首页 > 论文 > 激光与光电子学进展 > 57卷 > 22期(pp:221012--1)

基于多视角低秩表征的短视频多标签学习模型

Microvideo Multilabel Learning Model Based on Multiview Low-Rank Representation

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

提出一种基于多视角低秩表征的短视频多标签分类模型。该模型将低秩表征和多标签学习结合到同一框架中,利用不同类型特征的一致性学习本征稳定的低秩表示。同时为了获得标签相关性的潜在表示,构建了标签相关性学习项来自适应地捕获标签的相关性矩阵。此外,模型利用监督信息进一步提高了其表征能力。大量的实验结果证实了所提方法的优越性。

Abstract

We propose a microvideo multilabel learning model based on a multiview low-rank representation, which combines the low-rank representation and multilabel learning into a unified framework and uses the consistency in different features to learn an intrinsically robust low-rank representation. Meanwhile, to represent the potential label correlations, our proposed model constructs a label correlation learning term to adaptively capture the labels’ correlation matrix. Furthermore, the supervised information is exploited to further improve the representation ability of our model. Extensive experiments on a large-scale public dataset show the effectiveness of the proposed scheme.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP391.4

DOI:10.3788/LOP57.221012

所属栏目:图像处理

基金项目:国家自然科学基金;

收稿日期:2020-03-10

修改稿日期:2020-04-10

网络出版日期:2020-11-01

作者单位    点击查看

吕卫:天津大学电气自动化与信息工程学院, 天津 300072
李德盛:天津大学电气自动化与信息工程学院, 天津 300072
谭浪:北京智芯微电子科技有限公司, 北京 102200
井佩光:天津大学电气自动化与信息工程学院, 天津 300072
苏育挺:天津大学电气自动化与信息工程学院, 天津 300072

联系人作者:李德盛(lidesheng1996@tju.edu.cn)

备注:国家自然科学基金;

【1】Zhang M L, Zhou Z H. A review on multi-label learning algorithms [J]. IEEE Transactions on Knowledge and Data Engineering. 2014, 26(8): 1819-1837.Zhang M L, Zhou Z H. A review on multi-label learning algorithms [J]. IEEE Transactions on Knowledge and Data Engineering. 2014, 26(8): 1819-1837.

【2】Boutell M R, Luo J B, Shen X P, et al. Learning multi-label scene classification [J]. Pattern Recognition. 2004, 37(9): 1757-1771.Boutell M R, Luo J B, Shen X P, et al. Learning multi-label scene classification [J]. Pattern Recognition. 2004, 37(9): 1757-1771.

【3】Read J, Pfahringer B, Holmes G, et al. Classifier chains for multi-label classification [J]. Machine Learning. 2011, 85(3): 333-359.

【4】Zhang Q W, Zhong Y, Zhang M L. Feature-induced labeling information enrichment for multi-label learning[C]∥ 32th AAAI Conference on Artificial Intelligence, February 2-7, 2018, New Orleans, Louisiana, USA. Reston,. VA: , 2018, 4446-4453.

【5】Nie L Q, Wang X, Zhang J L, et al. Enhancing micro-video understanding by harnessing external sounds[C]∥Proceedings of the 2017 ACM on Multimedia Conference-MM ’17, October 19-27, 2017. Mountain View, California, USA. New York: , 2017, 1192-1200.

【6】Lian Q S, Xia C C. Compressed sensing of color images based on local Gaussian model in the dual-tree complex wavelet [J]. Laser & Optoelectronics Progress. 2011, 48(10): 101001.
练秋生, 夏长城. 基于双树复数小波局部高斯模型的彩色图像压缩感知 [J]. 激光与光电子学进展. 2011, 48(10): 101001.

【7】Yang P, Liu D E, Li R X, et al. Damage detection of metal parts by combining information entropy and low-rank tensor analysis [J]. Laser & Optoelectronics Progress. 2019, 56(21): 211006.
杨鹏, 刘德儿, 李瑞雪, 等. 结合信息熵与低秩张量分析的金属零件破损检测 [J]. 激光与光电子学进展. 2019, 56(21): 211006.

