu , Wenxuan Wang , Qin Jin

Understanding egocentric videos plays a vital role for embodied intelligence. Recent multi-modal large language models (MLLMs) can accept both visual and audio inputs. However, due to the challenge of obtaining text labels with coherent…

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

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

Vision-language models (VLMs) have recently shown promising results in traditional downstream tasks. Evaluation studies have emerged to assess their abilities, with the majority focusing on the third-person perspective, and only a few…

计算机视觉与模式识别 · 计算机科学 2024-03-29 Sijie Cheng , Zhicheng Guo , Jingwen Wu , Kechen Fang , Peng Li , Huaping Liu , Yang Liu

Understanding and answering questions based on a user's pointing gesture is essential for next-generation egocentric AI assistants. However, current Multimodal Large Language Models (MLLMs) struggle with such tasks due to the lack of…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Yura Choi , Roy Miles , Rolandos Alexandros Potamias , Ismail Elezi , Jiankang Deng , Stefanos Zafeiriou

Egocentric video reasoning centers on an unobservable agent behind the camera who dynamically shapes the environment, requiring inference of hidden intentions and recognition of fine-grained interactions. This core challenge limits current…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Baoqi Pei , Yifei Huang , Jilan Xu , Yuping He , Guo Chen , Fei Wu , Yu Qiao , Jiangmiao Pang

The enhancement of generalization in robots by large vision-language models (LVLMs) is increasingly evident. Therefore, the embodied cognitive abilities of LVLMs based on egocentric videos are of great interest. However, current datasets…

计算机视觉与模式识别 · 计算机科学 2025-03-14 Ronghao Dang , Yuqian Yuan , Wenqi Zhang , Yifei Xin , Boqiang Zhang , Long Li , Liuyi Wang , Qinyang Zeng , Xin Li , Lidong Bing

Long-horizon egocentric video presents significant challenges for visual navigation due to viewpoint drift and the absence of persistent geometric context. Although recent vision-language models perform well on image and short-video…

计算机视觉与模式识别 · 计算机科学 2026-04-09 James Tribble , Hao Wang , Si-En Hong , Chaoyi Zhou , Ashish Bastola , Siyu Huang , Abolfazl Razi

Egocentric video-language understanding demands both high efficiency and accurate spatial-temporal modeling. Existing approaches face three key challenges: 1) Excessive pre-training cost arising from multi-stage pre-training pipelines, 2)…

计算机视觉与模式识别 · 计算机科学 2025-06-18 Xiaoqi Wang , Yi Wang , Lap-Pui Chau

Egocentric Video Question Answering (QA) requires models to handle long-horizon temporal reasoning, first-person perspectives, and specialized challenges like frequent camera movement. This paper systematically evaluates both proprietary…

计算机视觉与模式识别 · 计算机科学 2025-04-08 Alkesh Patel , Vibhav Chitalia , Yinfei Yang

Despite extensive efforts on egocentric video datasets and benchmarks, understanding users' internal states, which is crucial for enabling seamless AI assistant experiences, remains largely overlooked. In this work, we introduce…

Large Video-Language Models (Video-LMs) have achieved impressive progress in multimodal understanding, yet their reasoning remains weakly grounded in space and time. We present Know-Show, a new benchmark designed to evaluate spatio-temporal…

计算机视觉与模式识别 · 计算机科学 2026-04-01 Chinthani Sugandhika , Chen Li , Deepu Rajan , Basura Fernando

Multimodal AI agents are increasingly automating complex real-world workflows that involve online web execution. However, current web-agent benchmarks suffer from a critical limitation: they focus entirely on web-based interaction and…

计算机视觉与模式识别 · 计算机科学 2026-03-25 Shoubin Yu , Lei Shu , Antoine Yang , Yao Fu , Srinivas Sunkara , Maria Wang , Jindong Chen , Mohit Bansal , Boqing Gong

Recent video multimodal large language models achieve impressive results across various benchmarks. However, current evaluations suffer from two critical limitations: (1) inflated scores can mask deficiencies in fine-grained visual…

计算机视觉与模式识别 · 计算机科学 2026-04-03 Jiahao Meng , Tan Yue , Qi Xu , Haochen Wang , Zhongwei Ren , Weisong Liu , Yuhao Wang , Renrui Zhang , Yunhai Tong , Haodong Duan

Video understanding typically requires fine-tuning the large backbone when adapting to new domains. In this paper, we leverage the egocentric video foundation models (Ego-VFMs) based on video-language pre-training and propose a…

计算机视觉与模式识别 · 计算机科学 2025-02-28 Tz-Ying Wu , Kyle Min , Subarna Tripathi , Nuno Vasconcelos

The emergence of advanced multimodal large language models (MLLMs) has significantly enhanced AI assistants' ability to process complex information across modalities. Recently, egocentric videos, by directly capturing user focus, actions,…

计算机视觉与模式识别 · 计算机科学 2025-10-15 Taiying Peng , Jiacheng Hua , Miao Liu , Feng Lu

Egocentric video understanding is inherently complex due to the dynamic 4D nature of the environment, where camera motion and object displacements necessitate a continuous re-evaluation of spatial relations. In this work, we target a suite…

计算机视觉与模式识别 · 计算机科学 2026-04-01 Fangrui Zhu , Yunfeng Xi , Jianmo Ni , Mu Cai , Boqing Gong , Long Zhao , Chen Qu , Ian Miao , Yi Li , Cheng Zhong , Huaizu Jiang , Shwetak Patel

Emerging embodied AI applications, such as wearable cameras and autonomous agents, have underscored the need for robust reasoning from first person video streams. We introduce EgoVLM, a vision-language model specifically designed to…

计算机视觉与模式识别 · 计算机科学 2025-06-04 Ashwin Vinod , Shrey Pandit , Aditya Vavre , Linshen Liu

First-person video highlights a camera-wearer's activities in the context of their persistent environment. However, current video understanding approaches reason over visual features from short video clips that are detached from the…

计算机视觉与模式识别 · 计算机科学 2023-11-13 Tushar Nagarajan , Santhosh Kumar Ramakrishnan , Ruta Desai , James Hillis , Kristen Grauman