Existing multi-modal large language models (MLLMs) face significant challenges in processing long video sequences due to strict input token limitations. As a result, current video understanding approaches, especially in egocentric settings characterized by complex dynamics, frequent state changes, and moving cameras, are forced to massively subsample frames. This leads to severe loss of temporal and contextual information, constraining their ability to perform fine-grained video reasoning. In this work, we introduce a framework for egocentric video question answering (VQA) that overcomes these input constraints through Egocentric Scene Graphs (EgoSGs), i.e., temporally grounded, structured representations that capture objects, attributes, spatial relations, and interactions over time. By representing videos as compact, text-based scene graphs, our method preserves the essential visual and temporal information of the original video in a symbolic form that drastically reduces input length while maintaining semantic richness. Crucially, this enables MLLMs to reason efficiently over entire video sequences within their token budget. On HD-EPIC VQA, our method achieves state-of-the-art results, outperforming strong video-based baselines on multiple models and suggesting that structured, temporally grounded representations like EgoSGs can bridge long-form egocentric video understanding and the context limitations of today's MLLMs.
Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Guangxi Zhuang Autonomous Region Information Center（广西壮族自治区信息中心）；The Hong Kong University of Science and Technology（香港科技大学）
EARL: Towards a Unified Analysis-Guided Reinforcement Learning Framework for Egocentric Interaction Reasoning and Pixel Grounding
Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong SAR（香港理工大学电子与电气工程系）；Division of Emerging Interdisciplinary Areas (EMIA), The Hong Kong University of Science and Technology, Hong Kong SAR（香港理工大学新兴跨学科领域研究中心）
University of Groningen（格罗宁根大学）；University of Barcelona（巴塞罗那大学）；Computer Vision Center（计算机视觉中心）
Nowadays, there is an upsurge of interest in using lifelogging devices. Such devices generate huge amounts of image data; consequently, the need for automatic methods for analyzing and summarizing these data is drastically increasing. We present a new method for familiar scene recognition in egocentric videos, based on background pattern detection through automatically configurable COSFIRE filters. We present some experiments over egocentric data acquired with the Narrative Clip.
Georgia Institute of Technology（佐治亚理工学院）；ETH Zürich（苏黎世联邦理工学院）；Zhejiang University（浙江大学）
We introduce a novel task of reconstructing a time series of second-person 3D human body meshes from monocular egocentric videos. The unique viewpoint and rapid embodied camera motion of egocentric videos raise additional technical barriers for human body capture. To address those challenges, we propose a simple yet effective optimization-based approach that leverages 2D observations of the entire video sequence and human-scene interaction constraint to estimate second-person human poses, shapes, and global motion that are grounded on the 3D environment captured from the egocentric view. We co…
CVC, Universitat Autònoma de Barcelona（巴塞罗那自治大学计算机视觉中心）；MICC, University of Florence（佛罗伦萨大学MICC）
Word spotting in natural scene images has many applications in scene understanding and visual assistance. In this paper we propose a technique to create and exploit an intermediate representation of images based on text attributes which are character probability maps. Our representation extends the concept of the Pyramidal Histogram Of Characters (PHOC) by exploiting Fully Convolutional Networks to derive a pixel-wise mapping of the character distribution within candidate word regions. We call this representation the Soft-PHOC. Furthermore, we show how to use Soft-PHOC descriptors for word spo…
University of Groningen（格罗宁根大学）；University of Barcelona（巴塞罗那大学）；University of Rovira i Virgili（罗维拉-威尔吉利大学）
Recent studies have shown that the environment where people eat can affect their nutritional behaviour. In this work, we provide automatic tools for a personalised analysis of a person's health habits by the examination of daily recorded egocentric photo-streams. Specifically, we propose a new automatic approach for the classification of food-related environments, that is able to classify up to 15 such scenes. In this way, people can monitor the context around their food intake in order to get an objective insight into their daily eating routine. We propose a model that classifies food-related…
Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding
State Key Laboratory of General Artificial Intelligence, BIGAI（通用人工智能国家重点实验室）；University of Science and Technology of China（中国科学技术大学）；Tsinghua University（清华大学）；Peking University（北京大学）
EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Zhejiang University（浙江大学）；The University of Tokyo（东京大学）；Fudan University（复旦大学）；Nanjing University（南京大学）
University of Minnesota（明尼苏达大学）；Carnegie Mellon University（卡内基梅隆大学）
In this paper, we study a problem of egocentric scene understanding, i.e., predicting depths and surface normals from an egocentric image. Egocentric scene understanding poses unprecedented challenges: (1) due to large head movements, the images are taken from non-canonical viewpoints (i.e., tilted images) where existing models of geometry prediction do not apply; (2) dynamic foreground objects including hands constitute a large proportion of visual scenes. These challenges limit the performance of the existing models learned from large indoor datasets, such as ScanNet and NYUv2, which compris…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Intel Visual Computing Institute（英特尔视觉计算研究院）；University of Bath（巴斯大学）
Marker-based and marker-less optical skeletal motion-capture methods use an outside-in arrangement of cameras placed around a scene, with viewpoints converging on the center. They often create discomfort by possibly needed marker suits, and their recording volume is severely restricted and often constrained to indoor scenes with controlled backgrounds. We therefore propose a new method for real-time, marker-less and egocentric motion capture which estimates the full-body skeleton pose from a lightweight stereo pair of fisheye cameras that are attached to a helmet or virtual-reality headset. It…
