GiT: Towards Generalist Vision Transformer through Universal Language Interface

Open paper
Benchmark Model Rank Results
video-captioning-on-msrvtt-ctnGIT#1CIDEr: 32.43SPICE: 13.70ROUGE-L: 24.51
video-captioning-on-msvd-ctnGIT#1CIDEr: 45.63ROUGE-L: 27.51SPICE: 15.58

Rank counts only results with a code link.