【8】Niu Q, Chen X H. Image recognition using joint projection learning algorithm based on latent low-rank representation [J]. Laser & Optoelectronics Progress. 2019, 56(14): 141006.
牛强, 陈秀宏. 基于隐式低秩表示的联合投影学习算法及图像识别 [J]. 激光与光电子学进展. 2019, 56(14): 141006.

【9】Zhang J, Fu J P, Li X H. Low-rank regularized heterogeneous tensor decomposition algorithm for subspace clustering [J]. Laser & Optoelectronics Progress. 2018, 55(7): 071003.
张静, 付建鹏, 李新慧. 基于低秩正则化异构张量分解的子空间聚类算法 [J]. 激光与光电子学进展. 2018, 55(7): 071003.

【10】Yang P, Liu D E, Li R X, et al. Damage detection of metal parts by combining information entropy and low-rank tensor analysis [J]. Laser & Optoelectronics Progress. 2019, 56(21): 211006.
杨鹏, 刘德儿, 李瑞雪, 等. 结合信息熵与低秩张量分析的金属零件破损检测 [J]. 激光与光电子学进展. 2019, 56(21): 211006.

【11】Zhang X H, Hao R F, Li T Y. Hyperspectral abnormal target detection based on low rank and sparse matrix decomposition-sparse representation [J]. Laser & Optoelectronics Progress. 2019, 56(4): 042801.
张晓慧, 郝润芳, 李廷鱼. 基于低秩稀疏矩阵分解和稀疏字典表达的高光谱异常目标检测 [J]. 激光与光电子学进展. 2019, 56(4): 042801.

【12】Hassannejad H, Matrella G, Ciampolini P, et al. Food image recognition using very deep convolutional networks[C]∥Proceedings of the 2nd International Workshop on Multimedia Assisted Dietary Management-MADiMa ’16, October 16, 2016, Amsterdam, The Netherlands. New York: , 2016, 41-49.

【13】Wang L M, Qiao Y, Tang X O. Action recognition with trajectory-pooled deep-convolutional descriptors[C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015, Boston, MA, USA. New York: , 2015, 4305-4314.

【14】Jia Z L, Zhang X, Guan N Y, et al. Gene ranking of RNA-seq data via discriminant non-negative matrix factorization [J]. PLoS One. 2015, 10(9): e0137782.

【15】Liu G C, Yan S C. Latent Low-Rank Representation for subspace segmentation and feature extraction[C]∥2011 International Conference on Computer Vision, November 6-13, 2011, Barcelona, Spain. New York: , 2011, 1615-1622.

【16】Zhu Y, Kwok J T, Zhou Z H. Multi-label learning with global and local label correlation [J]. IEEE Transactions on Knowledge and Data Engineering. 2018, 30(6): 1081-1094.

【17】Zhang M L, Zhou Z H. ML-KNN: a lazy learning approach to multi-label learning [J]. Pattern Recognition. 2007, 40(7): 2038-2048.Zhang M L, Zhou Z H. ML-KNN: a lazy learning approach to multi-label learning [J]. Pattern Recognition. 2007, 40(7): 2038-2048.

【18】Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015, Boston, MA, USA. New York: , 2015, 1-9.

【19】Tran D, Bourdev L, Fergus R, et al. Learning spatiotemporal features with 3D convolutional networks[C]∥2015 IEEE International Conference on Computer Vision (ICCV), December 7-13, 2015, Santiago, Chile. New York: , 2015, 4489-4497.

【20】Yeh C K, Wu W C, Ko W J, et al. Learning deep latent spaces for multi-label classification 31th AAAI Conference on Artificial Intelligence, February 4-9, 2017, San Francisco, California. Reston,[C]. VA: , 2017, 2838-2844.

引用该论文

Lü Wei,Li Desheng,Tan Lang,Jing Peiguang,Su Yuting. Microvideo Multilabel Learning Model Based on Multiview Low-Rank Representation[J]. Laser & Optoelectronics Progress, 2020, 57(22): 221012

吕卫,李德盛,谭浪,井佩光,苏育挺. 基于多视角低秩表征的短视频多标签学习模型[J]. 激光与光电子学进展, 2020, 57(22): 221012

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF