VISTA: Technical Report for the Ego4D Short-Term Object Interaction Anticipation at EgoVis 2026
Researchers have developed VISTA, a novel system designed for anticipating human-object interactions in egocentric videos. VISTA integrates spatial object detection with temporal context from a frozen V-JEPA 2.1 model to predict future interactions. This approach achieved first place in the EgoVis 2026 Ego4D Short-Term Object Interaction Anticipation Challenge. AI
IMPACT Sets a new benchmark for egocentric video analysis and human-object interaction prediction.