More Web Proxy on the site http://driver.im/

poster

Semi-supervised multi-instance multi-label learning for video annotation task

Authors:

Zhi-Hua ZhouAuthors Info & Claims

MM '12: Proceedings of the 20th ACM international conference on Multimedia

Pages 737 - 740

https://doi.org/10.1145/2393347.2396300

Published: 29 October 2012 Publication History

Abstract

Traditional approaches for automatic video annotation usually represent one video clip with a flat feature vector, neglecting the fact that video data contain natural structures. It is also noteworthy that a video clip is often relevant to multiple concepts. Indeed, the video annotation task is inherently a Multi-Instance Multi-Label learning (MIML) problem. Considering that manually annotating videos is labor-intensive and time-consuming, this paper proposes a semi-supervised MIML approach, SSMIML, which is able to exploit abundant unannotated videos to help improve the annotation performance. This approach takes label correlations into account, and enforces similar instances to share similar multi-labels. Evaluation on TREVID 2005 show that the proposed approach outperforms several state-of-the-art methods.

References

[1]

A. Argyriou, T. Evgeniou, and M. Pontil. Multi-task feature learning. In NIPS 19, pages 41--48. 2007.

[2]

M. Belkin, P. Niyogi, and V. Sindhwani. Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. J. Mach. Learn. Res., 7:2399--2434, 2006.

Digital Library

[3]

T. Evgeniou, C. A. Micchelli, and M. Pontil. Learning multiple tasks with kernel methods. J. Mach. Learn. Res., 6:615--637, 2005.

Digital Library

[4]

J. Fan, H. Luo, and X. Lin. Semantic video classification by integrating flexible mixture model with adaptive em algorithm. In MIR, pages 9--16, 2003.

Digital Library

[5]

S. Feng and D. Xu. Transductive multi-instance multi-label learning algorithm with application to automatic image annotation. Expert Syst. Appl., 37(1):661--670, 2010.

Digital Library

[6]

Z. Gu, T. Mei, X.-S. Hua, J. Tang, and X. Wu. Multi-layer multi-instance kernel for video concept detection. In MM, pages 349--352, 2007.

Digital Library

[7]

Z. Gu, T. Mei, X.-S. Hua, J. Tang, and X. Wu. Multi-layer multi-instance learning for video concept detection. IEEE Trans. Multimedia, 10(8):1605--1616, 2008.

Digital Library

[8]

Y. Jia and C. Zhang. Instance-level semisupervised multiple instance learning. In AAAI, pages 640--645, 2008.

Digital Library

[9]

Y.-F. Li, S.-J. Huang, and Z.-H. Zhou. Regularized semi-supervised multi-label learning. J. Comp. Res. Dev., 49(6):1272--1278, 2012 (in Chinese).

[10]

Y.-X. Li, S. Ji, J. Ye, S. Kumar, and Z.-H. Zhou. Drosophila gene expression pattern annotation through multi-instance multi-label learning. ACM/IEEE Trans. Comput. Biol. Bioinf., 9(1):98--112, 2012.

Digital Library

[11]

Y. Liu, R. Jin, and L. Yang. Semi-supervised multi-label learning by constrained non-negative matrix factorization. In AAAI, pages 421--426, 2006.

Digital Library

[12]

M. Naphade, L. Kennedy, J. R. Kender, S. F. Chang, P. Over, and A. Hauptmann. A light scale concept ontology for multimedia understanding for TRECVID 2005. Technical report, IBM Research, 2005.

[13]

M. Naphade and J. Smith. A generalized multiple instance learning algorithm for large scale modeling of multimedia semantics. In ICASSP, pages 341--344, 2005.

[14]

N. Nguyen. A new svm approach to multi-instance multi-label learning. In ICDM, pages 384--392, 2010.

Digital Library

[15]

C. Petersohn. Fraunhofer HHI at TRECVID 2004: Shot boundary detection system. In TRECVID, 2004.

[16]

G.-J. Qi, X.-S. Hua, Y. Rui, J. Tang, T. Mei, M. Wang, and H.-J. Zhang. Correlative multilabel video annotation with temporal kernels. ACM Trans. Multimedia Comput., Comm. Appl., 5(1):1--27, 2008.

Digital Library

[17]

R. Rahmani and S. A. Goldman. MISSL: Multiple-instance semi-supervised learning. In ICML, pages 705--712, 2006.

Digital Library

[18]

B. Schölkopf and A. J. Smola. Learning with Kernels. MIT Press, 2002.

[19]

A. J. Smola, S. Vishwanathan, and T. Hofmann. Kernel methods for missing variables. In AISTATS, pages 325--332, 2005.

[20]

J. Tang, X.-S. Hua, M. Wang, T. Mei, G.-J. Qi, and X. Wu. Structure-sensitive manifold ranking for video concept detection. In MM, pages 852--861, 2007.

