Vamos: Versatile Action Models for Video Understanding

Benchmark Model Rank Results
video-question-answering-on-next-qaVamos#20Accuracy: 77.3
zero-shot-video-question-answer-on-egoschema-1Vamos (GPT-4o)#15Accuracy: 53.6
zero-shot-video-question-answer-on-egoschema-1Vamos (GPT-4)#19Accuracy: 48.3
zero-shot-video-question-answer-on-egoschema-1Vamos (13B)#22Accuracy: 36.7