UT-Austin Computer Vision Group Publications

[view with images/code/slides] [view by topic] [view by year] [student theses]




steady

Slow and Steady Feature Analysis: Higher Order Temporal Coherence in Video.  D. Jayaraman and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, June 2016.  (Spotlight)  [pdf]









summary transfer

Summary Transfer: Exemplar-based Subset Selection for Video Summarization.  K. Zhang, W-L. Chao, F. Sha, and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, June 2016.  [pdf] [supp]









active image segmentation

Active Image Segmentation Propagation.  S. Jain and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, June 2016.  [pdf]









pull the plug

Pull the Plug?  Predicting If Computers or Humans Should Segment Images.  D. Gurari, S. Jain, M. Betke, and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, June 2016.  [pdf]  [supp]









interactee heatmap

Subjects and Their Objects: Localizing Interactees for a Person-Centric View of Importance.  C-Y. Chen and K. Grauman.  arXiv: :1604.04842v1, April 2016.  [pdf]









360 look ahead

Look Ahead Before You Leap: End-to-End Active Recognition by Forecasting the Effect of Motion.  D. Jayaraman and K. Grauman.  UT Tech Report A115-06, Dec 2015.  [arXiv]









fine grained attributes

Fine-Grained Comparisons with Attributes.  A. Yu and K. Grauman.  Chapter in Visual Attributes.  R. Feris, C. Lampert, and D. Parikh, Editors.  Springer.  To appear, 2016.









divide and conquer

Divide, Share, and Conquer: Multi-task Attribute Learning with Selective Sharing.  C-Y. Chen, Dinesh Jayaraman, F. Sha, and K. Grauman.  Chapter in Visual Attributes.  R. Feris, C. Lampert, and D. Parikh, Editors.  Springer.  To appear, 2016.









interactive image search

Attributes for Image Retrieval.  A. Kovashka and K. Grauman. Chapter in Visual Attributes.  R. Feris, C. Lampert, and D. Parikh, Editors.  Springer.  To appear, 2016.









max sub

Efficient Activity Detection in Untrimmed Video with Max-Subgraph Search.  C-Y. Chen and K. Grauman.  IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), April 2016.









text detection

Text Detection in Stores Using a Repetition Prior.  B. Xiong and K. Grauman.  In Proceedings of the IEEE Winter Conference on Computer Vision (WACV).  Lake Placid, NY, March 2016.  [pdf]









ego rep

Learning Image Representations Tied to Ego-Motion.  D. Jayaraman and K. Grauman.  In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, Dec 2015.  (Oral)  [pdf]  [supp]  [code,data]  [slides]









jnd

Just Noticeable Differences in Visual Attributes.  A. Yu and K. Grauman.  In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, Dec 2015.  [pdf]  [supp] [poster] [project page]









whittle search

WhittleSearch: Interactive Image Search with Relative Attribute Feedback.  A. Kovashka, D. Parikh, and K. Grauman.  International Journal on Computer Vision (IJCV), Volume 115, Issue 2, pp 185-210, November 2015.  [link]  [arxiv] [demo]









shades examples

Discovering Attribute Shades of Meaning with the Crowd.  A. Kovashka and K. Grauman.  International Journal on Computer Vision (IJCV), Volume 114, Issue 1, pp. 56-73, August 2015.  [link[arxiv]  [data]









bplr

Boundary Preserving Dense Local Regions.  J. Kim and K. Grauman.  IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Volume 37, No 5, pp. 931-943, April 2015. [link]  [code]









storyboard

Predicting Important Objects for Egocentric Video Summarization.  Y J. Lee and K. Grauman.  International Journal on Computer Vision, Volume 114, Issue 1, pp. 38-55, August 2015.  [link]  [arxiv]









lazy local

Predicting Useful Neighborhoods for Lazy Local Learning.  A. Yu and K. Grauman.  In Advances in Neural Information Processing Systems (NIPS), Montreal, Canada, Dec 2014.  [pdf]  [supp]  [poster]









video summary

Large-Margin Determinantal Point Processes.  W-L. Chao, B. Gong, K. Grauman, and F. Sha. In Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI), Amsterdam, Netherlands, July 2015.  [pdf]  [supp]









