Language Repository for Long Video Understanding

Benchmark Model Rank Results
zero-shot-video-question-answer-on-egoschemaLangRepo (12B)#3Accuracy: 66.2
zero-shot-video-question-answer-on-egoschema-1LangRepo (12B)#20Accuracy: 41.2
zero-shot-video-question-answer-on-intentqaLangRepo (12B)#9Accuracy: 59.1
zero-shot-video-question-answer-on-next-gqaLangRepo (12B)#6Acc@GQA: 17.1
zero-shot-video-question-answer-on-next-qaLangRepo (12B)#18Accuracy: 60.9