An online mistake detector built from a ViT, Q-Former, and LLM achieves second place on HoloAssist with F1 55.0 and generates error explanations.
Is space-time attention all you need for video understanding? InICML, page 4, 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Technical Report for Egocentric Mistake Detection for the HoloAssist Challenge
An online mistake detector built from a ViT, Q-Former, and LLM achieves second place on HoloAssist with F1 55.0 and generates error explanations.