论文笔记 | HiT:Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval Posted on 2021-11-09 Edited on 2021-11-26 In Papers Disqus: Symbols count in article: 206 Reading time ≈ 1 mins.论文《HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval》笔记背景和问题概述和总结模型和方法The pipeline of our method.Hierarchical TransformerVideo EncodersTEXT EncodersMomentum Cross-modal ContrastMatchingExperments
