又是一个诡异的二进制局部特征，来自今年的cvpr。
个人感觉跟ORB如初一辄，没有太大的新意。当然据paper中的说法是：更快，更好。。。
现在对二进制特征越来越不感冒，除了速度快，其它性能只能说是差强人意。
相对描述子的层出不穷，特征点定位算法自从FAST,AGAST以来就没什么变化了。十分期待一个速度能与FAST媲美的blob型的特征点检测算法。
代码非常简单，可以到github上看。粗看了一下，不同于opencv中的ORB，提供了pattern的训练代码。
话说一年又过去鸟，今年CVPR的组委会公布结果的时候只有paper NO.，所以到现在才整理出CVPR的结果，在这里统计了中国大陆地区（包括香港）的结果，大家积极认领吧，还是和去年一样，木有写台湾的童鞋的论文，如果需要补充也提醒下，如果有留学的童鞋，也可以补充下，手工统计，如有错误，指正。。。。
Orals:
Face Alignment by Explicit Shape Regression， MSRA. PDF
Xudong Cao; Yichen Wei; Fang Wen; Jian Sun
Understanding Collective Crowd Behaviors:Learning Mixture Model of Dynamic Pedestrian-Agents
Bolei Zhou; Xiaogang Wang
A-Optimal Non-negative Projection for Image Representation 浙大的
Zheng Yang; Haifeng Liu
Nonrigid Structure-from-Motion Factorization Made Easy
Yuchao Dai; Hongdong Li; Mingyi He
What Are We Looking For: Towards Statistical Modeling of Saccadic Eye Movements and Visual Saliency 哈工大的
Xiaoshuai Sun; Hongxun Yao; Rongrong Ji; xianming Liu; Pengfei Xu
Street-to-Shop: Cross-Scenario Clothing Retrieval via Parts Alignment and Auxiliary Set 自动化所的
Si Liu; Zheng Song; Guangcan LIU; Changsheng Xu; Hanqing Lu; Shuicheng YAN
PS：cvpapers也有了对应页面，可常关注。
mark几个标题党。
| Editor’s note: the following is an anonymized letter from a Machine Learning researcher who decided to withdraw his submission from CVPR 2012. The submission received ratings of “Definitely Reject,” “Borderline” and “Weakly Reject.” The letter and the paper reviews are posted here with his permission. |
Hi Serge,
We decided to withdraw our paper #[ID no.] from CVPR “[Paper Title]” by [Author Name] et al.
We posted it on ArXiv: http://arxiv.org/ [ Paper ID] .
We are withdrawing it for three reasons: 1) the scores are so low, and the reviews so ridiculous, that I don’t know how to begin writing a rebuttal without insulting the reviewers; 2) we prefer to submit the paper to ICML where it might be better received; 3) with all the fuss I made, leaving the paper in would have looked like I might have tried to bully the program committee into giving it special treatment.
Getting papers about feature learning accepted at vision conference has always been a struggle, and I’ve had more than my share of bad reviews over the years. Thankfully, quite a few of my papers were rescued by area chairs.
This time though, the reviewers were particularly clueless, or negatively biased, or both. I was very sure that this paper was going to get good reviews because: 1) it has two simple and generally applicable ideas for segmentation (“purity tree” and “optimal cover”); 2) it uses no hand-crafted features (it’s all learned all the way through. Incredibly, this was seen as a negative point by the reviewers!); 3) it beats all published results on 3 standard datasets for scene parsing; 4) it’s an order of magnitude faster than the competing methods.
从2001到2011的cvpr best paper列表：
CVPR 2011委员会宣布了以下奖项：
Longuet-Higgins Prize（介绍）
Rapid Object Detection using a Boosted Cascade of Simple Features,（连接）
Paul A. Viola, Michael J. Jones.
Sponsored by Microsoft
经典的viola-jones算法,用过opencv的都知道
Best Paper
Real-time Human Pose Recognition in Parts from Single Depth Images,
Jamie Shotton, Andrew FItzgibbon, Mat Cook, Toby Sharp, Mark Finocchio, Richard Moore, Alex Kipman, Andrew Blake.
Sponsored by Google
Best Paper Honorable Mention
Discrete-Continuous Optimization for Large-scale Structure from Motion,（链接）
David Crandall, Andrew Owens, Noah Snavely, Daniel Huttenlocher
Sponsored by Google
Best Student Paper
Recognition Using Visual Phrases,（链接）
Ali Farhadi, Mohammad Amin Sadeghi
Sponsored by United Technologies Research Center
一个简单实用的视觉重要性检测方法。
Ming-Ming Cheng, Guo-Xin Zhang, Niloy J. Mitra, Xiaolei Huang, Shi-Min Hu. Global Contrast based Salient Region Detection. IEEE CVPR, Colorado Springs, USA, June 21-23, 2011. [Project page] [Bib]
项目主页： http://cg.cs.tsinghua.edu.cn/people/~cmm/saliency/
可执行程序已经公开。专利已经得到受理。代码和论文已经公开。显著性检测代码只有100行左右。
话说在情人节那天早上，偶第一个知道的消息就是悲催的消息，CVPR2011的decisions出来了，群里面貌似也有双borderline+weak ac被拒的Winsty，不过也有很好的消息，可能是由于情人节的关系，群里面已知有两位童鞋的BF/GF/LG/LP被录取了oral，不管怎么样让偶们整理下这次CVPR中国区的结果吧，社群里面的童鞋请认领，各位童鞋以下结果手工录入，如有差错请提醒：
Oral：
最新评论