CE$^4$L: Continual Ego, Exo, and Ego-Exo Learning
Quick summary
arXiv:2609.23492v1 Announce Type: cross Abstract: Perception for embodied agents is video-based, often multi-view (ego, exo, or both), and inherently continual, with simultaneous task and viewpoint shifts. Yet continual learning (CL) remains dominated by exo-only recognition tasks, obscuring behavior under these real-world coupled shifts. We introduce Continual Ego, E}xo, and Ego-Exo Learning (CE$^4$L), a unified multi-view CL benchmark spanning four representative tasks: cross-view referenced skill assessment, temporal action segmentation, cross-view association, and action anticipation & pla
Key takeaways
- arXiv:2609.23492v1 Announce Type: cross Abstract: Perception for embodied agents is video-based, often multi-view (ego, exo, or both), and inherently continual, with simultaneous task and viewpoint shifts.
- Yet continual learning (CL) remains dominated by exo-only recognition tasks, obscuring behavior under these real-world coupled shifts.
- We introduce Continual Ego, E}xo, and Ego-Exo Learning (CE$^4$L), a unified multi-view CL benchmark spanning four representative tasks: cross-view referenced skill assessment, temporal action segmentation, cross-view association, and action anticipation & pla
Why it matters
The value of this work lies as much in how it was tested as in the claim itself. Sample design, baselines, uncertainty and replication help separate a laboratory result from real-world impact.
Member comments