Related papers: Exo2Ego: Exocentric Knowledge Guided MLLM for Egoc…
Robot learning increasingly depends on large and diverse data, yet robot data collection remains expensive and difficult to scale. Egocentric human data offer a promising alternative by capturing rich manipulation behavior across everyday…
We introduce EgoLife, a project to develop an egocentric life assistant that accompanies and enhances personal efficiency through AI-powered wearable glasses. To lay the foundation for this assistant, we conducted a comprehensive data…
Understanding human activity is a crucial yet intricate task in egocentric vision, a field that focuses on capturing visual perspectives from the camera wearer's viewpoint. Traditional methods heavily rely on representation learning that is…
Given a video captured from a first person perspective and the environment context of where the video is recorded, can we recognize what the person is doing and identify where the action occurs in the 3D space? We address this challenging…
We pose keystep recognition as a node classification task, and propose a flexible graph-learning framework for fine-grained keystep recognition that is able to effectively leverage long-term dependencies in egocentric videos. Our approach,…
Egocentric videos provide a distinctive setting in which sound serves as crucial cues to understand user activities and surroundings, particularly when visual information is unstable or occluded due to continuous camera movement.…
Egocentric video is increasingly used as a data source for robot learning, activity understanding, and embodied AI research, but collecting it at scale remains fragmented in practice: each candidate host device, such as an Android phone,…
Egocentric gestures are the most natural form of communication for humans to interact with wearable devices such as VR/AR helmets and glasses. A major issue in such scenarios for real-world applications is that may easily become necessary…
People continuously perceive and interact with their surroundings based on underlying intentions that drive their exploration and behaviors. While research in egocentric user and scene understanding has focused primarily on motion and…
Human demonstrations offer rich environmental diversity and scale naturally, making them an appealing alternative to robot teleoperation. While this paradigm has advanced robot-arm manipulation, its potential for the more challenging,…
The pursuit of artificial general intelligence (AGI) has been accelerated by Multimodal Large Language Models (MLLMs), which exhibit superior reasoning, generalization capabilities, and proficiency in processing multimodal inputs. A crucial…
Ego-to-exo video generation refers to generating the corresponding exocentric video according to the egocentric video, providing valuable applications in AR/VR and embodied AI. Benefiting from advancements in diffusion model techniques,…
An embodied AI assistant operating on egocentric video must integrate spatial cues across time - for instance, determining where an object A, glimpsed a few moments ago lies relative to an object B encountered later. We introduce…
Procedure learning involves identifying the key-steps and determining their logical order to perform a task. Existing approaches commonly use third-person videos for learning the procedure, making the manipulated object small in appearance…
What if accessing the web did not require a screen, a stable desk, or even free hands? For people navigating crowded cities, living with low vision, or experiencing cognitive overload, smart glasses coupled with AI agents could turn the web…
Monocular egocentric human pose estimation is essential for ubiquitous activity monitoring. However, understanding the user's absolute location within the environment remains a challenge. Existing methods primarily focus on relative motion…
We introduce LEAP (illustrated in Figure 1), a novel method for generating video-grounded action programs through use of a Large Language Model (LLM). These action programs represent the motoric, perceptual, and structural aspects of…
This paper introduces EgoMAGIC (Medical Assistance, Guidance, Instruction, and Correction), an egocentric medical activity dataset collected as part of DARPA's Perceptually-enabled Task Guidance (PTG) program. This dataset comprises 3,355…
We introduce EgoSchema, a very long-form video question-answering dataset, and benchmark to evaluate long video understanding capabilities of modern vision and language systems. Derived from Ego4D, EgoSchema consists of over 5000 human…
Visual grounding associates textual descriptions with objects in an image. Conventional methods target third-person image inputs and named object queries. In applications such as AI assistants, the perspective shifts -- inputs are…