zero shot

Zero-shot Recognition with Unreliable Attributes.  D. Jayaraman and K. Grauman.  In Advances in Neural Information Processing Systems (NIPS), Montreal, Canada, Dec 2014.  [pdf]  [supp]  [poster]  [code]









seq dpp

Diverse Sequential Subset Selection for Supervised Video Summarization.  B. Gong, W. Chao, K. Grauman, and F. Sha.  In Advances in Neural Information Processing Systems (NIPS), Montreal, Canada, Dec 2014.  [pdf]  [supp]  [poster]









interactees

Predicting the Location of "Interactees" in Novel Human-Object Interactions.  C-Y. Chen and K. Grauman.  In Proceedings of the Asian Conference on Computer Vision (ACCV), Singapore, Nov 2014.  [pdf]









coseg

Which Image Pairs Will Cosegment Well?  Predicting Partners for Cosegmentation.  S. Jain and K. Grauman.  In Proceedings of the Asian Conference on Computer Vision (ACCV), Singapore, Nov 2014.  [pdf]









snap points

Detecting Snap Points in Egocentric Video with a Web Photo Prior.  B. Xiong and K. Grauman.  In Proceedings of the European Conference on Computer Vision (ECCV), Zurich, Switzerland, Sept 2014.  [pdf]  [project page]  [data]  [code]

Intentional Photos from an Unintentional Photographer: Detecting Snap Points in Egocentric Video with a Web Photo Prior.  B. Xiong and K. Grauman.  Invited chapter.  In Mobile Cloud Visual Media Computing.  Springer International Publishing.  Editors: G. Hua and X.-S. Hua.  pp 85-111.  November 2015.  [pdf]









supervoxel seg

Supervoxel-Consistent Foreground Propagation in Video.  S. Jain and K. Grauman.  In Proceedings of the European Conference on Computer Vision (ECCV), Zurich, Switzerland, Sept 2014.  [pdf]  [project page]  [data]









shades

Discovering Shades of Attribute Meaning with the Crowd.  A. Kovashka and K. Grauman.  Third International Workshop on Parts and Attributes, in conjunction with the European Conference on Computer Vision.  Zurich, Switzerland, Sept 2014.  [pdf]









decorrelating attributes

Decorrelating Semantic Visual Attributes by Resisting the Urge to Share.  D. Jayaraman, F. Sha, and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, Ohio, June 2014.  (Oral)  [pdf]  [supp]  [project page]  [slides]  [poster]  [code]









fine grained visual comparisons

Fine-Grained Visual Comparisons with Local Learning.  A. Yu and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, Ohio, June 2014.  [pdf]  [supp]  [poster]  [data]  [project page]









setwise active

Beyond Comparing Image Pairs: Setwise Active Learning for Relative Attributes.  L. Liang and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, Ohio, June 2014.  [pdf]  [supp]  [project page]  [code for data collection] [code for algorithm] [poster]
 
Beyond Comparing Image Pairs: Setwise Active Learning for Relative Attributes.  L. Liang and K. Grauman. 
Workshop on Computer Vision and Human Computation (CVHC), CVPR 2014.  [abstract]









inferring unseen poses

Inferring Unseen Views of People.  C.-Y. Chen and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, Ohio, June 2014.  [pdf]  [supp]  [project page]  [poster]









analogous attributes

Inferring Analogous Attributes.  C.-Y. Chen and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, Ohio, June 2014.  [pdf]  [supp]  [project page]  [poster]

Inferring Analogous Attributes: Large-Scale Transfer of Category-Specific Attribute Classifiers. 
C.-Y. Chen and K. Grauman.  International Workshop on Large Scale Visual Recognition and Retrieval (BigVision) at CVPR 2014. [abstract]









domain adaptation

Learning Kernels for Unsupervised Domain Adaptation with Applications to Visual Object Recognition.  B. Gong, K. Grauman, and F. Sha.  International Journal of Computer Vision (IJCV), Volume 109, Issue 1-2, pp. 3-27, August 2014.  [link]









pivots

Attribute Pivots for Guiding Relevance Feedback in Image Search.  A. Kovashka and K. Grauman.  In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Sydney, Australia, December 2013.  [pdf]  [poster]  [project page] [patented]

Interactive Image Search with Attribute-based Guidance and Personalization.  A. Kovashka and K. Grauman. 
Workshop on Computer Vision and Human Computation (CVHC), CVPR 2014.  [abstract]









predict annotation strength

Predicting Sufficient Annotation Strength for Interactive Foreground Segmentation.  S. Jain and K. Grauman.  In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Sydney, Australia, December 2013.  [pdf]  [poster]  [project page]  [data]

