Learning the Latent "Look":
Unsupervised Discovery of a Style-Coherent Embedding from
Fashion Images. W.-L. Hsiao and K.
Grauman. In Proceedings of the
International Conference on Computer Vision (ICCV),Venice,
Italy,
Oct 2017 [pdf]
Encoder-decoder
model for image restoration tasks (inpainting, pixel
interpolation, deblurring, denoising) and on-demand training
approach to deal with mix of corruption difficulty levels
On-Demand Learning for Deep Image Restoration.
R. Gao and K. Grauman. In Proceedings of the
International Conference on Computer Vision (ICCV), Venice,
Italy, Oct 2017. [pdf]
Unsupervised
visual
representation learning from object proposals using
unlabeled video data. Caffe/Python implementation.
Object-Centric Representation Learning from
Unlabeled Videos. R. Gao, D. Jayaraman and K. Grauman. In
Proceedings of the Asian Conference on Computer Vision,
ACCV, Taipei, Taiwan, Nov. 2016.
"Embodied"
equivariant visual representation learning using motor
signals accompanying unlabeled video data. Caffe
implementation.
Learning
image representations tied to egomotion. D. Jayaraman and K. Grauman. In
Proceedings of the International Conference on Computer Vision
(ICCV), Santiago, Chile, Dec 2015. [pdf]
Learning
linear SVM rankers through fine-grained local learning.
Pre-trained Mahalanobis matrices included. Use in
conjunction with the UT Zappos50K dataset. Matlab
implementation.
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, OH, June 2014. [pdf]
Zero-shot
Recognition with Unreliable
Attributes.
D. Jayaraman and K. Grauman. In Advances
in Neural Information Processing Systems (NIPS),
Montreal, Canada, Dec 2014.
An algorithm to
detect snap points with a Web photo prior. MATLAB code.
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]
Fast, dense (pixel-level) image
correspondences. Shown to improve both accuracy and
speed of SIFT Flow and Patch Match algorithms.
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]
BPLR feature detector,
plus some descriptors for the extracted BPLRs, including HOG,
chordiogram, and color histogram. Written in MATLAB and
tested in Linux 32 and 64 bits.
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]
Kernelized hashing
algorithm which allows sub-linear time search under an
arbitrary kernel function. MATLAB code.
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]
An algorithm to
predict the annotation modality that is sufficiently strong
for accurate segmentation of a given image (Matlab and C++).
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]
An algorithm for active learning of
a ranking function that selects useful sets of examples to
be partially ordered by an annotator, plus MTurk interface
code for the cascading partial order annotation collection
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]
Code and test data for Tree of
Metrics (ToM), which learns a local metric at each node of a
semantic taxonomy with disjoint sparsity regularization.
Tree of Metrics for Disjoint Visual
Features, S. J. Hwang, K. Grauman, and F. Sha, In
Proceedings of the Neural Information Processing Systems
(NIPS), 2011, Granada, Spain. [pdf]
Code and test data for semantic kernel forest, which learns a
category-specific kernel from forest of metrics learned on
multiple semantic taxonomies.
Semantic Kernel Forests from Multiple Taxonomies, S. J.
Hwang, K. Grauman, and F. Sha, In Proceedings of the Neural
Information Processing Systems (NIPS), 2012, Lake Tahoe,
NV [pdf]
Generating
taxonomies
Codes to generate a taxonomy of target categories based on
WordNet or attributes, used in Tree of Metrics or Semantic
Kernel Forests
Tree of Metrics for Disjoint Visual
Features, S. J. Hwang, K. Grauman, and F. Sha, In
Proceedings of the Neural Information Processing Systems
(NIPS), 2011, Granada, Spain. [pdf]
Semantic Kernel Forests from
Multiple Taxonomies, S. J. Hwang, K. Grauman, and F. Sha, In
Proceedings of the Neural Information Processing Systems
(NIPS), 2012, Lake Tahoe, NV.
[pdf]
Generating object segment
hypotheses based on shape sharing approach. Written
in Matlab and C++ (Matlab wrapper provided).
Shape Sharing for Object
Segmentation. J. Kim and K. Grauman. In Proceedings of
the European Conference on Computer Vision (ECCV), Firenze,
Italy, Oct. 2012. (Oral) [pdf]
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]
Action
detection in continuous video. Fast branch-and-cut
approach to identify the subvolume in a video that maximizes the
linear classifier's score.Note that CPLEX student license is
available here.
Efficient Activity
Detection with Max-Subgraph Search. C.-Y. Chen and K.
Grauman. To appear,
Proceedings of the IEEE Conference on Computer Vision and
Pattern Recognition (CVPR), Providence, RI, June 2012.
[pdf]
Active
frame selection for video label propagation
A dynamic programming-based algorithm to actively choose
frames for human annotation along with label propagation with
minimum expected error. Written in Matlab and tested on 64 bit
Linux
Active Frame Selection for Label Propagation in
Videos. S. Vijayanarasimhan and K. Grauman. In Proceedings of the European Conference on Computer
Vision (ECCV), Florence, Italy, October 2012. [pdf]
Fast branch-and-cut approach to identify the subregion
in an image that maximizes the classifier's score, for family
of additive classifiers. Note that CPLEX student license
is available here.
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]
Unsupervised segmentation of main
foreground objects in video.
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]
Region-to-image matching method, written in Matlab and
C++ (Matlab wrapper provided).
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]
Batch-mode active learning
algorithm to select the set of examples that appear most
informative to an SVM, such that their total associated
annotation cost meets a given budget.
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]
The full pipeline for context-aware
discovery with object-graphs. Implemented in Matlab
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]
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]
Implementation
of
Value-of-Information
active learning criterion for multi-level multi-class case,
as
proposed in the CVPR 2009 paper
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]
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]
Used for the
Semantic Robot Vision Challenge in 2008
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]
Approximate
Correspondences in High Dimensions.K.
Grauman and T. Darrell.In Advances in Neural Information
Processing Systems 19 (NIPS) 2007.[pdf]
Relative importance embedding learned from tagged
images with KCCA.
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]
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.[pdf]