Whareformer: A Novel Approach for Long Video Object Tracking

dimadamen · x · 2026-07-10

Although trained exclusively on just 50 videos from the EPIC-KITCHENS dataset, the Whareformer model outperformed alternative solutions across over 100 long video tests. The research leverages the online DenStream algorithm to efficiently maintain persistent and transient appearance micro-clusters, enabling the re-tracking of objects in egocentric perspectives even after they disappear for over 30 minutes.

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

Original post →

More from Research

Research channel →