{"type":"ScholarlyArticle","title":"Label Distribution Learning with Label Correlations via Low-Rank Approximation","authors":[{"name":"Tingting Ren","slug":"tingting-ren","given":"Tingting","family":"Ren","affiliation":"School of Computer Science and Engineering , Nanjing University of Science and Technology , China"},{"name":"Xiuyi Jia","slug":"xiuyi-jia","given":"Xiuyi","family":"Jia","affiliation":"School of Computer Science and Engineering , Nanjing University of Science and Technology , China; Jiangsu Key Laboratory of Big Data Security & Intelligent Processing , Nanjing University of Posts and Telecommunications , China; State Key Laboratory for Novel Software Technology , Nanjing University , China"},{"name":"Weiwei Li","slug":"weiwei-li","given":"Weiwei","family":"Li","affiliation":"College of Astronautics , Nanjing University of Aeronautics and Astronautics , China"},{"name":"Shu Zhao","slug":"shu-zhao","given":"Shu","family":"Zhao","affiliation":"School of Computer Science and Technology , Anhui University , China"}],"abstract":"Label distribution learning (LDL) can be viewed as the generalization of multi-label learning. This novel paradigm focuses on the relative importance of different labels to a particular instance. Most previous LDL methods either ignore the correlation among labels, or only exploit the label correlations in a global way. In this paper, we utilize both the global and local relevance among labels to provide more information for training model and propose a novel label distribution learning algorithm. In particular, a label correlation matrix based on low-rank approximation is applied to capture the global label correlations. In addition, the label correlation among local samples are adopted to modify the label correlation matrix. The experimental results on real-world data sets show that the proposed algorithm outperforms state-of-the-art LDL methods.","doi":"10.24963/ijcai.2019/461","url":"https://ijcai.org/proceedings/2019/461","pdf":"https://ijcai.org/proceedings/2019/0461.pdf","markdown":"https://ijcai.org/proceedings/2019/461.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/461","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Machine Learning M-Z","track":"Main track","number":461,"pages":{"first":3325,"last":3331},"keywords":["Machine Learning: Multi-instance;Multi-label;Multi-view learning","Machine Learning: Structured Prediction"],"videos":[],"references":[{"position":1,"raw":"LDLLC CPNN LDL-SCL PT-SVM Yeast-alpha .0362±.0018(1) .0577±.0010(8) .0392±.0018(4) .0412±.0006(7) .0382±.0009(3) .0402±.0007(6) .0376±.0008(2) .0398±.0007(5)","title":"PT-SVM Yeast-alpha","authors":"Ldllc Cpnn, Ldl-Scl","year":"2010","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"Yeast-cdc .0420±.0021(1) .0602±.0006(8) .0459±.0019(5) .0473±.0007(7) .0427±.0010(3) .0465±.0012(6) .0422±.0010(2) .0445±.0011(4)","title":"Yeast-cdc","authors":null,"year":"0420","venue":"Yeast-cdc","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"Yeast-cold .0560±.0029(1) .0708±.0012(8) .0596±.0014(4) .0643±.0023(6) .0585±.0016(2) .0603±.0023(5) .0591±.0012(3) .0662±.0030(7)","title":"Yeast","authors":null,"year":"0560","venue":"Yeast","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"Yeast-diau .0563±.0044(1) .0759±.0014(8) .0599±.0011(4) .0632±.0013(5) .0594±.0018(2) .0634±.0014(6) .0596±.0014(3) .0758±.0034(7)","title":"Yeast","authors":null,"year":"0563","venue":"Yeast","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"Yeast-dtt .0382±.0030(1) .0575±.0035(8) .0426±.0021(4.5) .0455±.0014(7) .0408±.0011(2) .0426±.0019(4.5) .0416±.0016(3) .0446±.0019(6)","title":"Yeast","authors":null,"year":"0382","venue":"Yeast","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"Yeast-elu .0402±.0019(1) .0602±.0007(8) .0419±.0010(4) .0455±.0005(7) .0415±.0009(2) .0425±.0009(5) .0417±.0005(3) .0438±.0008(6)","title":"Yeast-elu","authors":null,"year":"2007","venue":"Yeast-elu","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"Yeast-heat .0579±.0028(1) .0765±.0013(8) .0608±.0022(4) .0634±.0012(7) .0596±.0019(2) .0615±.0009(5.5) .0602±.0014(3) .0615±.0010(5.5)","title":"Yeast-heat","authors":null,"year":"0579","venue":"Yeast-heat","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"Yeast-spo .0811±.0061(1) .0962±.0022(8) .0854±.0018(4) .0921±.0026(6) .0846±.0030(3) .0859±.0025(5) .0836±.0016(2) .0922±.0035(7)","title":"Yeast-spo","authors":null,"year":"0811","venue":"Yeast-spo","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"Yeast-spo5 .0876±.0051(1) .0988±.0031(8) .0927±.0018(5) .0963±.0026(7) .0911±.0035(2) .0915±.0031(3) .0918±.0032(4) .0960±.0034(6)","title":"Yeast-spo","authors":null,"year":"0051","venue":"Yeast-spo","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"Yeast-spoem .0745±.0092(1) .0925±.0048(7) .0880±.0033(3.5) .0902±.0026(6) .0854±.0026(2) .0880±.0028(3.5) .0882±.0038(5) .0942±.0075(8)","title":"Yeast-spoem","authors":null,"year":"0745","venue":"Yeast-spoem","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"s-JAFFE .1186±.0159(2) .1535±.0086(7) .1305±.0048(4) .1291±.0056(3) .1501±.0099(5) .1556±.0082(8) .1148±.0086(1) .1532±.0070(6)","title":"JAFFE","authors":null,"year":"1186","venue":"JAFFE","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"SBU 3DFE .1405±.0069(1) .1607±.0031(7) .1585±.0018(4) .1554±.0024(3) .1593±.0052(5) .1601±.0028(6) .1421±.0035(2) .1626±.0035(8)","title":"SBU","authors":null,"year":"1405","venue":"SBU","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"Natural Scene .4434±.0312(1) .5397±.0039(7) .4757±.0056(3) .4706±.0008(2) .5354±.0076(6) .5174±.0097(5) .5000±.0064(4) .6496±.0175(8)","title":"Natural Scene","authors":null,"year":"0039","venue":"Natural Scene","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"Movie .1578±.0077(1) .2014±.0035(7) .1639±.0033(2) .1773±.0048(4) .1849±.0058(5) .1877±.0067(6) .1740±.0033(3) .3054±.0178(8) Human Gene .1935±.0115(1) .2176±.0039(4) .2160±.0017(3) .2557±.0037(7) .2726±.0038(8) .2178±.0025(5) .2089±.0027(2) .2179±.0065(6) Table 2: Sφrensen (the lower the better) results on all the data. The value is measured by 10 times 10-fold cross validation shown in mean±std(rank) form. The best results on each row are highlighted. Data LDL-LCLR IIS-LDL BFGS-LDL AA-kNN LDLLC CPNN LDL-SCL PT-SVM Yeast-alpha .9638±.0018(1) .9423±.0010(8) .9608±.0018(4) .9588±.0006(7) .9618±.0009(3) .9598±.0007(6) 9620±.0008(2) .9602±.0007(5)","title":"Data LDL-LCLR IIS-LDL BFGS-LDL AA-kNN LDLLC CPNN LDL-SCL PT","authors":null,"year":"1578","venue":"Human Gene","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"Yeast-cdc .9580±.0021(1) .9398±.0006(8) .9541±.0019(5) .9527±.0007(7) .9573±.0010(3) .9535±.0012(6) .9578±.0010(2) .9555±.0011(4)","title":"Yeast-cdc","authors":null,"year":"9580","venue":"Yeast-cdc","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"Yeast-cold .9440±.0029(1) .9292±.0012(8) .9404±.0014(4) .9357±.0023(6) .9415±.0016(2) .9397±.0023(5) .9409±.0012(3) .9338±.0030(7)","title":"Yeast-cold","authors":null,"year":"9440","venue":"Yeast-cold","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"Yeast-diau .9437±.0044(1) .9241±.0014(8) .9401±.0011(4) .9368±.0013(5) .9406±.0018(2) .9366±.0014(6) .9404±.0014(3) .9242±.0034(7)","title":"Yeast-diau","authors":null,"year":"2014","venue":"Yeast-diau","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"Yeast-dtt .9618±.0030(1) .9425±.0035(8) .9574±.0021(4.5) .9545±.0014(7) .9592±.0011(2) .9574±.0019(4.5) .9584±.0016(3) .9554±.0019(6)","title":"Yeast-dtt","authors":null,"year":"9618","venue":"Yeast-dtt","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"Yeast-elu .9598±.0019(1) .9398±.0007(8) .9581±.0010(4) .9545±.0005(7) .9585±.0009(2) .9575±.0009(5) .9583±.0006(3) .9562±.0008(6)","title":"Yeast-elu","authors":null,"year":"2007","venue":"Yeast-elu","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"Yeast-heat .9421±.0028(1) .9235±.0013(8) .9392±.0022(4) .9366±.0012(7) .9404±.0019(2) .9385±.0009(5.5) .9398±.0014(3) .9385±.0010(5.5)","title":"Yeast-heat","authors":null,"year":"2013","venue":"Yeast-heat","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"Yeast-spo .9189±.0061(1) .9038±.0022(8) .9146±.0018(4) .9079±.0026(6) .9154±.0030(3) .9141±.0025(5) .9164±.0016(2) .9078±.0035(7)","title":"Yeast-spo","authors":null,"year":"9189","venue":"Yeast-spo","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"Yeast-spo5 .9124±.0051(1) .9012±.0031(8) .9073±.0018(5) .9037±.0026(7) .9089±.0035(2) .9085±.0031(3) .9082±.0032(4) .9040±.0034(6)","title":"Yeast-spo","authors":null,"year":"9124","venue":"Yeast-spo","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"Yeast-spoem .9255±.0092(1) .9075±.0048(7) .9120±.0033(3.5) .9098±.0026(6) .9146±.0026(2) .9120±.0028(3.5) .9118±.0038(5) .9058±.0075(8)","title":"Yeast-spoem","authors":null,"year":"1948","venue":"Yeast-spoem","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"s-JAFFE .8814±.0159(2) .8465±.0086(7) .8695±.0048(4) .8709±.0056(3) .8499±.0099(5) .8444±.0082(8) .8851±.0086(1) .8468±.0070(6)","title":"JAFFE","authors":null,"year":"8814","venue":"JAFFE","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"SBU 3DFE .8595±.0069(1) .8393±.0031(7) .8415±.0018(4) .8446±.0024(3) .8407±.0052(5) .8399±.0028(6) .8579±.0036(2) .8374±.0035(8)","title":"SBU","authors":null,"year":"0069","venue":"SBU","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"Natural Scene .5566±.0312(1) .4603±.0039(7) .5243±.0056(3) .5294±.0008(2) .4646±.0076(6) .4826±.0097(5) .5004±.0064(4) .3504±.0175(8)","title":"Natural Scene","authors":null,"year":"0039","venue":"Natural Scene","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"Movie .8422±.0077(1) .7986±.0035(7) .8361±.0033(2) .8227±.0048(4) .8151±.0058(5) .8123±.0067(6) .8260±.0033(3) .6946±.0178(8) Human Gene .8065±.0115(1) .7824±.0039(4) .7840±.0017(3) .7443±.0037(7) .7274±.0038(8) .7822±.0025(5) .7911±.0023(2) .7810±.0100(6)","title":"Human Gene","authors":null,"year":"8422","venue":"Human Gene","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Boyd et al., 2011] Stephen Boyd, Neal Parikh, Eric Chu, Borja Peleato, and Jonathan Eckstein. Distributed opti- mization and statistical learning via the alternating direc- tion method of multipliers. Foundations & Trends in Ma- chine Learning, 3(1):1-122, 2011.","title":"Distributed optimization and statistical learning via the alternating direction method of multipliers","authors":"Stephen Boyd, Neal Parikh, Eric Chu, Borja Peleato, Jonathan Eckstein","year":"2011","venue":"Foundations & Trends in Machine Learning","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Cai et al., 2010] Jianfeng Cai, Emmanuel J. Candès, and Zuowei Shen. A singular value thresholding algorithm for matrix completion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(4):1956-1982, 2010.","title":"A singular value thresholding algorithm for matrix completion","authors":"Jianfeng Cai, Emmanuel J Candès, Zuowei Shen","year":"2010","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Demšar, 2006] Janez Demšar. Statistical comparisons of classifiers over multiple data sets. Journal of Machine Learning Research, 7(Jan):1-30, 2006.","title":"Janez Demšar. Statistical comparisons of classifiers over multiple data sets","authors":"Demšar","year":"2006","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Gao et al., 2017] Binbin Gao, Chao Xing, Chenwei Xie, Jianxin Wu, and Xin Geng. Deep label distribution learn- ing with label ambiguity. IEEE Transactions on Image Processing, 26(6):2825-2838, 2017.","title":"Deep label distribution learning with label ambiguity","authors":"Binbin Gao, Chao Xing, Chenwei Xie, Jianxin Wu, Xin Geng","year":"2017","venue":"IEEE Transactions on Image Processing","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Gao et al., 2018] Binbin Gao, Hongyu Zhou, Jianxin Wu, and Xin Geng. Age estimation using expectation of label distribution learning. In International Joint Conference on Artificial Intelligence, pages 712-718, 2018.","title":"Age estimation using expectation of label distribution learning","authors":"Binbin Gao, Hongyu Zhou, Jianxin Wu, Xin Geng","year":"2018","venue":"International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2018/99"},{"position":33,"raw":"[Geng and Xia, 2014] Xin Geng and Yu Xia. Head pose es- timation based on multivariate label distribution. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 1837-1842, 2014.","title":"Head pose estimation based on multivariate label distribution","authors":"Xin Geng, Yu Xia","year":"2014","venue":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Geng et al., 2010] Xin Geng, Kate Smith-Miles, and Zhi- Hua Zhou. Facial age estimation by learning from label distributions. In AAAI Conference on Artificial Intelli- gence, pages 451-456, 2010.","title":"Facial age estimation by learning from label distributions","authors":"Xin Geng, Kate Smith-Miles, Zhi-Hua Zhou","year":"2010","venue":"AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Geng et al., 2013] Xin Geng, Chao Yin, and Zhi-Hua Zhou. Facial age estimation by learning from label distributions. IEEE Transactions on Pattern Analysis and Machine In- telligence, 35(10):2401-2412, 2013.","title":"Facial age estimation by learning from label distributions","authors":"Xin Geng, Zhi-Hua Chao Yin, Zhou","year":"2013","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Geng et al., 2014] Xin Geng, Qin Wang, and Yu Xia. Fa- cial age estimation by adaptive label distribution learning. In International Conference on Pattern Recognition, pages 4465-4470, 2014.","title":"Facial age estimation by adaptive label distribution learning","authors":"Xin Geng, Qin Wang, Yu Xia","year":"2014","venue":"International Conference on Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Geng, 2016] Xin Geng. Label distribution learning. IEEE Transactions on Knowledge and Data Engneering, 28(7):1734-1748, 2016.","title":"Label distribution learning","authors":"Xin Geng, Geng","year":"2016","venue":"IEEE Transactions on Knowledge and Data Engneering","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[He et al., 2017] Zhouzhou He, Xi Li, Zhongfei Zhang, Fei Wu, Xin Geng, Yaqing Zhang, Ming-Hsuan Yang, and Yueting Zhuang. Data-dependent label distribution learn- ing for age estimation. IEEE Transactions on Image Pro- cessing, 26(8):3846-3858, 2017.","title":"Data-dependent label distribution learning for age estimation","authors":"He","year":"2017","venue":"IEEE Transactions on Image Processing","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Huo et al., 2016] Zengwei Huo, Xu Yang, Chao Xing, Ying Zhou, Peng Hou, Jiaqi Lv, and Xin Geng. Deep age dis- tribution learning for apparent age estimation. In IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 722-729, 2016.","title":"Deep age distribution learning for apparent age estimation","authors":"Zengwei Huo, Xu Yang, Chao Xing, Ying Zhou, Peng Hou, Jiaqi Lv, Xin Geng","year":"2016","venue":"IEEE Conference on Computer Vision and Pattern Recognition Workshops","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Jia et al., 2018] Xiuyi Jia, Weiwei Li, Junyu Liu, and Yu Zhang. Label distribution learning by exploiting la- bel correlations. In AAAI Conference on Artificial Intelli- gence, 2018.","title":"Label distribution learning by exploiting label correlations","authors":"Jia","year":"2018","venue":"AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Liu et al., 2010] Guangcan Liu, Zhouchen Lin, and Yong Yu. Robust subspace segmentation by low-rank represen- tation. In International Conference on Machine Learning, pages 663-670, 2010.","title":"Robust subspace segmentation by low-rank representation","authors":"Liu","year":"2010","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Malouf, 2002] Robert Malouf. A comparison of algorithms for maximum entropy parameter estimation. In Confer- ence on Natural Language Learning, pages 49-55, 2002.","title":"A comparison of algorithms for maximum entropy parameter estimation","authors":"Robert Malouf","year":"2002","venue":"Conference on Natural Language Learning","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Tsoumakas et al., 2007] G Tsoumakas, I Katakis, and D Taniar. Multi-label classification: An overview. Interna- tional Journal of Data Warehousing & Mining, 3(3):1-13, 2007.","title":"Multi-label classification: An overview","authors":"Tsoumakas, Katakis, Taniar","year":"2007","venue":"International