这篇论文是daijifeng老师又一篇好文,一贯的好想法,而且实现的很漂亮,arxiv link Motivation 现实图片中的物体变化很多,之前只能通过数据增强来使网络“记住”这些变种如n object scale, pose, viewpoint, and part deformation,但是这种数据增强只能依赖一些先验知识比如反转后物体类别不变等,但是有些变化是未知而且手动设
Windows下运行Discriminatively Trained Deformable Part Models代码 Version 4 Felzenszwalb的Discriminatively Trained Deformable Part Models URL:http://www.cs.brown.edu/~pff/latent/ 这是目前最好的object detect
一、综述 Deformable Part Model和LatentSVM结合用于目标检测由大牛P.Felzenszwalb提出,代表作是以下3篇paper: [1] P. Felzenszwalb, D. McAllester, D.Ramaman. A Discriminatively Trained, Multiscale, Deformable Part Model. Proceed
基于自生成模板的彩色柔性可变形物体重建 论文原文:Jituo Li, Xinqi Liu, Haijing Deng, Tianwei Wang, Guodong Lu, and Jin Wang. 2022. Reconstruction of Colored Soft Deformable Objects Based on Self-Generated Template. Comput. A