iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering
Open paper
Benchmark
Model
Rank
Results
dense-video-captioning-on-activitynet-captions
iPerceive (Chadha et al., 2020)
–
METEOR: 7.87
BLEU-3: 2.93
BLEU-4: 1.29
video-question-answering-on-tvqa
iPerceive (Chadha et al., 2020)
–
Accuracy: 76.96
Rank counts only results with a code link.