姚鸿勋 - 哈尔滨工业大学

个人简介

工作经历 2004-目前哈尔滨工业大学计算机科学与技术学院博士生导师 2004.7-2005.6 NEC中国研究院访问教授 2003-2004 哈尔滨工业大学计算机科学与技术学院教授 1997-2003 哈尔滨工业大学计算机科学与技术学院副教授，教研室教学主任 1992-1997 哈尔滨工业大学计算机科学与工程系讲师 1990-1992 哈尔滨工业大学计算机科学与工程系助教教育经历 1997-2003：哈尔滨工业大学计算机应用技术专业获博士学位 1987-1990：哈尔滨船舶工程学院计算机应用技术专业获硕士学位 1983-1987：哈尔滨船舶工程学院计算机科学与技术系获学士学位荣誉 2021年获中国”计算机专业优秀教师奖” 2019年黑龙江省自然科学技术二等奖 2018年获中国图象图形学学会优秀博士论文导师，计算学部“优博指导奖” 2018年获哈尔滨工业大学优秀共产党员“十佳”称号 2018年获哈尔滨工业大学“三八红旗手”奖 2018年获哈尔滨工业大学“研究生精品课程”奖 2017年获哈尔滨工业大学“优秀工会工作者”奖 2015年黑龙江省自然科学技术二等奖 2013年、2016年两度获哈尔滨工业大学优秀博士论文指导教师 2004年黑龙江省高等学校自然科学著作壹等奖 2003年黑龙江省高等学校教学成果贰等奖 2002年黑龙江省高等学校自然科学著作壹等奖 1998年哈尔滨工业大学“教学优秀贰等奖” 主要任职哈尔滨工业大学计算机学院教授，博士生导师中国图象图形学学会常务理事中国图象图形学学会情感计算与理解专委会主任中国图象图形学学会女科技工作者工作委员会委员中国图象图形学学会制度建设工作委会会委员中国计算机学会多媒体专委会执行委员黑龙江省人工智能学会常务理事

