ResearcharXivNEW

UNIEGO: Proxies as Mediators for Unified Egocentric Video Representation Learning

Chi 2026-06-18
Wenhao ChiArkaprava SinhaDominick Reilly

Egocentric video understanding is inherently limited by the narrow perspective of wearable cameras: a single viewpoint, a single modality, a single model cannot capture the full richness of human action. We argue that a truly expressive egocentric representation must subsume complementary knowledge across viewpoints, modalities, and foundation model representations, yet remain deployable from egoc

Read on arXiv
Data aggregated and editorially reviewed by TrendMing.

Key Contributions

  • Egocentric video understanding is inherently limited by the narrow perspective of wearable cameras: a single viewpoint, a single modality, a single model cannot capture the full richness of human action.
  • We argue that a truly expressive egocentric representation must subsume complementary knowledge across viewpoints, modalities, and foundation model representations, yet remain deployable from egoc

Research Themes

AIResearch