中文
相关论文

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

200 篇论文

Pretraining egocentric vision-language models has become essential to improving downstream egocentric video-text tasks. These egocentric foundation models commonly use the transformer architecture. The memory footprint of these models…

计算机视觉与模式识别 · 计算机科学 2024-06-17 Hector A. Valdez , Kyle Min , Subarna Tripathi

In Composed Video Retrieval, a video and a textual description which modifies the video content are provided as inputs to the model. The aim is to retrieve the relevant video with the modified content from a database of videos. In this…

计算机视觉与模式识别 · 计算机科学 2024-07-24 Thomas Hummel , Shyamgopal Karthik , Mariana-Iuliana Georgescu , Zeynep Akata

Existing approaches to video understanding, mainly designed for short videos from a third-person perspective, are limited in their applicability in certain fields, such as robotics. In this paper, we delve into open-ended question-answering…

计算机视觉与模式识别 · 计算机科学 2024-04-02 Shangzhe Di , Weidi Xie

Ultra-long egocentric videos spanning multiple days present significant challenges for video understanding. Existing approaches still rely on fragmented local processing and limited temporal modeling, restricting their ability to reason…

计算机视觉与模式识别 · 计算机科学 2026-03-02 Shitong Sun , Ke Han , Yukai Huang , Weitong Cai , Jifei Song

In recent years, the thriving development of research related to egocentric videos has provided a unique perspective for the study of conversational interactions, where both visual and audio signals play a crucial role. While most prior…

计算机视觉与模式识别 · 计算机科学 2024-04-04 Wenqi Jia , Miao Liu , Hao Jiang , Ishwarya Ananthabhotla , James M. Rehg , Vamsi Krishna Ithapu , Ruohan Gao

This paper considers the problem of Multi-Hop Video Question Answering (MH-VidQA) in long-form egocentric videos. This task not only requires to answer visual questions, but also to localize multiple relevant time intervals within the video…

计算机视觉与模式识别 · 计算机科学 2024-08-27 Qirui Chen , Shangzhe Di , Weidi Xie

Video Question Answering (VideoQA) represents a crucial intersection between video understanding and language processing, requiring both discriminative unimodal comprehension and sophisticated cross-modal interaction for accurate inference.…

计算机视觉与模式识别 · 计算机科学 2024-10-15 Ting Yu , Kunhao Fu , Shuhui Wang , Qingming Huang , Jun Yu

In egocentric videos, actions occur in quick succession. We capitalise on the action's temporal context and propose a method that learns to attend to surrounding actions in order to improve recognition performance. To incorporate the…

计算机视觉与模式识别 · 计算机科学 2021-11-02 Evangelos Kazakos , Jaesung Huh , Arsha Nagrani , Andrew Zisserman , Dima Damen

We introduce an approach for pre-training egocentric video models using large-scale third-person video datasets. Learning from purely egocentric data is limited by low dataset scale and diversity, while using purely exocentric…

计算机视觉与模式识别 · 计算机科学 2021-04-19 Yanghao Li , Tushar Nagarajan , Bo Xiong , Kristen Grauman

Egocentric AI agents, such as smart glasses, rely on pointing gestures to resolve referential ambiguities in natural language commands. However, despite advancements in Multimodal Large Language Models (MLLMs), current systems often fail to…

计算机视觉与模式识别 · 计算机科学 2026-04-24 Chentao Li , Zirui Gao , Mingze Gao , Yinglian Ren , Jianjiang Feng , Jie Zhou

Human activities are particularly complex and variable, and this makes challenging for deep learning models to reason about them. However, we note that such variability does have an underlying structure, composed of a hierarchy of patterns…

计算机视觉与模式识别 · 计算机科学 2025-05-20 Simone Alberto Peirone , Francesca Pistilli , Giuseppe Averta

We introduce an object-aware decoder for improving the performance of spatio-temporal representations on ego-centric videos. The key idea is to enhance object-awareness during training by tasking the model to predict hand positions, object…

计算机视觉与模式识别 · 计算机科学 2023-08-16 Chuhan Zhang , Ankush Gupta , Andrew Zisserman

Understanding human behavior from complementary egocentric (ego) and exocentric (exo) points of view enables the development of systems that can support workers in industrial environments and enhance their safety. However, progress in this…

Long-form egocentric video understanding provides rich contextual information and unique insights into long-term human behaviors, holding significant potential for applications in embodied intelligence, long-term activity analysis, and…

计算机视觉与模式识别 · 计算机科学 2026-01-27 Wenqi Zhou , Kai Cao , Hao Zheng , Yunze Liu , Xinyi Zheng , Miao Liu , Per Ola Kristensson , Walterio Mayol-Cuevas , Fan Zhang , Weizhe Lin , Junxiao Shen

Modern vision-language models achieve strong performance in static perception, but remain limited in the complex spatiotemporal reasoning required for embodied, egocentric tasks. A major source of failure is their reliance on temporal…

人工智能 · 计算机科学 2026-04-14 Xiaoda Yang , Yuxiang Liu , Shenzhou Gao , Can Wang , Jingyang Xue , Lixin Yang , Yao Mu , Tao Jin , Shuicheng Yan , Zhimeng Zhang , Zhou Zhao

Mathematical reasoning in real-world video settings presents a fundamentally different challenge than in static images or text. It requires interpreting fine-grained visual information, accurately reading handwritten or digital text, and…

计算机视觉与模式识别 · 计算机科学 2025-06-25 Hanoona Rasheed , Abdelrahman Shaker , Anqi Tang , Muhammad Maaz , Ming-Hsuan Yang , Salman Khan , Fahad Shahbaz Khan

The egocentric and exocentric viewpoints of a human activity look dramatically different, yet invariant representations to link them are essential for many potential applications in robotics and augmented reality. Prior work is limited to…

计算机视觉与模式识别 · 计算机科学 2023-11-28 Zihui Xue , Kristen Grauman

Multimodal large language models (MLLMs) are increasingly considered as a foundation for embodied agents, yet it remains unclear whether they can reliably reason about the long-term physical consequences of actions from an egocentric…

计算机视觉与模式识别 · 计算机科学 2026-03-13 Chengjun Yu , Xuhan Zhu , Chaoqun Du , Pengfei Yu , Wei Zhai , Yang Cao , Zheng-Jun Zha

Can Video-LLMs achieve consistent temporal understanding when videos capture the same event from different viewpoints? To study this, we introduce EgoExo-Con (Consistency), a benchmark of comprehensively synchronized egocentric and…

计算机视觉与模式识别 · 计算机科学 2025-10-31 Minjoon Jung , Junbin Xiao , Junghyun Kim , Byoung-Tak Zhang , Angela Yao

AI personal assistants deployed via robots or wearables require embodied understanding to collaborate with humans effectively. However, current Vision-Language Models (VLMs) primarily focus on third-person view videos, neglecting the…

计算机视觉与模式识别 · 计算机科学 2024-06-24 Alessandro Suglia , Claudio Greco , Katie Baker , Jose L. Part , Ioannis Papaioannou , Arash Eshghi , Ioannis Konstas , Oliver Lemon