Whareformer: A Novel Approach for Long Video Object Tracking

dimadamen · x · 2026-07-10

Whareformer trains an embedding network that integrates appearance and position discrepancies, utilizing a transformer encoder for contrastive assignment. Its memory mechanism updates based on online assignment without ever deleting trajectories, empowering the model to reuse and track objects across extremely long time intervals in egocentric videos.

Related event: Whareformer: A New Approach for Online Object Tracking in Long Egocentric Videos(6 posts)→

Original post →

More from Research

Research channel →