skip to main content
10.1145/1873951.1873958acmconferencesArticle/Chapter ViewAbstractPublication PagesmmConference Proceedingsconference-collections
research-article

Unified tag analysis with multi-edge graph

Published: 25 October 2010 Publication History

Abstract

Image tags have become a key intermediate vehicle to organize, index and search the massive online image repositories. Extensive research has been conducted on different yet related tag analysis tasks, e.g., tag refinement, tag-to-region assignment, and automatic tagging. In this paper, we propose a new concept of multi-edge graph, through which a unified solution is derived for the different tag analysis tasks. Specifically, each vertex of the graph is first characterized by a unique image. Then each image is encoded as a region bag with multiple image segmentations, and the thresholding of the pairwise similarities between regions naturally constructs the multiple edges between each vertex pair. The unified tag analysis is then generally described as the tag propagation between a vertex and its edges, as well as between all edges cross the entire image repository. We develop a core vertex-vs-edge tag equation unique for multi-edge graph to unify the image/vertex tag(s) and region-pair/edge tag(s). Finally, unified tag analysis is formulated as a constrained optimization problem, where the objective function characterizing the cross-patch tag consistency is constrained by the core equations for all vertex pairs, and the cutting plane method is used for efficient optimization. Extensive experiments on various tag analysis tasks over three widely used benchmark datasets validate the effectiveness of our proposed unified solution.

References

[1]
Flickr. http://www.°ickr.com/.
[2]
Picasa. http://picasa.google.com/.
[3]
L. Kennedy, S.-F. Chang, and I. Kozintsev. To search or to label?: Predicting the performance of search-based automatic image classifiers. In MIR, 2006.
[4]
T. Chua, J. Tang, R. Hong, H. Li, Z. Luo, and Y. Zheng. Nus-wide: A real-world web image database from national university of singapore. In CIVR, 2009.
[5]
D. Liu, X.-S. Hua, L. Yang, M. Wang, and H.-J. Zhang. Tag ranking. In WWW, 2009.
[6]
M. Ames and M. Naaman. Why we tag: Motivations for annotation in mobile and online media. In CHI,2007.
[7]
C. Wang, F. Jing, L. Zhang, and H.-J. Zhang. Content-based image annotation refinement. In CVPR, 2007.
[8]
D. Liu, X.-S. Hua, M. Wang, and H.-J. Zhang. Image retagging. In MM, 2010.
[9]
L. Cao and L. Fei-Fei. Spatially coherent latent topic model for concurrent segmentation and classification of objects and scenes. In ICCV, 2007.
[10]
Y. Chen, L. Zhu, A. Yuille, and H.-J. Zhang. Unsupervised learning of probabilistic object models (poms) for object classification, segmentation, and recognition using knowledge propagation. TPAMI, 2009.
[11]
J. Shotton, J. Winn, C. Rother, and A. Criminisi. Textonboost: Joint appearance, shape and context modeling for multi-class object recognition and segmentation. In ECCV, 2006.
[12]
X. Liu, B. Cheng, S. Yan, J. Tang, T. Chua, and H. Jin. Label to region by bi-layer sparsity priors. In MM, 2009.
[13]
J. Li and J. Wang. Automatic linguistic indexing of pictures by a statistical modeling approach. TPAMI, 2003.
[14]
E. Chang, K. Goh, G. Sychay, and G. Wu. Cbsa: content-based soft annotation for multimodal image retrieval using bayes point machines. TCSVT, 2003.
[15]
J. Jeon, V. Lavrenko, and R. Manmatha. Automatic image annotation and retrieval using cross-media relevance models. In SIGIR, 2003.
[16]
S. Feng, R. Manmatha, and V. Lavrenko. Multiple bernoulli relevance models for image and video annotation. In CVPR, 2004.
[17]
D. Zhou, O. Bousquet, T. Lal, J. Weston, and B. Sch-olkopf. Learning with local and global consistency. In NIPS, 2003.
[18]
D. Zhou and C. Burges. Spectral clustering and transductive learning with multiple views. In ICML, 2007.
[19]
D. Zhou, S. Zhu, K. Yu, X. Song, B. Tseng, H. Zha, and C. Giles. Learning multiple graphs for document recommendations. In WWW, 2008.
[20]
D. Zhou, J. Huang, and B. Sch-olkopf. Learning with hypergraphs: Clustering, classification, and embedding. In NIPS, 2006.
[21]
P. Felzenszwalb and D. Huttenlocher. Efficient graph-based image segmentation. IJCV, 2004.
[22]
J. Shi and J. Malik. Normalized cuts and image segmentation. TPAMI, 2000.
[23]
B. Russell, W. Freeman, A. Efros, J. Sivic, and A. Zisserman. Using multiple segmentations to discover objects and their extent in image collections. In CVPR, 2006.
[24]
K. Mikolajczyk and C. Schmid. Scale & affine invariant interest point detectors. IJCV, 2004.
[25]
D. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, 2004.
[26]
J. Kelley. The cutting-plane method for solving convex programs. JSIAM, 1960.
[27]
T. Joachims. Training linear svms in linear time. In KDD, 2006.
[28]
H. M-uller, S. Marchand-Maillet, and T. Pun. The truth about corel - evaluation in image retrieval. In CIVR, 2002.
[29]
Y. Liu, R. Jin, and L. Yang. Semi-supervised multi-label learning by constrained non-negative matrix factorization. In AAAI, 2006.
[30]
G. Chen, Y. Song, F. Wang, and C. Zhang. Semi-supervised multi-label learning by solving a sylvester equation. In SDM, 2008.
[31]
Z.-J. Zha, T. Mei, J. Wang, Z. Wang, and X.-S. Hua. Graph-based semi-supervised learning with multiple labels. JVCI, 2009.
[32]
R. Rahmani and S. Goldman. MISSL: Multiple instance semi-supervised learning. In ICML, 2006.