Digital Library

[21]

M. Wang, X.-S. Hua, T. Mei, R. Hong, G. Qi, Y. Song, and L.-R. Dai. Semi-supervised kernel density estimation for video annotation. Comput. Vis. Image Und., 113(3):384--396, 2009.

Digital Library

[22]

W. Wang and Z.-H. Zhou. Learnability of multi-instance multi-label learning. Chinese Sci. Bull., 57(19):2488--2491, 2012.

[23]

L. Xie, P. Xu, S.-F. Chang, A. Divakaran, and H. Sun. Structure analysis of soccer video with domain knowledge and hidden markov models. Pattern Recogn. Lett., 25(7):767--775, 2004.

Digital Library

[24]

X.-S. Xu, X. Xue, and Z.-H. Zhou. Ensemble multi-instance multi-label learning approach for video annotation task. In MM, pages 1153--1156, 2011.

Digital Library

[25]

R. Yan and M. Naphade. Semi-supervised cross feature learning for semantic concept detection in videos. In CVPR, pages 657--663, 2005.

Digital Library

[26]

A. Yanagawa, S.-F. Chang, L. Kennedy, and W. Hsu. Columbia university's baseline detectors for 374 LSCOM semantic visual concepts. Technical Report# 222--2006--8, Columbia University ADVENT, Mar. 2007.

[27]

S.-H. Yang, H. Zha, and B.-G. Hu. Dirichlet-bernoulli alignment: A generative model for multi-class multi-label multi-instance corpora. In NIPS 23, pages 2143--2150. 2009.

[28]

Z.-J. Zha, X.-S. Hua, T. Mei, J. Wang, G.-J. Qi, and Z. Wang. Joint multi-label multi-instance learning for image classification. In CVPR, pages 1--8, 2008.

[29]

Z.-J. Zha, T. Mei, J. Wang, Z. Wang, and X.-S. Hua. Graph-based semi-supervised learning with multiple labels. J. Vis. Comm. Image Rep., 20(2):97--103, 2009.

Digital Library

[30]

Z.-H. Zhou and M.-L. Zhang. Multi-instance multi-label learning with application to scene classification. In NIPS 19, pages 1609--1616. 2007.

[31]

Z.-H. Zhou, M.-L. Zhang, S.-J. Huang, and Y.-F. Li. Multi-instance multi-label learning. Artif. Intell., 176(1):2291--2320, 2012.

Digital Library

Cited By

Zhang XLuo TLiu YHou CCai JKankanhalli MPrabhakaran BBoll SSubramanian RZheng LSingh VCesar PXie LXu D(2024)Imbalanced Multi-instance Multi-label Learning via Coding Ensemble and Adaptive ThresholdsProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3680911(5413-5422)Online publication date: 28-Oct-2024
https://dl.acm.org/doi/10.1145/3664647.3680911
Yang CLi P(2023)Mobile game props recommendation for machine learningJournal of Intelligent & Fuzzy Systems10.3233/JIFS-22070344:3(4093-4102)Online publication date: 9-Mar-2023
https://doi.org/10.3233/JIFS-220703
Perini LVercruyssen VDavis JSingh ASun YAkoglu LGunopulos DYan XKumar ROzcan FYe J(2023)Learning from Positive and Unlabeled Multi-Instance Bags in Anomaly DetectionProceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining10.1145/3580305.3599409(1897-1906)Online publication date: 6-Aug-2023
https://dl.acm.org/doi/10.1145/3580305.3599409
Show More Cited By

Index Terms

Semi-supervised multi-instance multi-label learning for video annotation task
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision tasks
        Video summarization
  2. Machine learning

Recommendations

Ensemble multi-instance multi-label learning approach for video annotation task
MM '11: Proceedings of the 19th ACM international conference on Multimedia

Automatic video annotation is an important ingredient for video indexing, browsing, and retrieval. Traditional studies represent one video clip with a flat feature vector; however, video data usually has natural structure. Moreover, a video clip is ...
Inductive Semi-supervised Multi-Label Learning with Co-Training
KDD '17: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

In multi-label learning, each training example is associated with multiple class labels and the task is to learn a mapping from the feature space to the power set of label space. It is generally demanding and time-consuming to obtain labels for training ...
Semi-supervised multi-label classification using incomplete label information
Highlights
- An inductive semi-supervised method called Smile is proposed for multi-label classification using incomplete label information.
Abstract
Classifying multi-label instances using incompletely labeled instances is one of the fundamental tasks in multi-label learning. Most existing methods regard this task as supervised weak-label learning problem and assume sufficient ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

