Hierarchical Conditional Relation Networks for Video Question Answering

Benchmark Model Rank Results
video-question-answering-on-sutd-trafficqaHCRN#31/4: 36.491/2: 63.79
visual-question-answering-on-msrvtt-qa-1HCRN#22Accuracy: 0.356
visual-question-answering-on-msvd-qa-1HCRN#26Accuracy: 0.361