Predicting Sufficient Annotation Strength for Interactive Foreground Segmentation.  S. Jain and K. Grauman.  Workshop on Computer Vision and Human Computation (CVHC), CVPR 2014.  [abstract]









adapt attributes

Attribute Adaptation for Personalized Image Search.  A. Kovashka and K. Grauman.  In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Sydney, Australia, December 2013.  [pdf]  [poster]  [project page









active learning of actions

Active Learning of an Action Detector from Untrimmed Videos.  S. Bandla and K. Grauman.  In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Sydney, Australia, December 2013.  [pdf]  [project page]  [annotation code] [poster] [annotations]









implicit cues

Implied Feedback: Learning Nuances of User Behavior in Image Search.  D. Parikh and K. Grauman.  In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Sydney, Australia, December 2013.  [pdf]  [supp]









latent domains

Reshaping Visual Datasets for Domain Adaptation.  B. Gong, K. Grauman, and F. Sha.  In Proceedings of Advances in Neural Information Processing Systems (NIPS), Tahoe, Nevada, December 2013.  [pdf]









pose

Watching Unlabeled Video Helps Learn New Human Actions from Very Few Labeled Snapshots.  C-Y. Chen and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, OR, June 2013.  (Oral)  [pdf]  [project page]









story

Story-Driven Summarization for Egocentric Video.  Z. Lu and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, OR, June 2013.  [pdf]  [project page] [data] [poster]









dsp

Deformable Spatial Pyramid Matching for Fast Dense Correspondences.  J. Kim, C. Liu, F. Sha, and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, OR, June 2013.[pdf]  [project page] [code]









object centric

Object-Centric Spatio-Temporal Pyramids for Egocentric Activity Recognition.  T. McCandless and K. Grauman.  In Proceedings of the British Machine Vision Conference (BMVC), Bristol, UK, Sept 2013.  [pdf]  [abstract] [poster]









analogy

Analogy-Preserving Semantic Embedding for Visual Object Categorization.  S. J. Hwang, K. Grauman, and F. Sha.  In International Conference on Machine Learning (ICML), Atlanta, GA, June 2013.  [pdf]









landmarks

Connecting the Dots with Landmarks:  Discriminatively Learning Domain-Invariant Features for Unsupervised Domain AdaptationB. Gong, K. Grauman, and F. ShaIn International Conference on Machine Learning (ICML), Atlanta, GA, June 2013.  (Oral) [pdf]  [supp]









shape sharing

Shape Sharing for Object Segmentation.  J. Kim and K. Grauman.  To appear, Proceedings of the European Conference on Computer Vision (ECCV), Florence, Italy, October 2012.  (Oral)  [pdf [supp]  [project page] [code] [slides]









label propagation

Active Frame Selection for Label Propagation in Videos.  S. Vijayanarasimhan and K. Grauman.  To appear, Proceedings of the European Conference on Computer Vision (ECCV), Florence, Italy, October 2012.  [pdf] [poster]  [project page]  [code]  [data]









forest

Semantic Kernel Forests from Multiple Taxonomies.  S. J. Hwang, K. Grauman, and F. Sha.  In Advances in Neural Information Processing Systems (NIPS), Tahoe, Nevada, December 2012.  [pdf]  [poster]  [project page[code]

Semantic Kernel Forests from Multiple Taxonomies.  S. J. Hwang, F. Sha, and K. Grauman.  In Big Data Meets Computer Vision: First International Workshop on Large Scale Visual Recognition and Retrieval.  In conjunction with NIPS, 2012. (Oral)  [pdf [code]









video summary

Discovering Important People and Objects for Egocentric Video Summarization.  Y. J. Lee, J. Ghosh, and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, June 2012.  [pdf]  [poster]  [data]  [project page] 









activity detection

Efficient Activity Detection with Max-Subgraph Search.  C.-Y. Chen and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, June 2012.  [pdf]  [poster] [project page]  [code]









whittle search

WhittleSearch: Image Search with Relative Attribute Feedback. A. Kovashka, D. Parikh, and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, June 2012.  [pdf]  [supp]  [poster[project page] [demo] [patented]









localized attributes

Discovering Localized Attributes for Fine-grained Recognition.  K. Duan, D. Parikh, D. Crandall, and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, June 2012.  [pdf [poster]  [project page] 









domain
                adaptation

Geodesic Flow Kernel for Unsupervised Domain Adaptation.  B. Gong, Y. Shi, F. Sha, and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, June 2012.  (Oral)  [pdf]  [supp]  [slides]  [project page]

Overcoming Dataset Bias: An Unsupervised Domain Adaptation Approach.  B. Gong, F. Sha, and K. Grauman.  In Big Data Meets Computer Vision: First International Workshop on Large Scale Visual Recognition and Retrieval.  In conjunction with NIPS, 2012.  (Oral)  [pdf]  [project page]









rbm hash

Learning Binary Hash Codes for Large-Scale Image Search.  K. Grauman and R. Fergus.  Book chapter, in Machine Learning for Computer Vision, Ed., R. Cipolla, S. Battiato, and G. Farinella, Studies in Computational Intelligence Series, Springer, Volume 411, pp. 49-87, 2013 [pdf]  [link]









face recons

Reconstructing a Fragmented Face from a Cryptographic Identification Protocol.  A. Luong, M. Gerbush, B. Waters, and K. Grauman.  In Proceedings of the IEEE Workshop on Applications of Computer Vision (WACV), Clearwater Beach, FL, January 2013.  [pdf]  [poster]









relative attributes

Relative Attributes.  D. Parikh and K. Grauman.  In Proceedings of the International Conference on Computer Vision (ICCV), Barcelona, Spain, November 2011.  (Oral)  [pdf] [project page] [data [slides [Marr Prize, ICCV Best Paper Award]

Relative Attributes for Enhanced Human-Machine Communication.  D. Parikh, A. Kovashka, A. Parkash, and K. Grauman.  Invited paper, Proceedings of AAAI 2012, Sub-Area Spotlights Track for Best Papers.  [pdf]









keysegments

Key-Segments for Video Object Segmentation.  Y. J. Lee, J. Kim, and K. Grauman.  In Proceedings of the International Conference on Computer Vision (ICCV), Barcelona, Spain, November 2011.  [pdf]  [poster] [project page] [video results] [code]









image rationale

Annotator Rationales for Visual Recognition.  J. Donahue and K. Grauman.  In Proceedings of the International Conference on Computer Vision (ICCV), Barcelona, Spain, November 2011.  [pdf]  [project page] [data]  [video overview]









active attributes

Actively Selecting Annotations Among Objects and Attributes.  A. Kovashka, S. Vijayanarasimhan, and K. Grauman.  In Proceedings of the International Conference on Computer Vision (ICCV), Barcelona, Spain, November 2011.  [pdf]  [project page]









tree of metrics




Learning a Tree of Metrics with Disjoint Visual Features.  S. J. Hwang, K. Grauman,
F. Sha.  To appear, Advances in Neural Information Processing Systems (NIPS).  Granada, Spain, December 2011.  [pdf]  [poster] [project page]  [code]









recognition

Visual Object Recognition, Kristen Grauman and Bastian Leibe, Synthesis Lectures on Artificial Intelligence and Machine Learning, April 2011, Vol. 5, No. 2, Pages 1-181.  [link]









face discovery

Face Discovery with Social Context.  Y. J. Lee and K. Grauman.  In Proceedings of the British Machine Vision Conference (BMVC), Dundee, U.K., August 2011. [pdf] [abstract] [project page]









live learning

Large-Scale Live Active Learning: Training Object Detectors with Crawled Data and Crowds.  S. Vijayanarasimhan and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, CO, June 2011.  (Oral)  [pdf] [project page] [slides]

We show some additional analysis of the annotation collection, to be presented at the Human Computation Workshop (HCOMP), at AAAI 2011.  [pdf]

Large-Scale Live Active Learning: Training Object Detectors with Crawled Data and Crowds.  S. Vijayanarasimhan and K. Grauman.  International Journal of Computer Vision (IJCV), Volume 108, Issue 1-2, pp. 97-114, May 2014.  [link]









BPLR

Boundary-Preserving Dense Local Regions.  J. Kim and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, CO, June 2011.  (Oral)  [pdf]  [project page]  [code] [slides]









attribute discovery


Interactively Building a Discriminative Vocabulary of Nameable Attributes.  D. Parikh and K. Grauman.
  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, CO, June 2011.  [pdf]  [project page] [poster]

