CVPR2012文章整理

转http://www.bfcat.com/index.php/2012/04/cvpr2012-papers/

 

看了一下CVPR2012的papers on the web，很多文章的链接都还没有出来。根据题目，挑选了几篇感兴趣的。关注一下。有一些链接papers on the web还没有公布，自己上网搜了一下。其他的就等着不定时更新吧。

今年国内的文章不少啊，很多不光是中国人，也是国内高校的。

最佳学生论文：

Max-Margin Early Event Detectors.
Hoai, M. & De la Torre, F. (2012)
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Paper Project BibTex.
Best student paper award

最佳论文：

Yuchao Dai , Hongdong Li, Mingyi He, A simple prior-free method for non rigid structure from motion factorization, To appear in CVPR 2012 (ORAL). [acceptance rate is 2.5% , i.e. 48 papers accepted as oral, out of 1933 submissions.] New paper. 2012. ( PDF preprint ) ( Yuchao was a CSC-funded visiting PhD student from China to ANU;Congratulations to Yuchao !);

显著性：

关于显著性的文章也多起来的，不过大多数是利用显著性来完成其他任务的。关于显著性提取的文章只有几篇。

A Unified Approach to Salient Object Detection via Low Rank Matrix Recovery， Xiaohui Shen, Ying Wu； ORAL 这个和刚刚参加的VALSE2012上面讲的低秩分解应该是有关系的。

What Are We Looking For: Towards Statistical Modeling of Saccadic Eye Movements and Visual Saliency， Xiaoshuai Sun, Hongxun Yao, Rongrong Ji, xianming Liu, Pengfei Xu；哈工大的ORAL 这个和眼动数据扯上关系了。

Boosting Bottom-up and Top-down Visual Features for Saliency Estimation，(PDF) Ali Borji； 高层知识加入进来进行显著性分析

Exploiting Local and Global Patch Rarities for Saliency Detection，(PDF) Ali Borji, Laurent Itti；这个人的另一篇，原来是Itti的学生

Probabilistic Learning of Task-Specific Visual Attention，(PDF) Ali Borji, Dicky Sihite, Laurent Itti； 这个人的第三篇了，全是显著性。。。。

Ali Borji好能写啊。看了一下他的主页，应该是Itti的学生，2009年拿到博士学位的。2012中了5篇第一作者的会议，都是高档的, AAAI, CVPR, ICRA，全是显著性方面的。

Leveraging Stereopsis for Saliency Analysis， Yuzhen Niu, Yujie Geng , Xueqing Li, Feng Liu； 还有一个通过立体视觉进行显著性分析的

Saliency Filters， (PDF) (Project) Federico Perazzi, Philipp Krähenb¨¹hl, Yael Pritch, Alexander Hornung；又提出个新概念，还是基于对比度的

Salient Object Detection for Searched Web Images via Global Saliency，(PDF) Peng Wang, Jingdong Wang, Gang Zeng, Jie Feng, Hongbin Zha；

分割

On Multiple Foreground Cosegmentation，（Project） Gunhee Kim, Eric Xing；ORAL

Weakly Supervised Structured Output Learning for Semantic Segmentation (PDF)， Alexander Vezhnevets, Vittorio Ferrari, Joachim Buhmann； ORAL

Finding Animals: Semantic Segmentation using Regions and Parts，(PDF) Pablo Arbelaez, Bharath Hariharan, Chunhui Gu, Saurabh Gupta, Lubomir Bourdev, Jitendra Malik； ORAL J.Malik的文章肯定要看的

Multi-Class Cosegmentation，(PDF) Armand Joulin, Francis Bach, Jean Ponce； Co-Seg 果然是最热的

Figure-ground segmentation by transferring window masks， Daniel Kuettel, Vittorio Ferrari；

Active Learning for Semantic Segmentation with Expected Change, (PDF), A.Vezhnevets, J. M. Buhmann, V. Ferrari

The Role of Image Understanding in Segmentation，(PDF) Larry Zitnick, Devi Parikh； 题目起的很大气，值得看看

Layered Segmentation and Optical Flow Estimation Over Time，(PDF) (Sup. Mat) Deqing Sun, Erik Sudderth, Michael Black； 多层分割与光流计算，这个有点意思

A Hierarchical Image Clustering Cosegmentation Framework，(PDF) Edward Kim, Hongsheng Li, Xiaolei Huang；

Affinity Learning via Self-diffusion for Image Segmentation and Clustering， Bo Wang, Zhuowen Tu； 据说Zhuowen Tu今年中了好多篇

Describing the Scene as a Whole: Joint Object Detection, Scene Classification and Semantic Segmentation， Jian Yao, Sanja Fidler, Raquel Urtasun； 这个题目起的就更大了

Joint 2D-3D Temporally Consistent Semantic Segmentation of Street Scenes，(PDF) Georgios Floros, Bastian Leibe； 这个主题我感兴趣

