Related papers: EgoPrompt: Prompt Learning for Egocentric Action R…
Egocentric action recognition is gaining significant attention in the field of human action recognition. In this paper, we address data scarcity issue in egocentric action recognition from a compositional generalization perspective. To…
Egocentric video-language pretraining is a crucial step in advancing the understanding of hand-object interactions in first-person scenarios. Despite successes on existing testbeds, we find that current EgoVLMs can be easily misled by…
Recognizing human activities from visual inputs, particularly through a first-person viewpoint, is essential for enabling robots to replicate human behavior. Egocentric vision, characterized by cameras worn by observers, captures diverse…
Understanding affect is central to anticipating human behavior, yet current egocentric vision benchmarks largely ignore the person's emotional states that shape their decisions and actions. Existing tasks in egocentric perception focus on…
Video-Language Pretraining (VLP), which aims to learn transferable representation to advance a wide range of video-text downstream tasks, has recently received increasing attention. Best performing works rely on large-scale, 3rd-person…
Long-term action anticipation from egocentric video is critical for applications such as human-computer interaction and assistive technologies, where anticipating user intent enables proactive and context-aware AI assistance. However,…
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…
AI personal assistants, deployed through robots or wearables, require embodied understanding to collaborate effectively with humans. However, current Multimodal Large Language Models (MLLMs) primarily focus on third-person (exocentric)…
Predicting when to initiate speech in real-world environments remains a fundamental challenge for conversational agents. We introduce EgoSpeak, a novel framework for real-time speech initiation prediction in egocentric streaming video. By…
Egocentric assistants often rely on first-person view data to capture user behavior and context for personalized services. Since different users exhibit distinct habits, preferences, and routines, such personalization is essential for truly…
For efficient human-agent interaction, an agent should proactively recognize their target user and prepare for upcoming interactions. We formulate this challenging problem as the novel task of jointly forecasting a person's intent to…
Advancements in egocentric video datasets like Ego4D, EPIC-Kitchens, and Ego-Exo4D have enriched the study of first-person human interactions, which is crucial for applications in augmented reality and assisted living. Despite these…
Egocentric action anticipation consists in understanding which objects the camera wearer will interact with in the near future and which actions they will perform. We tackle the problem proposing an architecture able to anticipate actions…
Egocentric vision captures the scene from the point of view of the camera wearer, while exocentric vision captures the overall scene context. Jointly modeling ego and exo views is crucial to developing next-generation AI agents. The…
The EPIC-KITCHENS-100 Action Detection challenge evaluates whether a model can localize the start and end of each action in long untrimmed egocentric videos and assign the corresponding verb--noun action label. In this report, we formulate…
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…
Analyzing instructional interactions between an instructor and a learner who are co-present in the same physical space is a critical problem for educational support and skill transfer. Yet such face-to-face instructional scenes have not…
Humans can rearrange objects in cluttered environments using egocentric perception, navigating occlusions without global coordinates. Inspired by this capability, we study long-horizon multi-object non-prehensile rearrangement for mobile…
Embodied cognition argues that intelligence arises from sensorimotor interaction rather than passive observation. It raises an intriguing question: do modern vision-language models (VLMs), trained largely in a disembodied manner, exhibit…
Humans develop visual intelligence through perceiving and interacting with their environment - a self-supervised learning process grounded in egocentric experience. Inspired by this, we ask how can artificial systems learn stable object…