Self-Chained Image-Language Model for Video Localization and Question Answering

Benchmark Model Rank Results
video-question-answering-on-starSeViLA#3Average Accuracy: 64.9
video-question-answering-on-starSeViLA (0-shot)#12Average Accuracy: 44.6
zero-shot-video-question-answer-on-intentqaSeViLA (4B)#7Accuracy: 60.9
zero-shot-video-question-answer-on-tvqaSEVILA (no speech)#7Accuracy: 38.2
zero-shot-video-question-answer-on-egoschema-subsetSeViLA (4B)#13Accuracy: 25.7
zero-shot-video-question-answer-on-next-qaSevila (4B)#18Accuracy: 63.6
video-question-answering-on-next-qaSeViLA#26Accuracy: 73.8
zero-shot-video-question-answer-on-egoschema-fullsetSeViLA (4B)#54Accuracy: 22.7