From c2edaec1cccc2f017907ff838bfec2ea32dd7d3b Mon Sep 17 00:00:00 2001 From: bryanzhu Date: Fri, 5 Nov 2021 20:16:36 -0700 Subject: [PATCH] add three papers --- README.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/README.md b/README.md index 25d9d72..0761a1d 100644 --- a/README.md +++ b/README.md @@ -38,3 +38,6 @@ 1. Video recognition 1. Anchor-free object detection 1. Knowledge graph +1. [MoCo](https://arxiv.org/abs/1911.05722), 对比学习让自监督训练的backbone比有监督训练的更香 +1. [ViT](https://arxiv.org/abs/2010.11929), 开启CV界的transformer时代。 +1. [Two-stream networks](https://arxiv.org/abs/1406.2199)，首次超越手工特征IDT的视频分类架构