Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding
Open paper
Benchmark
Model
Rank
Results
video-question-answering-on-lvbench
Active Video Perception (Gemini-2.5-Pro)
–
Accuracy: 74.8
video-question-answering-on-mlvu
Active Video Perception (Gemini-2.5-Pro)
–
Accuracy: 84.3
Rank counts only results with a code link.