MM '12: Proceedings of the 20th ACM international conference on Multimedia

October 2012

1584 pages

ISBN:9781450310895

DOI:10.1145/2393347

General Chairs:
Noboru Babaguchi
Osaka University, Japan
,
Kiyoharu Aizawa
The University of Tokyo, Japan
,
John Smith
IBM, USA
,
Program Chairs:
Shin'ichi Satoh
National Institute of Informatics, Japan
,
Thomas Plagemann
University of Oslo, Norway
,
Xian-Sheng Hua
Microsoft, USA
,
Rong Yan
Facebook, USA

Copyright © 2012 ACM.

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

SIGMM: ACM Special Interest Group on Multimedia

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 29 October 2012

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Poster

Conference

MM '12

Sponsor:

SIGMM

MM '12: ACM Multimedia Conference

October 29 - November 2, 2012

Nara, Japan

Acceptance Rates

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

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

20
Total Citations
View Citations
365
Total Downloads

Downloads (Last 12 months)13
Downloads (Last 6 weeks)1

Reflects downloads up to 15 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Zhang XLuo TLiu YHou CCai JKankanhalli MPrabhakaran BBoll SSubramanian RZheng LSingh VCesar PXie LXu D(2024)Imbalanced Multi-instance Multi-label Learning via Coding Ensemble and Adaptive ThresholdsProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3680911(5413-5422)Online publication date: 28-Oct-2024
https://dl.acm.org/doi/10.1145/3664647.3680911
Yang CLi P(2023)Mobile game props recommendation for machine learningJournal of Intelligent & Fuzzy Systems10.3233/JIFS-22070344:3(4093-4102)Online publication date: 9-Mar-2023
https://doi.org/10.3233/JIFS-220703
Perini LVercruyssen VDavis JSingh ASun YAkoglu LGunopulos DYan XKumar ROzcan FYe J(2023)Learning from Positive and Unlabeled Multi-Instance Bags in Anomaly DetectionProceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining10.1145/3580305.3599409(1897-1906)Online publication date: 6-Aug-2023
https://dl.acm.org/doi/10.1145/3580305.3599409
Papadopoulos ADelopoulos A(2023)Leveraging Unlabelled Data in Multiple-Instance Learning Problems for Improved Detection of Parkinsonian Tremor in Free-Living ConditionsIEEE Journal of Biomedical and Health Informatics10.1109/JBHI.2023.326709527:7(3569-3578)Online publication date: Jul-2023
https://doi.org/10.1109/JBHI.2023.3267095
Saleh AWeigang L(2023)Deep self-organizing cubeExpert Systems with Applications: An International Journal10.1016/j.eswa.2023.120627230:COnline publication date: 26-Jul-2023
https://dl.acm.org/doi/10.1016/j.eswa.2023.120627
Tang CLiu XWang PZhang CLi MWang L(2019)Adaptive Hypergraph Embedded Semi-Supervised Multi-Label Image AnnotationIEEE Transactions on Multimedia10.1109/TMM.2019.290986021:11(2837-2849)Online publication date: Nov-2019
https://doi.org/10.1109/TMM.2019.2909860
Tang HWang YTang SChu DLi C(2019)A Randomized Clustering Forest Approach for Efficient Prediction of Protein FunctionsIEEE Access10.1109/ACCESS.2019.28921207(12360-12372)Online publication date: 2019
https://doi.org/10.1109/ACCESS.2019.2892120
Zhang PWu HXu X(2018)A Dual-CNN Model for Multi-label Classification by Leveraging Co-occurrence Dependencies Between LabelsAdvances in Multimedia Information Processing – PCM 201710.1007/978-3-319-77380-3_30(315-324)Online publication date: 10-May-2018
https://doi.org/10.1007/978-3-319-77380-3_30
Soleimani HMiller D(2017)Semisupervised, multilabel, multi-instance learning for structured dataNeural Computation10.1162/NECO_a_0093929:4(1053-1102)Online publication date: 1-Apr-2017
https://dl.acm.org/doi/10.1162/NECO_a_00939
Zhang JWang ZYuan JTan YLiu QLienhart RWang HChen SBoll SChen PFriedland GLi JYan S(2017)Positive and Unlabeled Learning for Anomaly Detection with Multi-featuresProceedings of the 25th ACM international conference on Multimedia10.1145/3123266.3123304(854-862)Online publication date: 23-Oct-2017
https://dl.acm.org/doi/10.1145/3123266.3123304
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents