CVPR 2013 录用论文(目标跟踪部分)

转载:http://blog.csdn.net/gxf1027/article/details/8650878#comments

完整录用论文官方链接:http://www.pamitc.org/cvpr13/program.php

CvPapers链接已出

今年有关RGB-D摄像机应用和研究的论文渐多起来了。

当然,自己还是比较关心Tracking方面的Papers。从作者来看,一作大部分为华人,而且有不少在Tracking这个圈子里相当有名的牛,比如Ming-Hsuan YangRobert CollinsChunhua Shen等。此外,从录用论文题目初步判断,Sparse coding(representation)的热度在减退,所以Haibin Ling老师并没有这方面的文章录用,且纯粹的tracking-by-detection几乎不见踪影了。

以下是摘录的tracking方面的录用论文:

Oral部分:

Structure Preserving Object Tracking. Lu Zhang, Laurens van der Maaten

Tracking Sports Players with Context-Conditioned Motion Models. Jingchen Liu, Peter Carr, Robert Collins, Yanxi Liu

 

Post部分:

Online Object Tracking: A Benchmark. Yi Wu, Jongwoo Lim,Ming-Hsuan Yang(目标跟踪的测试视频真是越来越脱离实际了,为什么不多从一些实际应用场景中截取呢。此外,还是极其佩服作者的耐心和贡献,他/她<光从名字真不好判断啊>用了两种metric来全面地评价state-of-the-art trackers。其中用到了AUC曲线<记录在不同重叠率或中心定位误差限制下的跟踪sucess ratio>,我觉得这是非常严谨的做法,这大概是首创吧。并且,测试了不同初始化<模拟了检测器输出的位置误差,和在视频不同阶段开始跟踪测试>情况下trackers的表现,这也是之前几乎没人做过的吧。做这种测试还是需要投入大量时间,光是让各种codes在自己的机器上跑起来有时候就会让人很抓狂了,其中的繁琐也只有做过的人才能真正体会吧。剧透一下,最终的结果No.1属于Struck

Learning Compact Binary Codes for Visual Tracking. Xi Li,Chunhua Shen, Anthony Dick, Anton van den Hengel (延续了作者之前论文的体系,包括用SVM做跟踪和加入图结构来描述样本间的关联等。虽然把Binary Codes放到题目里,但是作者却没有明晰地解释为什么要用二值特征。这让像我这样的初学者不解到底费这么大劲把实值特征转换为二进制串的收益在哪里。)

Part-based Visual Tracking with Online Latent Structural Learning. Rui Yao, Qinfeng Shi,Chunhua Shen, Yanning Zhang, Anton van den Hengel

Self-paced learning for long-term tracking.James Supancic III, Deva Ramanan(long-term的噱头还是很吸引人的,和当年TLD一样,看看是否是工程的思想多一些)

Visual Tracking via Locality Sensitive Histograms.Shengfeng He, Qingxiong Yang, Rynson Lau, Jiang Wang, Ming-Hsuan Yang (CityU of HK,使用直方图作为表观在当前研究背景下真是反其道而行之啊)

Minimum Uncertainty Gap for Robust Visual Tracking. Junseok Kwon, Kyoung Mu Lee (VTD作者,浏览了一下论文,满屏的公式推导啊,没有看下去的动力了)

Least Soft-thresold Squares Tracking. Dong Wang,Huchuan Lu,Ming-Hsuan Yang(本来对这篇很有期望的,但是看完之后感情受欺骗......和作者的Online Object Tracking with Sparse Prototypes从目标函数和优化方法来看几乎是一模一样的,只是叙述的角度不同。不言明了)

Tracking People and Their Objects. Tobias Baumgartner,Dennis Mitzel, Bastian Leibe(这个应该也有应用的背景和前景)

(以上不全包括多目标跟踪方面的论文)

 

 其它关注的论文:

Alternating Decision Forests.Samuel Schulter, Paul Wohlhart,Christian Leistner, Amir Saffari,Peter M. Roth,Horst Bischof(Forest也是近些年的热点之一。此外,TU Graz视觉组在各种Top会议上很是active。作者将Boosting的思想引入到RF中,对样本分类的难易程度作为样本权重)

Semi-supervised Node Splitting for Random Forest Construction. Xiao Liu, Mingli Song, Dacheng Tao, Zicheng Liu, Luming Zhang, Chun Chen, Jiajun Bu (虽然Forest很热,但是纯粹关于Forest的研究还是不多,在这类会议上)

Optimizing 1-Nearest Prototype Classifiers.Paul Wohlhart, Michael Donoser, Peter Roth,Horst Bischof (by TU Graz)

Single-Pedestrian Detection aided by Multi-pedestrian Detection. Wanli Ouyang, Xiaogang Wang

Measuring Crowd Collectiveness.Bolei Zhou,Xiaogang Wang (群体行为分析方面顶尖的组,一作小牛人)

Crossing the Line: Crowd Counting by Integer Programming with Local Features. Zheng Ma,Antoni Chan

Histograms of Sparse Codes for Object Detection. Xiaofeng Ren,Deva Ramanan

Multi-Source Multi-Scale Counting in Extremely Dense Crowd Images. Haroon Idrees, Imran Saleemi, Mubarak Shah

Human Pose Estimation from Still Images using Body Parts Dependent Joint Regressors.Matthias Dantone,Juergen Gall, Luc Van Gool, Christian Leistner (Gall的Hough Forest令人印象比较深)

Efficient Detector Adaptation for Object Detection in a Video.Pramod Sharma, Ram Nevatia

Robust Multi-Resolution Pedestrian Detection in Traffic Scenes. Junjie Yan, Xucong Zhang, Zhen Lei, Dong Yi, Shengcai Liao, Stan Li (Oral)

Fast multiple-part based object detection using KD-Ferns. Dan Levi, Shai Silberstein, Aharon Bar-Hillel 

Online Dominant and Anomalous Behavior Detection in VideosMehrsan Javan Roshtkhari, Martin Levine

BoF meets HOG: Feature Extraction based on Histograms of Oriented p.d.f Gradients for Image Classification. Takumi Kobayashi

Real-time Model-based Rigid Object Pose Estimation and Tracking Combining Dense and Sparse Visual Cues. Karl Pauwels, Leonardo Rubio, Javier Díaz, Eduardo Ros

The SVM-minus Similarity Score for Video Face Recognition. Lior Wolf, Noga Levy

Occlusion patterns for object class detection. Bojan Pepikj, Michael Stark, Peter Gehler, Bernt Schiele

Separable Dictionary Learning. Simon Hawe, Matthias Seibert, Martin Kleinsteuber

Scalable Sparse Subspace Clustering. Xi Peng, Lei Zhang, Zhang Yi

评论 2
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值