Cited By

View all
  • (2021)Learning Fundamental Visual Concepts Based on Evolved Multi-Edge Concept GraphIEEE Transactions on Multimedia10.1109/TMM.2020.304207223(4400-4413)Online publication date: 2021
  • (2019)Fundamental Visual Concept Learning From Correlated Images and TextIEEE Transactions on Image Processing10.1109/TIP.2019.289994428:7(3598-3612)Online publication date: Jul-2019
  • (2019)Multimedia integrated annotation based on common space learningMultimedia Tools and Applications10.1007/s11042-017-5068-078:1(437-456)Online publication date: 1-Jan-2019
  • Show More Cited By

Index Terms

  1. Unified tag analysis with multi-edge graph

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    MM '10: Proceedings of the 18th ACM international conference on Multimedia
    October 2010
    1836 pages
    ISBN:9781605589336
    DOI:10.1145/1873951
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

    Sponsors

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 25 October 2010

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. automatic tagging
    2. multi-edge graph
    3. tag refinement
    4. tag-to-region assignment

    Qualifiers

    • Research-article

    Conference

    MM '10
    Sponsor:
    MM '10: ACM Multimedia Conference
    October 25 - 29, 2010
    Firenze, Italy

    Acceptance Rates

    Overall Acceptance Rate 2,145 of 8,556 submissions, 25%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)8
    • Downloads (Last 6 weeks)1
    Reflects downloads up to 20 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2021)Learning Fundamental Visual Concepts Based on Evolved Multi-Edge Concept GraphIEEE Transactions on Multimedia10.1109/TMM.2020.304207223(4400-4413)Online publication date: 2021
    • (2019)Fundamental Visual Concept Learning From Correlated Images and TextIEEE Transactions on Image Processing10.1109/TIP.2019.289994428:7(3598-3612)Online publication date: Jul-2019
    • (2019)Multimedia integrated annotation based on common space learningMultimedia Tools and Applications10.1007/s11042-017-5068-078:1(437-456)Online publication date: 1-Jan-2019
    • (2018)Visual understanding by mining social mediaFrontiers of Computer Science: Selected Publications from Chinese Universities10.1007/s11704-017-6377-112:3(406-422)Online publication date: 1-Jun-2018
    • (2018)Image Tagging by Joint Deep Visual-Semantic PropagationAdvances in Multimedia Information Processing – PCM 201710.1007/978-3-319-77380-3_3(25-35)Online publication date: 10-May-2018
    • (2017)Multimodal Classification of Violent Online Political Extremism Content with Graph Convolutional NetworksProceedings of the on Thematic Workshops of ACM Multimedia 201710.1145/3126686.3126776(245-252)Online publication date: 23-Oct-2017
    • (2017)iPrivacy: Image Privacy Protection by Identifying Sensitive Objects via Deep Multi-Task LearningIEEE Transactions on Information Forensics and Security10.1109/TIFS.2016.263609012:5(1005-1016)Online publication date: May-2017
    • (2017)Graph-boosted convolutional neural networks for semantic segmentation2017 International Joint Conference on Neural Networks (IJCNN)10.1109/IJCNN.2017.7965909(612-618)Online publication date: May-2017
    • (2017)A discriminative graph inferring framework towards weakly supervised image parsingMultimedia Systems10.1007/s00530-015-0458-523:1(5-18)Online publication date: 1-Feb-2017
    • (2016)CNN-RNN: A Unified Framework for Multi-label Image Classification2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)10.1109/CVPR.2016.251(2285-2294)Online publication date: Jun-2016
    • Show More Cited By

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media