Motion-Appearance Co-Memory Networks for Video Question Answering
Open paper
Benchmark
Model
Rank
Results
visual-question-answering-on-msrvtt-qa-1
Co-Mem
–
Accuracy: 0.32
visual-question-answering-on-msvd-qa-1
Co-Mem
–
Accuracy: 0.317
Rank counts only results with a code link.