We show some additional results in our short abstract to be presented at the Fine-Grained Visual Categorization Workshop (FGVC) at CVPR 2011.  [Best Poster Award] [pdf]










easiest

Learning the Easy Things First: Self-Paced Visual Category Discovery.  Y. J. Lee and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, CO, June 2011. [pdf] [project page]  [poster]









sharing features

Sharing Features Between Objects and Their Attributes.  S. J. Hwang, F. Sha, and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, CO, June 2011.  [pdf]  [project page] [poster]

We show some additional results in our short abstract to appear in Fine-Grained Visual Categorization Workshop (FGVC) at CVPR 2011.  [pdf] [poster]









mtlgroup

Learning with Whom to Share in Multi-task Feature Learning.  Z. Kang, K. Grauman, and F. Sha.  In Proceedings of the International Conference on Machine Learning (ICML), Bellevue, WA, July 2011.  [pdf] [supp]  [code]









max subgraph segmentation

Efficient Region Search for Object Detection.  S. Vijayanarasimhan and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, CO, June 2011.  [pdf]  [project page]  [code]









location recognition

Clues from the Beaten Path: Location Estimation with Bursty Sequences of Tourist Photos.  C.-Y. Chen and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, CO, June 2011.  [pdf]  [project page]  [data]  [poster]

Clues from the Beaten Path: Location Estimation with Bursty Sequences of Tourist Photos.  C.-Y. Chen.  Master's thesis, December 2010.  [pdf]









hash hyperplane

Hashing Hyperplane Queries to Near Points with Applications to Large-Scale Active Learning.  P. Jain, S. Vijayanarasimhan, and K. Grauman.  In Advances in Neural Information Processing Systems (NIPS), Vancouver, Canada, December 2010.  [pdf] [supp] [project page]  [poster]

Hashing Hyperplane Queries to Near Points with Applications to Large-Scale Active Learning.  S. Vijayanarasimhan, P. Jain, and K. Grauman.  Transactions on Pattern Analysis and Machine Intelligence (PAMI), Volume 36, No. 2, pp. 276-288, February 2014. [link]










object graph

       

Object-Graphs for Context-Aware Category Discovery.  Y. J. Lee and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, June 2010. (Oral) [pdf] [project page] [slides] [code]

Object-Graphs for Context-Aware Category Discovery.  Y. J. Lee and K. Grauman.  In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Vol. 34, No. 2, pp. 346-358, February 2012. [link]











implicit tag cues


Reading Between The Lines: Object Localization Using Implicit Cues from Image Tags.  S. J. Hwang and K. Grauman. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, June 2010. (Oral) [pdf]  [project page] [slides] [data]

Reading Between The Lines: Object Localization Using Implicit Cues from Image Tags.  S. J. Hwang and K. Grauman.  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Vol. 34, No. 6, pp. 1145-1158, June 2012. [link]










imgret

Accounting for the Relative Importance of Objects in Image Retrieval.  S. J. Hwang and K. Grauman.  In Proceedings of the British Machine Vision Conference (BMVC), Aberystwyth, UK, September 2010. (Oral)  [pdf]  [slides] [project page] [data]

Learning the Relative Importance of Objects from Tagged Images for Retrieval and Cross-Modal Search.  S. J. Hwang and K. Grauman.  International Journal of Computer Vision (IJCV), Vol. 100, Issue 2, pp. 134-153, November 2012.  [link]










              

video clips


Far-Sighted Active Learning on a Budget for Image and Video Recognition.  S. Vijayanarasimhan, P. Jain, and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, June 2010.  [pdf]  [project page]  [code]










questions

Cost-Sensitive Active Visual Category Learning.  S. Vijayanarasimhan and K. Grauman.  International Journal of Computer Vision (IJCV), Vol. 91, Issue 1 (2011), p. 24, (online first July 2010).  [link]