Exploiting Nonlocal Spatiotemporal Structure for Video Segmentation，(PDF, Slides)Hsien-Ting Cheng, Narendra Ahuja； 视频分割的，而且是非局部的特征

Joint Motion Estimation and Segmentation of Complex Scenes with Label Costs and Occlusion Modeling， Markus Unger, Manuel Werlberger, Thomas Pock, Horst Bischof； 同时估计运动和遮挡，在复杂场景下如果能做好真不容易

Unsupervised co-segmentation through region matching (PDF)， Jose Rubio, Joan Serrat, Antonio López, Nikos Paragios； 通过区域匹配做联合分割

Segmentation Using Superpixels: A Bipartite Graph Partitioning Approach，(PDF) Zhenguo Li, Xiao-Ming Wu, Shih-Fu Chang； 在超像素上做分割，使用二分图

Multiclass Pixel Labeling with Non-Local Matching Constraints， (PDF) Stephen Gould；

Regression Tree Fields -- An Efficient, Non-parametric Approach to Image Labeling Problems (PDF,project, supplementary material)， Jeremy Jancsary, Sebastian Nowozin, Toby Sharp, Carsten Rother

视频

Evaluation of Super-Voxel Methods for Early Video Processing (PDF)， Chenliang Xu (SUNNY at Buffalo), Jason J. Corso(SUNNY at Buffalo)

Discovering Important People and Objects for Egocentric Video Summarization，(PDF) （Project）Yong Jae Lee, Joydeep Ghosh, Kristen Grauman 美女教授今年有5篇CVPR

Video Stabilization with a Depth Camera， Shuaicheng Liu, Yingting Wang, Lu Yuan, Ping Tan, Jian Sun；视频稳像，现在不算很热点了，但是还是一个很值得做的方向

Higher Order Motion Models and Spectral Clustering，(PDF) Peter Ochs, Thomas Brox； 做视频分割的

立体视觉

A Closed-Form Solution to Uncalibrated Photometric Stereo via Diffuse Maxima， Thoma Papadhimitri,Paolo Favaro； ORAL

A Non-Local Cost Aggregation Method for Stereo Matching，Qingxiong Yang；

Online Continuous Stereo Extrinsic Parameter Estimation，Peter Hansen, Peter Rander, Hatem Alismail, Brett Browning； 立体相机外参自标定

其他

Jigsaw Puzzles with Pieces of Unknown Orientation (PDF)， Andrew Gallagher； ORAL

Are we ready for Autonomous Driving? (PDF, dataset)， Andreas Geiger, Philip Lenz, Raquel Urtasun； ORAL

The Shape Boltzmann Machine: a Strong Model of Object Shape (PDF, project, videos, code)，S. M. Ali Eslami, Nicolas Heess, John Winn；ORAL 这篇文章的信息很全啊。

Pedestrian detection at 100 frames per second，(PDF) Rodrigo Benenson, Markus Mathias, Radu Timofte, Luc Van Gool； ORAL Van Gool教授，您是要逆天啊，100帧

Connected Contours: a Contour Completion Model that respects Closure-Effect，Yansheng Ming,Hongdong Li, Xuming He； ORAL 关于轮廓连接的，也算是contour grouping吧

Recognizing Scene Viewpoint using Panoramic Place Representation (PDF, Dataset, source code, more results, analysis and project webpage)， Jianxiong Xiao (MIT), Krista A. Ehinger (MIT), Aude Oliva (MIT), Antonio Torralba (MIT)； 视点分析

Three things everyone should know to improve object retrieval，(PDF) Relja Arandjelovic, Andrew Zisserman； 这个题目也起的很霸气

Towards Compact Topical Descriptors， Ling-Yu Duan, Rongrong Ji, Jie Chen, Wen Gao；关于主题描述的

Structure From Motion with Points, Objects, and Regions，(PDF) Yingze Bao, Johnny Chao, Mohit Bagra, Silvio Savarese；

Spatial Bias in Multi-Atlas Based Segmentation， Hongzhi Wang, Paul Yushkevich；

The Scale of Edges， Changhu Wang；

Occlusion Reasoning for Object Detection under Arbitrary Viewpoint， Edward Hsiao, Martial Hebert；

D-Nets: Beyond Patch-Based Image Descriptors (PDF)， Felix von Hundelshausen, Rahul Sukthankar； 又一个新的描述子

Mode-Seeking on Graphs via Random Walks，(PDF) (Project) Minsu Cho, Kyoung Mu Lee；

Optical Flow in the Presence of Spatially-Varying Motion Blur，(PDF) Travis Portz, Li Zhang,Hongrui Jiang；

RGB-(D) Scene Labeling: Features and Algorithms，(PDF) Xiaofeng Ren, Liefeng Bo, Dieter Fox； 使用深度相机进行场景标注，任晓峰的