研究领域

计算机视觉智能多媒体数据分析与理解情感计算人工智能模型理论媒体技术与艺术智慧农业应用

近期论文

查看导师新发文章（温馨提示：请注意重名现象，建议点开原文通过作者单位确认）

Unsupervised Low-Light Video Enhancement With Spatial-Temporal Co-Attention Transformer. Xiaoqian LvShengping ZhangChenyang WangWeigang ZhangHongxun YaoQingming Huang IEEE Trans. Image Process. 32: 4701-4715 Center-push loss for joint view-based 3D model classification and retrieval feature learning. Dong WangBin WangHongxun YaoHong Liu Signal Image Video Process. 17(4): 873-880 HPnet: Hybrid Parallel Network for Human Pose Estimation. Haoran LiHongxun YaoYuxin Hou Sensors 23(9): 4425 MIFNet: Multiple instances focused temporal action proposal generation. Lining WangHongxun YaoHaosen YangSibo WangSheng Jin Neurocomputing 538: 126025 Learning Enriched Hop-Aware Correlation for Robust 3D Human Pose Estimation. Shengping ZhangChenyang WangLiqiang NieHongxun YaoQingming HuangQi Tian Int. J. Comput. Vis. 131(6): 1566-1583 Spatio-Temporal Deformable Attention Network for Video Deblurring. Huicong ZhangHaozhe XieHongxun Yao ECCV 2022 Temporal Action Proposal Generation with Background Constraint. Haosen YangWenhao WuLining WangSheng JinBoyang XiaHongxun YaoHujie Huang AAAI 2022: 3054-3062 Visual Chirality Meets Freehand Sketches. Ying ZhengYiyi ZhangXiaogang XuJun WangHongxun Yao ICIP 2021: 1544-1548 Image editing with varying intensities of processing. Yasi WangYuankai QiHongxun YaoDong GongQi Wu Comput. Vis. Image Underst. 211: 103260 Adaptive Spatio-Temporal Convolutional Network for Video Deblurring. Fengzhi DuanHongxun Yao ICIG (3) 2021: 777-788 3D Reconstruction from Single-View Image Using Feature Selection. Bo WangHongxun Yao ICIG (3) 2021: 143-152 Deep Semantic Parsing of Freehand Sketches With Homogeneous Transformation, Soft-Weighted Loss, and Staged Learning. Ying ZhengHongxun YaoXiaoshuai Sun IEEE Trans. Multim. 23: 3590-3602 Toward 3D object reconstruction from stereo images. Haozhe XieHongxun YaoShangchen ZhouShengping ZhangXiaojun TongWenxiu Sun Neurocomputing 463: 444-453 Sketch-specific data augmentation for freehand sketch recognition. Ying ZhengHongxun YaoXiaoshuai SunShengping ZhangSicheng ZhaoFatih Porikli Neurocomputing 456: 528-539 Unsupervised Discrete Hashing With Affinity Similarity. Sheng JinHongxun YaoQin ZhouYao LiuJianqiang HuangXian-Sheng Hua IEEE Trans. Image Process. 30: 6130-6141 Efficient Regional Memory Network for Video Object Segmentation. Haozhe XieHongxun YaoShangchen ZhouShengping ZhangWenxiu Sun CVPR 2021: 1286-1295 Iterated shape-bias graph cut with application to ellipse segmentation. Xin SunDong LiWei WangHongxun YaoDongliang XuZhanwei DuMingui Sun J. Intell. Fuzzy Syst. 40(1): 53-63 Asynchronous Teacher Guided Bit-wise Hard Mining for Online Hashing. Sheng JinQin ZhouHongxun YaoYao LiuXian-Sheng Hua AAAI 2021: 1717-1724 Object contour tracking via adaptive data-driven kernel. Xin SunWei WangDong LiBin ZouHongxun Yao EURASIP J. Adv. Signal Process. 2020(1): 9 Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images. Haozhe XieHongxun YaoShengping ZhangShangchen ZhouWenxiu Sun Int. J. Comput. Vis. 128(12): 2919-2935 Actionness-pooled Deep-convolutional Descriptor for fine-grained action recognition. Tingting HanHongxun YaoXiaoshuai SunWenlong XieSicheng ZhaoWei Yu Neurocomputing 398: 442-452 TVENet: Temporal variance embedding network for fine-grained action representation. Tingting HanHongxun YaoWenlong XieXiaoshuai SunSicheng ZhaoJun Yu Pattern Recognit. 