more papers to check out from cvpr

Here are more CVPR 2010 papers which I either found interesting or plan on reading when I get back to PIT.  Enjoy!

Connecting Modalities: Semi-supervised Segmentation and Annotation of Images Using Unaligned Text Corpora  
Authors:  Richard Socher (Stanford University) , Li Fei-Fei (Stanford University) 

Cascade Object Detection with Deformable Part Models  
Authors:  Pedro Felzenszwalb (University of Chicago) , Ross Girshick (University ) , David McAllester (Toyota Technological Institute, Chicago) 

Beyond Active Noun Tagging: Modeling Contextual Interactions for Multi-Class Active Learning  
Authors:  Behjat Siddiquie (UMIACS) , Abhinav Gupta (Carnegie Mellon University)  

Tiered Scene Labeling with Dynamic Programming  
Authors:  Pedro Felzenszwalb (University of Chicago) , Olga Veksler (University of Western Ontario) 

Layered Object Detection for Multi-Class Segmentation  
Authors:  Yi Yang (UCI) , Sam Hallman () , Deva Ramanan () , Charless Fowlkes (UC Irvine) 

Efficiently Selecting Regions for Scene Understanding  
Authors:  M. Pawan Kumar (Stanford University) , Daphne Koller (Stanford)   

Image Webs: Computing and Exploiting Connectivity in Image Collections
Authors:  Kyle Heath (Stanford) , Natasha Gelfand (Nokia Research - Palo Alto, CA) , Maks Ovsjanikov (Stanford University) , Mridul Aanjaneya (Stanford University) , Leonidas Guibas (Stanford University)

constrained parametric min-cuts: exciting segmentation for the sake of recognition

I would like to introduce two papers about Constrained Parametric Min-Cuts from C. Sminchisescu's group.  These papers are very relevant to my research direction (which lies at the intersection of segmentation and recognition).  Like my own work, these papers are about segmentation for recognition's sake.  The segmentation algorithm proposed in the paper is a sort of "segment sliding approach", where many binary graph-cuts optimization problems are solved for different Grab-Cut style initializations.  These segments are then scored using a learned scoring function -- think regression versus classification.  They show that these top segments are actually quite meaningful and correspond to object boundaries really well.  Finally a tractable number of top hypothesis (still overlapping at this stage), are piped into a recognition engine.

The idea that features derived from segments are better for recognition than features from the spatial support of a sliding rectangle resonates in all of my papers.  Regarding these CVPR2010 papers, I like their ideas of learning a category-free "segmentation-function" and the sort of multiple-segmentation version of this algorithm is very appealing.  If I remember correctly, the idea of learning a segmentation function comes to us from X. Ren, and the idea of using multiple segmentation comes from D. Hoiem. These papers are a cool new idea utilizing both insights.

J. Carreira and C. Sminchisescu. Constrained Parametric Min-Cuts for Automatic Object Segmentation. In CVPR 2010.

F. Li, J. Carreira, and C. Sminchisescu. Object Recognition as Ranking Holistic Figure-Ground Hypotheses. In CVPR 2010.


-------

Spotlights for these papers are during these tracks at CVPR2010:
Object Recognition III: Similar Shapes
Segmentation and Grouping II: Semantic Segmentation tracks

Exciting Computer Vision papers from Kristen Grauman's UT-Austin Group

Back in 2005, I remember meeting Kristen Grauman at MIT's accepted PhD student open house.  Back then she was a PhD student under Trevor Darrell (and is known for her work on the Pyramid Match Kernel), but now she has her own vision group at UT-Austin.  She is the the advisor behind many cool vision projects there, and here are a few segmenatation/categorization related papers from the upcoming CVPR2010 conference.  I look forward to checking out these papers because they are relevant to my own research interests.  NOTE: some of the papers links are still not up -- I just used the links from Kristen's webpage.

Object-Graphs for Context-Aware Category Discovery. Y. J. Lee and K. Grauman

---

Collect-Cut: Segmentation with Top-Down Cues Discovered in Multi-Object Images. Y. J. Lee and K. Grauman

---

Asymmetric Region-to-Image Matching for Comparing Images with Generic Object Categories. J. Kim and K. Grauman