Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension

Benchmark Model Rank Results
zero-shot-video-question-answer-on-egoschema-1Video-RAG (Based on LLaVA-Video)#5Accuracy: 66.7
zero-shot-video-question-answer-on-video-mmeVideo-RAG (based on LLaVA-Video)#1Accuracy (%): 77.4
zero-shot-video-question-answer-on-video-mme-1Video-RAG (Based on LLaVA-Video)#2Accuracy (%): 77.4
zero-shot-video-question-answer-on-zero-shotVideo-RAG (based on LLaVA-Video)#2Accuracy (% ): 65.4