Journal of Data Warehousing & Mining","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Xing et al., 2016] Chao Xing, Xin Geng, and Hui Xue. Lo- gistic boosting regression for label distribution learning. In IEEE Conference on Computer Vision and Pattern Recog- nition, pages 4489-4497, 2016.","title":"Logistic boosting regression for label distribution learning","authors":"Chao Xing, Xin Geng, Hui Xue","year":"2016","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Xu and Zhou, 2017] Miao Xu and Zhi-Hua Zhou. Incom- plete label distribution learning. In International Joint Conference on Artificial Intelligence, pages 3175-3181, 2017.","title":"Incomplete label distribution learning","authors":"Zhou ; ] Miao Xu, Zhi-Hua Xu, Zhou","year":"2017","venue":"International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2017/443"},{"position":46,"raw":"[Xu et al., 2014] Linli Xu, Zhen Wang, Zefan Shen, Yubo Wang, and Enhong Chen. Learning low-rank label cor- relations for multi-label classification with missing labels. In IEEE International Conference on Data Mining, pages 1067-1072, 2014.","title":"Learning low-rank label correlations for multi-label classification with missing labels","authors":"Xu","year":"2014","venue":"IEEE International Conference on Data Mining","doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Yuan, 1991] Ya-Xiang Yuan. A modified bfgs algorithm for unconstrained optimization. IMA Journal of Numerical Analysis, 11(3):325-332, 1991.","title":"A modified bfgs algorithm for unconstrained optimization","authors":"Ya-Xiang Yuan","year":"1991","venue":"IMA Journal of Numerical Analysis","doi":null,"url":null,"internal_url":null},{"position":48,"raw":"[Zhang et al., 2015] Zhaoxiang Zhang, Mo Wang, and Xin Geng. Crowd counting in public video surveillance by la- bel distribution learning. Neurocomputing, 166:151-163, 2015.","title":"Crowd counting in public video surveillance by label distribution learning","authors":"Zhang","year":"2015","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":49,"raw":"[Zhao and Geng, 2017] Quan Zhao and Xin Geng. Selec- tion of target function in label distribution learning. Fron- tiers of Computer Science and Technology, 5(11):708- 719, 2017.","title":"Selection of target function in label distribution learning","authors":"Geng Zhao, Quan Zhao, Xin Geng","year":"2017","venue":"Frontiers of Computer Science and Technology","doi":null,"url":null,"internal_url":null},{"position":50,"raw":"[Zhao and Zhou, 2018] Peng Zhao and Zhi-Hua Zhou. Label distribution learning by optimal transport. In AAAI Con- ference on Artificial Intelligence, pages 4506-4513, 2018.","title":"Label distribution learning by optimal transport","authors":"Peng Zhao, Zhi-Hua Zhou","year":"2018","venue":"AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":51,"raw":"[Zheng et al., 2018] Xiang Zheng, Xiuyi Jia, and Weiwei Li. Label distribution learning by exploiting sample correla- tions locally. In AAAI Conference on Artificial Intelli- gence, pages 4556-4563, 2018.","title":"Label distribution learning by exploiting sample correlations locally","authors":"Xiang Zheng, Xiuyi Jia, Weiwei Li","year":"2018","venue":"AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":52,"raw":"[Zhou et al., 2015] Ying Zhou, Hui Xue, and Xin Geng. Emotion distribution recognition from facial expressions. In ACM International Conference on Multimedia, pages 1247-1250, 2015.","title":"Emotion distribution recognition from facial expressions","authors":"Ying Zhou, Hui Xue, Xin Geng","year":"2015","venue":"ACM International Conference on Multimedia","doi":null,"url":null,"internal_url":null},{"position":53,"raw":"[Zhou et al., 2016] Deyu Zhou, Xuan Zhang, Yin Zhou, Quan Zhao, and Xin Geng. Emotion distribution learn- ing from texts. In Conference on Empirical Methods in Natural Language Processing, pages 638-647, 2016.","title":"Emotion distribution learning from texts","authors":"Deyu Zhou, Xuan Zhang, Yin Zhou, Quan Zhao, Xin Geng","year":"2016","venue":"Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}