103: 107267 Conditional GAN based individual and global motion fusion for multiple object tracking in UAV videos. Hongyang YuGuorong LiLi SuBineng ZhongHongxun YaoQingming Huang Pattern Recognit. Lett. 131: 219-226 Discrete Probability Distribution Prediction of Image Emotions with Shared Sparse Learning. Sicheng ZhaoGuiguang DingYue GaoXin ZhaoYoubao TangJungong HanHongxun YaoQingming Huang IEEE Trans. Affect. Comput. 11(4): 574-587 Deep Saliency Hashing for Fine-Grained Retrieval. Sheng JinHongxun YaoXiaoshuai SunShangchen ZhouLei ZhangXian-Sheng Hua IEEE Trans. Image Process. 29: 5336-5351 SSAH: Semi-Supervised Adversarial Deep Hashing with Self-Paced Hard Sample Generation. Sheng JinShangchen ZhouYao LiuChao ChenXiaoshuai SunHongxun YaoXian-Sheng Hua AAAI 2020: 11157-11164 GRNet: Gridding Residual Network for Dense Point Cloud Completion. Haozhe XieHongxun YaoShangchen ZhouJiageng MaoShengping ZhangWenxiu Sun ECCV (9) 2020: 365-381 PRF-Ped: Multi-scale Pedestrian Detector with Prior-based Receptive Field. Yuzhi TanHongxun YaoHaoran LiXiusheng LuHaozhe Xie ICPR 2020: 6059-6064 An Effective Way to Boost Black-Box Adversarial Attack. Xinjie FengHongxun YaoWenbin CheShengping Zhang MMM (1) 2020: 393-404 Focal CTC Loss for Chinese Optical Character Recognition on Unbalanced Datasets. Xinjie FengHongxun YaoShengping Zhang Complex. 2019: 9345861:1-9345861:11 Robust visual tracking via scale-and-state-awareness. Yuankai QiLei QinShengping ZhangQingming HuangHongxun Yao Neurocomputing 329: 75-85 Unsupervised semantic deep hashing. Sheng JinHongxun YaoXiaoshuai SunShangchen Zhou Neurocomputing 351: 19-25 Action recognition with multi-scale trajectory-pooled 3D convolutional descriptors. Xiusheng LuHongxun YaoSicheng ZhaoXiaoshuai SunShengping Zhang Multim. Tools Appl. 78(1): 507-523 Gradual recovery based occluded digit images recognition. Yasi WangHongxun YaoWei YuDong WangShangchen ZhouXiaoshuai Sun Multim. Tools Appl. 78(2): 2571-2586 Handling missing labels and class imbalance challenges simultaneously for facial action unit recognition. Yongqiang LiBaoyuan WuYongping ZhaoHongxun YaoQiang Ji Multim. Tools Appl. 78(14): 20309-20332 Hedging Deep Features for Visual Tracking. Yuankai QiShengping ZhangLei QinQingming HuangHongxun YaoJongwoo LimMing-Hsuan Yang IEEE Trans. Pattern Anal. Mach. Intell. 41(5): 1116-1130 Nighttime image enhancement based on image decomposition. Xuesong JiangHongxun YaoDilin Liu Signal Image Video Process. 13(1): 189-197 An efficient way to refine DenseNet. Xinjie FengHongxun YaoShengping Zhang Signal Image Video Process. 13(5): 959-965 Discovering Latent Discriminative Patterns for Multi-Mode Event Representation. Wenlong XieHongxun YaoXiaoshuai SunTingting HanSicheng ZhaoTat-Seng Chua IEEE Trans. Multim. 21(6): 1425-1436 Learning Descriptors With Cube Loss for View-Based 3-D Object Retrieval. Dong WangHongxun YaoFederico TombariSicheng ZhaoBin WangHong Liu IEEE Trans. Multim. 21(8): 2071-2082 Pix2Vox: Context-Aware 3D Reconstruction From Single and Multi-View Images. Haozhe XieHongxun YaoXiaoshuai SunShangchen ZhouShengping Zhang ICCV 2019: 2690-2698 Adaptive Semantic-Visual Tree for Hierarchical Embeddings. Shuo YangWei YuYing ZhengHongxun YaoTao Mei ACM Multimedia 2019: 2097-2105 Self-balance Motion and Appearance Model for Multi-object Tracking in UAV. Hongyang YuGuorong LiWeigang ZhangHongxun YaoQingming Huang MMAsia 2019: 12:1-12:6 Training samples-optimizing based dictionary learning algorithm for MR sparse superresolution reconstruction. Jun-Bao LiHuan-Yu LiuJeng-Shyang PanHongxun Yao Biomed. Signal Process. Control. 39: 177-184 Hierarchical semantic image matching using CNN feature pyramid. Wei YuXiaoshuai SunKuiyuan YangYong RuiHongxun Yao Comput. Vis. Image Underst. 