Automatic Visual Concept Learning for Social Event Understanding

被引:52
作者
Yang, Xiaoshan [1 ,2 ]
Zhang, Tianzhu [1 ,2 ]
Xu, Changsheng [1 ,2 ]
Hossain, M. Shamim [3 ]
机构
[1] Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
[2] China Singapore Inst Digital Media, Singapore 119613, Singapore
[3] King Saud Univ, Coll Comp & Informat Sci, SWE Dept, Riyadh 12372, Saudi Arabia
基金
中国国家自然科学基金; 北京市自然科学基金;
关键词
Event analysis; video recognition; RECOGNITION;
D O I
10.1109/TMM.2015.2393635
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Vision-based event analysis is extremely difficult due to the various concepts (object, action, and scene) contained in videos. Though visual concept-based event analysis has achieved significant progress, it has two disadvantages: visual concept is defined manually, and has only one corresponding classifier in traditional methods. To deal with these issues, we propose a novel automatic visual concept learning algorithm for social event understanding in videos. First, instead of defining visual concept manually, we propose an effective automatic concept mining algorithm with the help of Wikipedia, N-gram Web services, and Flickr. Then, based on the learned visual concept, we propose a novel boosting concept learning algorithm to iteratively learn multiple classifiers for each concept to enhance its representative discriminability. The extensive experimental evaluations on the collected dataset well demonstrate the effectiveness of the proposed algorithm for social event understanding.
引用
收藏
页码:346 / 358
页数:13
相关论文
共 45 条
[1]  
[Anonymous], 2013, PMLR
[2]  
[Anonymous], P MM 2013
[3]  
[Anonymous], 2012, ACM international conference proceeding series, DOI DOI 10.1145/2396761.2396785
[4]  
[Anonymous], 2012, P 2 ACM INT C MULTIM, DOI DOI 10.1145/2324796.2324825
[5]  
[Anonymous], P 2 ACM INT C MULT R
[6]  
[Anonymous], P 20 ACM INT C MULT
[7]  
[Anonymous], 2012, P 29 INT C MACH LEAR
[8]  
Bao B.-K., 2013, Proceedings of the International Conference on Multimedia Retrieval, P135, DOI 10.1145/2461466.2461491
[9]   Learning Deep Architectures for AI [J].
Bengio, Yoshua .
FOUNDATIONS AND TRENDS IN MACHINE LEARNING, 2009, 2 (01) :1-127
[10]  
Blum A., 1998, Proceedings of the Eleventh Annual Conference on Computational Learning Theory, P92, DOI 10.1145/279943.279962