Action knowledge for video captioning with graph neural networks

Open paper
Benchmark Model Rank Results
video-captioning-on-msrvtt-ctnAKGNN#2CIDEr: 25.90SPICE: 11.99ROUGE-L: 21.42
video-captioning-on-msvd-ctnAKGNN#2CIDEr: 35.08ROUGE-L: 25.11SPICE: 14.55

Rank counts only results with a code link.