NDLI: Label-to-region with continuity-biased bi-layer sparsity priors

Please wait, while we are loading the content...

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP) : Volume 10

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP) : Volume 9

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP) : Volume 8

Issue 4, November 2012

Table of contents: Online supplement volume 8, number 2s, online supplement volume 8, number 3s

Editorial

Label-to-region with continuity-biased bi-layer sparsity priors

Efficient targeted search using a focus and context video browser

User perception of media content association in olfaction-enhanced multimedia

NextSlidePlease: Authoring and delivering agile multimedia presentations

Object-based image retrieval with kernel on adjacency matrix and local combined features

In-video product annotation with web information mining

Algorithms for stochastic optimization of multicast content delivery with network coding

Issue 3s(Special section of best papers of ACM multimedia 2011, and special section on 3D mobile multimedia), September 2012

Issue 2S(Special Issue on Multimedia Security), September 2012

Issue 3, July 2012

Issue 2, May 2012

Issue 1S(Special Issue on P2P Streaming), February 2012

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP) : Volume 7

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP) : Volume 7S

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP) : Volume 6

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP) : Volume 5

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP) : Volume 4

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP) : Volume 3

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP) : Volume 2

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP) : Volume 1

Label-to-region with continuity-biased bi-layer sparsity priors

Content Provider	ACM Digital Library
Author	Liu, Xiaobai Yan, Shuicheng Tang, Jinhui Cheng, Bin Chua, Tat-Sheng Jin, Hai
Copyright Year	2012
Abstract	In this work, we investigate how to reassign the fully annotated labels at image level to those contextually derived semantic regions, namely Label-to-Region (L2R), in a collective manner. Given a set of input images with label annotations, the basic idea of our approach to L2R is to first discover the patch correspondence across images, and then propagate the common labels shared in image pairs to these correlated patches. Specially, our approach consists of following aspects. First, each of the input images is encoded as a Bag-of-Hierarchical-Patch (BOP) for capturing the rich cues at variant scales, and the individual patches are expressed by patch-level feature descriptors. Second, we present a sparse representation formulation for discovering how well an image or a semantic region can be robustly reconstructed by all the other image patches from the input image set. The underlying philosophy of our formulation is that an image region can be sparsely reconstructed with the image patches belonging to the other images with common labels, while the robustness in label propagation across images requires that these selected patches come from very few images. This preference of being sparse at both patch and image level is named bi-layer sparsity prior. Meanwhile, we enforce the preference of choosing larger-size patches in reconstruction, referred to as continuity-biased prior in this work, which may further enhance the reliability of L2R assignment. Finally, we harness the reconstruction coefficients to propagate the image labels to the matched patches, and fuse the propagation results over all patches to finalize the L2R task. As a by-product, the proposed continuity-biased bi-layer sparse representation formulation can be naturally applied to perform image annotation on new testing images. Extensive experiments on three public image datasets clearly demonstrate the effectiveness of our proposed framework in both L2R assignment and image annotation.
Starting Page	1
Ending Page	23
Page Count	23
File Format	PDF
ISSN	15516857
e-ISSN	15516865
DOI	10.1145/2379790.2379792
Volume Number	8
Issue Number	4
Journal	ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2012-11-30
Publisher Place	New York
Access Restriction	One Nation One Subscription (ONOS)
Subject Keyword	Label-to-Region Bag-of-hierarchical-patch Image annotation Sparse representation
Content Type	Text
Resource Type	Article
Subject	Hardware and Architecture Computer Networks and Communications

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Label to region by bi-layer sparsity priors

H (2009) Label to region by bi-layer sparsity priors

Image label completion by pursuing contextual decomposability

Large-scale multilabel propagation based on efficient sparse graph construction

Mining flickr landmarks by modeling reconstruction sparsity

Image Inpainting by Patch Propagation Using Patch Sparsity

A discriminative graph inferring framework towards weakly supervised image parsing

Multi-scale patch-based sparse appearance model for robust object tracking

Adding semantics to image-region annotations with the Name-It-Game

Label-to-region with continuity-biased bi-layer sparsity priors

Similar Documents

Label to region by bi-layer sparsity priors

H (2009) Label to region by bi-layer sparsity priors

Image label completion by pursuing contextual decomposability

Large-scale multilabel propagation based on efficient sparse graph construction

Mining flickr landmarks by modeling reconstruction sparsity

Image Inpainting by Patch Propagation Using Patch Sparsity

A discriminative graph inferring framework towards weakly supervised image parsing

Multi-scale patch-based sparse appearance model for robust object tracking

Adding semantics to image-region annotations with the Name-It-Game

Label-to-region with continuity-biased bi-layer sparsity priors