共计 3 篇文章

---

2023

论文笔记 Vid2Seq Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning 11-05 论文笔记 SoccerNet-Caption Dense Video Captioning for Soccer Broadcasts Commentaries 10-30 论文笔记 Human-centric Behavior Description in Videos New Benchmark and Model 10-26