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.
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