paperreading专题

【PaperReading】Stand-Alone Self-Attention in Vision Models

论文链接:https://arxiv.org/abs/1906.05909 代码:https://github.com/leaderj1001/Stand-Alone-Self-Attention 启示 1. 提出了一种代替空间卷积的操作——self attention,可以有效结合self attention操作和原来的空间卷积操作,在网络的初期使用原来的空间卷积操作,而后面和各个he

【PaperReading】5. Open-Vocabulary SAM

Category Content 论文题目 Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively 作者 Haobo Yuan1 Xiangtai Li1 Chong Zhou1 Yining Li2 Kai Chen2 Chen Change Loy1 1S-Lab, Nanya

【PaperReading】3. PTP

Category Content 论文题目 Position-guided Text Prompt for Vision-Language Pre-training Code: ptp 作者 Alex Jinpeng Wang (Sea AI Lab), Pan Zhou (Sea AI Lab), Mike Zheng Shou (Show Lab, National Univers

【PaperReading- VLM】1. FERRET

CategoryContent论文题目FERRET: REFER AND GROUND ANYTHING ANYWHERE AT ANY GRANULARITY作者Haoxuan You (Columbia University), Haotian Zhang, Zhe Gan, Xianzhi Du, Bowen Zhang, Zirui Wang, Liangliang Cao (Apple

PaperReading: Articulated Multi-Perspective Cameras and Their Application to Truck Motion Estimation

题外话:第一次写博客,之前研一上课也有很多报告想要写到博客中,但拖延症晚期一直没有弄。今天先尝试写一篇Paper Reading 之后再把先前的一些课程作业分享上来。 Paper Reading: Articulated Multi-Perspective Cameras and Their Application to Truck Motion Estimation 铰接多视角摄像机及其在