Scaling Egocentric Vision: The EPIC-KITCHENS Dataset
read the original abstract
First-person vision is gaining interest as it offers a unique viewpoint on people's interaction with objects, their attention, and even intention. However, progress in this challenging domain has been relatively slow due to the lack of sufficiently large datasets. In this paper, we introduce EPIC-KITCHENS, a large-scale egocentric video benchmark recorded by 32 participants in their native kitchen environments. Our videos depict nonscripted daily activities: we simply asked each participant to start recording every time they entered their kitchen. Recording took place in 4 cities (in North America and Europe) by participants belonging to 10 different nationalities, resulting in highly diverse cooking styles. Our dataset features 55 hours of video consisting of 11.5M frames, which we densely labeled for a total of 39.6K action segments and 454.3K object bounding boxes. Our annotation is unique in that we had the participants narrate their own videos (after recording), thus reflecting true intention, and we crowd-sourced ground-truths based on these. We describe our object, action and anticipation challenges, and evaluate several baselines over two test splits, seen and unseen kitchens. Dataset and Project page: http://epic-kitchens.github.io
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
Contextual Role Modulates Object Representational Geometry in the Human Brain
fMRI during naturalistic movies shows context-dependent double dissociation in object representational geometry: action targets organized by affordances in parietal networks, passive objects by semantics in occipito-t...
-
Decoding Pedestrian Crossing Intention from Egocentric Vision via Vision Language Models
Fine-tuned VLMs guided by eye gaze and ego motion achieve 14.5% accuracy improvement over a transformer baseline for egocentric pedestrian intent decoding.
-
The Conversations Beneath the Code: Triadic Data for Long-Horizon Software Engineering Agents
Triadic data—synchronized human-human conversations, human-AI sessions, and cross-functional team work—is the essential substrate for training long-horizon software engineering agents.
-
Contextual Role Modulates Object Representational Geometry in the Human Brain
fMRI during naturalistic movies shows context (action target vs passive) remaps object representational geometry via double dissociation in affordance vs semantic dimensions within selective networks.
-
World Action Models: The Next Frontier in Embodied AI
The paper introduces World Action Models as a new paradigm unifying predictive world modeling with action generation in embodied foundation models and provides a taxonomy of existing approaches.
-
World Action Models: A Survey
A survey that clarifies boundaries and organizes World Action Models by generation requirements and predictive substrates, identifying a trend toward generating less of the future.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.