Whareformer: A New Architecture for Object Tracking in Long Egocentric Videos
dimadamen · x · 2026-07-10
Whareformer is designed to tackle object tracking (OSNOM) in long egocentric videos, explicitly retaining objects that leave the field of view in its memory. By combining appearance and 3D position discrepancies, and utilizing new trajectory tokens for online learning and memory updates, the model effectively handles the challenge of re-identifying objects after prolonged absences.
More from Research
- ARISE study tested 45 AI clinical tools in 1,100 consult cases — HealthcareAIGuy · 2026-07-21
- Async OPD distillation doubles throughput while matching synchronous math accuracy — _lewtun · 2026-07-21
- A forecasting lesson on why R-squared alone led to overfitting and worse predictions — mdancho84 · 2026-07-21
- Google DeepMind’s Project Genie talk shows how creatives feed into model research — alexanderchen · 2026-07-21
- Nat Lambert says RL distillation does not use the strongest models as teachers — natolambert · 2026-07-21
- Thread claims GPT-5.6 Sol helped build a new counterexample factory for the Jacobian conjecture — LucaAmb · 2026-07-21