Minimizing Annotation Costs in Visual Category Learning.  S. Vijayanarasimhan and K. Grauman.  Invited chapter, in Cost-Sensitive Machine Learning, B. Krishnapuram, S. Yu, and B. Rao, Editors.  Chapman and Hall/CRC, December 2011.  [link]










collect-cut


Collect-Cut: Segmentation with Top-Down Cues Discovered in Multi-Object Images.  Y. J. Lee and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, June 2010.  [pdf]  [project page]  [poster]











space-time features


Learning a Hierarchy of Discriminative Space-Time Neighborhood Features for Human Action Recognition.  A. Kovashka and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, June 2010.  [pdf]  [project page]  [poster]











region to image matching


Asymmetric Region-to-Image Matching for Comparing Images with Generic Object Categories.  J. Kim and K. Grauman.  In  Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, June 2010.  [pdf]  [project page]  [code]










Cow

Top-Down Pairwise Potentials for Piecing Together Multi-Class Segmentation Puzzles.  S. Vijayanarasimhan and K.Grauman.  In Proceedings of the Seventh IEEE Computer Society Workshop on Perceptual Organization in Computer Vision (POCV), June 2010.  [pdf] [slides]










klsh


Kernelized Locality-Sensitive Hashing for Scalable Image Search.  B. Kulis and K. Grauman.  In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Kyoto, Japan, October 2009.  [pdf] [poster] [code] [project page]

Kernelized Locality-Sensitive Hashing.  B. Kulis and K. Grauman.  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Vol. 34, No. 6, pp. 1092-1104, June 2012.  [link]











shape discovery


Shape Discovery from Unlabeled Image Collections.  Y. J. Lee and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, June 2009.  [pdf] [project page] [poster]











cost-sensitive active
                learning


Multi-Level Active Prediction of Useful Image Annotations for Recognition.  S. Vijayanarasimhan and K. Grauman.  In Advances in Neural Information Processing Systems (NIPS), Vancouver, Canada, Dec. 2008.   (Oral) [pdf]   [slides] [project page]



Cost-Sensitive Active Visual Category Learning.  S. Vijayanarasimhan and K. Grauman.  Abstract presented at the Learning Workshop, Clearwater FL, April 2009.  [abstract] [slides]











Cost


What’s It Going to Cost You? : Predicting Effort vs. Informativeness for Multi-Label Image Annotations.  S. Vijayanarasimhan and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, June 2009.  [pdf] [project page]











image search


Efficiently Searching for Similar Images.  K. Grauman.  Invited article to appear in the Communications of the ACM, 2009.  [pre-print] [CACM link]











online hash table


Online Metric Learning and Fast Similarity Search.  P. Jain, B. Kulis, I. Dhillon, and K. Grauman.  In Advances in Neural Information Processing Systems (NIPS), Vancouver, Canada, Dec. 2008. (Oral) [pdf] [extended version]











semisupervised hash
                functions


Fast Image Search for Learned Metrics.  P. Jain, B. Kulis, and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Anchorage, Alaska, June 2008.  (Oral) [Best Student Paper Award]     [pdf] [slides (ppt)]  [project page]




Fast Similarity Search for Learned Metrics.   B. Kulis, P. Jain, and K. Grauman.   In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Vol. 31, No. 12, December 2009. [link
[project page]











space-time mrf


Observe Locally, Infer Globally: a Space-Time MRF for Detecting Abnormal Activities with Incremental Updates.  J. Kim and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, June 2009.  [pdf]  [project page]  [loopy BP code]











iterative foreground refinement
                foreground focus
foreground focus


Foreground Focus: Unsupervised Learning from Partially Matching Images.  Y. J. Lee and K. Grauman.  In International Journal of Computer Vision (IJCV), Vol. 85, No. 2, 2009.  [link]  [project page]

Foreground Focus: Finding Meaningful Features in Unlabeled Images. Y. J. Lee and K. Grauman.  In Proceedings of the British Machine Vision Conference (BMVC), Leeds, U.K., September 2008. (Oral) [pdf] [slides (ppt)] [project page]












keywords mil


Keywords to Visual Categories: Multiple-Instance Learning for Weakly Supervised Object Categorization.  S. Vijayanarasimhan and K. Grauman.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Anchorage, Alaska, June 2008.     [pdf]      [poster (pdf)]     [poster (ppt)]      [Semantic Robot Vision Challenge slides (ppt)]  [project page]  [code]











co-training human activity


Watch, Listen & Learn: Co-training on Captioned Images and Videos.  S. Gupta, J. Kim, K. Grauman, and R. Mooney.  In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML), Antwerp, Belgium, September 2008.   [pdf]  [project page]











