- Far-Sighted Active Learning on a Budget for Image and Video Recognition
- Boundary Preserving Dense Local Regions Jaechul Kim and Kristen Grauman
- Learning with Whom to Share in Multi-task Feature Learning Zhuoliang Kang zkang@usc.edu
- Efficient Region Search for Object Detection Sudheendra Vijayanarasimhan
- Watch, Listen & Learn: Co-training on Captioned Images and Videos
- Pyramid Match Hashing: Sub-Linear Time Indexing Over Partial Correspondences
- Collect-Cut: Segmentation with Top-Down Cues Discovered in Multi-Object Images
- Multi-Level Active Prediction of Useful Image Annotations for Recognition
- Approximate Correspondences in High Dimensions Kristen Grauman
- Large-Scale Live Active Learning: Training Object Detectors with Crawled Data and Crowds
- Asymmetric Region-to-Image Matching for Comparing Images with Generic Object Categories
- Interactive Discovery of Task-Specific Nameable Attributes Devi Parikh
- Interactively Building a Discriminative Vocabulary of Nameable Attributes Devi Parikh
- Keywords to Visual Categories: Multiple-Instance Learning for Weakly Supervised Object Categorization
- Fast Image Search for Learned Metrics Prateek Jain Brian Kulis Kristen Grauman
- Avoiding the "Streetlight Effect": Tracking by Exploring Likelihood Modes David Demirdjian, Leonid Taycher, Gregory Shakhnarovich, Kristen Grauman, and Trevor Darrell
- Efficient Image Matching with Distributions of Local Invariant Features Kristen Grauman and Trevor Darrell
- Supplementary file for: Object-Graphs for Context-Aware Category Discovery
- Approximate Correspondences in High Dimensions Kristen Grauman
- Kernelized Locality-Sensitive Hashing for Scalable Image Search Brian Kulis
- Efficiently Searching for Similar Images Kristen Grauman
- Online Metric Learning and Fast Similarity Search Prateek Jain, Brian Kulis, Inderjit S. Dhillon, and Kristen Grauman
- ISBN 0-7695-1272-0/01 $10.00 (C) 2001 IEEE In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Lihue, HI, December 2001.
- Learning with Whom to Share in Multi-task Feature Learning: Supplementary Material
- Learning the Easy Things First: Self-Paced Visual Category Discovery Yong Jae Lee and Kristen Grauman
- Foreground Focus: Finding Meaningful Features in Unlabeled Images
- Object-Graphs for Context-Aware Category Discovery Yong Jae Lee and Kristen Grauman
- A Statistical ImageBased Shape Model for Visual Hull Reconstruction and 3D Structure Inference
- Large-Scale Live Active Learning: Training Object Detectors with Crawled Data and Crowds
- Clues from the Beaten Path: Location Estimation with Bursty Sequences of Tourist Photos
- Hashing Hyperplane Queries to Near Points with Applications to Large-Scale Active Learning
- Hashing Hyperplane Queries to Near Points with Applications to Large-Scale Active Learning
- Learning a Hierarchy of Discriminative Space-Time Neighborhood Features for Human Action Recognition
- Top-Down Pairwise Potentials for Piecing Together Multi-Class Segmentation Puzzles
- Online Metric Learning and Fast Similarity Search Prateek Jain, Brian Kulis, Inderjit S. Dhillon, and Kristen Grauman
- Observe Locally, Infer Globally: a Space-Time MRF for Detecting Abnormal Activities with Incremental Updates
- Keywords to Visual Categories: Multiple-Instance Learning for Weakly Supervised Object Categorization
- Inferring 3D Structure with a Statistical Image-Based Shape Model Kristen Grauman, Gregory Shakhnarovich, Trevor Darrell
- In Proceedings of the CVPR-09 Workshop on Visual and Contextual Learning from Annotated Images and Videos (VCL),. Miami, Florida, June 2009.
- Yong Jae Lee Foreground Focus: Finding Meaningful Features in
- Active Learning with Gaussian Processes for Object Categorization Ashish Kapoor
- The Pyramid Match: Efficient Learning with Partial Correspondences Kristen Grauman
- The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features
- A Picture is Worth a Thousand Keywords: Image-Based Object Search on a Mobile Platform
- A Bayesian Approach to Image-Based Visual Hull Reconstruction Kristen Grauman, Gregory Shakhnarovich, Trevor Darrell
- A Statistical Image-Based Shape Model for Visual Hull Reconstruction and 3D Structure Inference
- What's It Going to Cost You?: Predicting Effort vs. Informativeness for Multi-Label Image Annotations
- Fast Contour Matching Using Approximate Earth Mover's Distance Kristen Grauman and Trevor Darrell
- Matching Sets of Features for Efficient Retrieval and Recognition
- Unsupervised Learning of Categories from Sets of Partially Matching Image Features
- Shape Discovery from Unlabeled Image Collections Yong Jae Lee and Kristen Grauman
- Key-Segments for Video Object Segmentation Yong Jae Lee, Jaechul Kim, and Kristen Grauman
- Actively Selecting Annotations Among Objects and Attributes Adriana Kovashka Sudheendra Vijayanarasimhan Kristen Grauman
- Annotator Rationales for Visual Recognition Jeff Donahue and Kristen Grauman
- LEE, GRAUMAN: FACE DISCOVERY WITH SOCIAL CONTEXT 1 Face Discovery with Social Context
- L i Hi h f Di i i ti S Ti N i hb h d F t f H A ti R itiLearning a Hierarchy of Discriminative Space Time Neighborhood Features for Human Action RecognitionLearning a Hierarchy of Discriminative Space-Time Neighborhood Features for Human Action Recognition
- Shape Discovery from Unlabeled Image Collections Yong Jae Lee and Kristen Grauman
- Learning Binary Hash Codes for Large-Scale Image Search
- Relative Attributes Devi Parikh
- C llC ll C S i i h TC S i i h T D C Di d i M l iD C Di d i M l i Obj IObj ICollectCollect Cut: Segmentation with TopCut: Segmentation with Top Down Cues Discovered in MultiDown Cues Discovered in Multi Object ImagesObject ImagesCollectCollect--Cut: Segmen
- Annotator Rationales for Visual Recognition Jeff Donahue and Kristen Grauman
- Learning a Tree of Metrics with Disjoint Visual Features
