paper-with-me

Video Captioning 벤치마크

Video Captioning on TVC

2개 결과 · ⬇ CSV · JSON

RankModel BLEU-4CIDEr Extra Training Data PaperCodeYear
1 VAST 19.974.1 VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset TXH-mercury/VALOR · txh-mercury/vast 2023
2 COSA 18.870.7 COSA: Concatenated Sample Pretrained Vision-Language Foundation Model txh-mercury/cosa 2023
1–2 / 2 페이지당 10 20 50 100