gaussian process active



Active Learning with Gaussian Processes for Object Categorization.  A. Kapoor, K. Grauman, R. Urtasun, and T. Darrell.  In Proceedings of the IEEE International Conference on Computer Vision, Rio de Janeiro, Brazil, October 2007.  [pdf]











caltech 101 result


Gaussian Processes for Object Categorization.  A. Kapoor, K. Grauman, R. Uratsun, and T. Darrell.  In International Journal of Computer Vision (IJCV), Vol. 88, No. 2, 2010. [link]











pyramid match kernel


The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features.  K. Grauman and T. Darrell.  In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Beijing, China, October 2005. (Oral) [pdf]  [ppt slides]  [code]  [project page]




The Pyramid Match: Efficient Learning with Partial Correspondences.  K. Grauman.   In Proceedings of the Association for the Advancement of Artificial Intelligence (AAAI),
(Nectar track, for AI results presented at other conferences in last two years) Vancouver, Canada, July 2007.   [pdf]




The Pyramid Match Kernel: Efficient Learning with Sets of Features.  K. Grauman and T. Darrell.  Journal of Machine Learning Research (JMLR), 8 (Apr): 725--760, 2007.  [pdf] 
[code] [project page]




Matching Sets of Features for Efficient Retrieval and Recognition,
K. Grauman, Ph.D. Thesis, MIT, 2006.  [pdf] (35.8 MB)











pyramid match hashing


Pyramid Match Hashing: Sub-Linear Time Indexing Over Partial Correspondences.  K. Grauman and T. Darrell.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Minneapolis, MN, June 2007.  [pdf]











approximate correspondences


Approximate Correspondences in High Dimensions.  K. Grauman and T. Darrell.   In Advances in Neural Information Processing Systems 19 (NIPS) 2007.  [pdf]   [code]    [poster (pdf)]   [poster (ppt)]











graph clustering images


Unsupervised Learning of Categories from Sets of Partially Matching Image Features.  K. Grauman and T. Darrell.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New York City, NY, June 2006.  (Oral) [pdf]  [ppt slides]











image matching


Efficient Image Matching with Distributions of Local Invariant Features.  K. Grauman and T. Darrell.  In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, June 2005.   [pdf]



Fast Contour Matching Using Approximate Earth Mover's Distance.  K. Grauman and T. Darrell.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Washington DC, June 2004. [pdf] [project page]  [code]











web image match


A Picture is Worth a Thousand Keywords: Image-Based Object Search on a Mobile Platform.  T. Yeh, K. Grauman, K. Tollmar, and T. Darrell.  In CHI 2005, Conference on Human Factors in Computing Systems, Portland, OR, April 2005.  [pdf]











inferring pose


Inferring 3D Structure with a Statistical Image-Based Shape Model.  K. Grauman, G. Shakhnarovich, and T. Darrell.  In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Nice, France, October 2003.  [pdf]  [project page]











pose estimation


Avoiding the ``Streetlight Effect'': Tracking by Exploring Likelihood Modes.  D. Demirdjian, L. Taycher, G. Shakhnarovich, K. Grauman, and T. Darrell.  In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Beijing, China, October 2005.   [pdf]











visual hull


A Bayesian Approach to Image-Based Visual Hull Reconstruction.  K. Grauman, G. Shakhnarovich, and T. Darrell.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Madison, WI, June 2003.  [pdf]  [project page]











virtual visual hull


Virtual Visual Hulls: Example-Based 3D Shape Inference from a Single Silhouette.  K. Grauman, G. Shakhnarovich, and T. Darrell.  In Proceedings of the 2nd Workshop on Statistical Methods in Video Processing, in conjunction with ECCV, Prague, Czech Republic, May 2004. [pdf]  [project page]











blink detection


Communication via Eye Blinks and Eyebrow Raises: Video-Based Human-Computer Interfaces. K. Grauman, M. Betke, J. Lombardi, J. Gips, and G. Bradski.  Universal Access in the Information Society, 2(4) pp. 359-373,  Springer-Verlag Heidelberg, November 2003. [link] [project page]











eye blink 2


Communication via Eye Blinks: Detection and Duration Analysis in Real Time.  K. Grauman, M. Betke, J. Gips, and G. Bradski.  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Lihue, HI, December 2001. [pdf]  [project page]