169: 40-51 Online multiple object tracking via exchanging object context. Hongyang YuLei QinQingming HuangHongxun Yao Neurocomputing 292: 28-37 Rediscover flowers structurally. Cheng PangHongxun YaoXiaoshuai SunSicheng ZhaoWei Yu Multim. Tools Appl. 77(7): 7851-7863 Off-the-shelf CNN features for 3D object retrieval. Dong WangBin WangSicheng ZhaoHongxun YaoHong Liu Multim. Tools Appl. 77(15): 19833-19849 Exploring part-aware segmentation for fine-grained visual categorization. Cheng PangHongxun YaoXiaoshuai SunSicheng ZhaoYanhao Zhang Multim. Tools Appl. 77(23): 30291-30310 Distinctive action sketch for human action recognition. Ying ZhengHongxun YaoXiaoshuai SunSicheng ZhaoFatih Porikli Signal Process. 144: 323-332 Event patches: Mining effective parts for event detection and understanding. Wenlong XieHongxun YaoSicheng ZhaoXiaoshuai SunTingting Han Signal Process. 149: 82-87 Locally aggregated histogram-based descriptors. Xiusheng LuHongxun YaoXin SunYanhao Zhang Signal Image Video Process. 12(2): 323-330 Predicting Personalized Image Emotion Perceptions in Social Networks. Sicheng ZhaoHongxun YaoYue GaoGuiguang DingTat-Seng Chua IEEE Trans. Affect. Comput. 9(4): 526-540 Weighted voxel: a novel voxel representation for 3D reconstruction. Haozhe XieHongxun YaoXiaoshuai SunShangchen ZhouXiaojun Tong ICIMCS 2018: 33:1-33:4 Illustrate your travel notes: web-based story visualization. JunLei ZhangHongxun YaoJiaLing HeXiaoshuai Sun ICIMCS 2018: 44:1-44:5 Cycle-Consistency Based Hierarchical Dense Semantic Correspondence. Chuang LinHongxun YaoWei YuXiaoshuai Sun ICIP 2018: 818-822 Local Image Descriptors with Statistical Losses. Dong WangBin WangHongxun YaoHong LiuFederico Tombari ICIP 2018: 1208-1212 Add: Actionness-Pooled Deep-Convolutional Descriptor. Tingting HanHongxun YaoXiaoshuai SunWenlong XieYanhao Zhang ICME 2018: 1-6 Very High Resolution Image Scene Classification with Semantic Fisher Vectors. Souleyman ChaibYanfeng GuHongxun YaoKhaled Belkadi IGARSS 2018: 6844-6847 ASMMC-MMAC 2018: The Joint Workshop of 4th the Workshop on Affective Social Multimedia Computing and first Multi-Modal Affective Computing of Large-Scale Multimedia Data Workshop. Dong-Yan HuangSicheng ZhaoBj?rn W. SchullerHongxun YaoJianhua TaoMin XuLei XieQingming HuangJie Yang ACM Multimedia 2018: 2120-2121 RS-MSSF Frame: Remote Sensing Image Classification Based on Extraction and Fusion of Multiple Spectral-Spatial Features. Hanane TeffahiHongxun Yao PCM (2) 2018: 582-595 How many zero crossings? A method for structure-texture image decomposition. Xiaolei JiangHongxun YaoShaohui Liu Comput. Graph. 68: 129-141 Exploiting the complementary strengths of multi-layer CNN features for image retrieval. Wei YuKuiyuan YangHongxun YaoXiaoshuai SunPengfei Xu Neurocomputing 237: 235-241 Text image deblurring via two-tone prior. Xiaolei JiangHongxun YaoSicheng Zhao Neurocomputing 242: 1-14 Actor identification via mining representative actions. Wenlong XieHongxun YaoXiaoshuai SunSicheng ZhaoWei YuShengping Zhang Neurocomputing 244: 1-9 View-based 3D object retrieval with discriminative views. Dong WangBin WangSicheng ZhaoHongxun YaoHong Liu Neurocomputing 252: 58-66 Discovering discriminative patches for free-hand sketch analysis. Ying ZhengHongxun YaoSicheng ZhaoYasi Wang Multim. Syst. 23(6): 691-701 Towards more efficient and flexible face image deblurring using robust salient face landmark detection. Yinghao HuangHongxun YaoSicheng ZhaoYanhao Zhang Multim. Tools Appl. 76(1): 123-142 Anomaly detection based on spatio-temporal sparse representation and visual attention analysis. Chen WangHongxun YaoXiaoshuai Sun Multim. Tools Appl. 76(5): 6263-6279 Breaking video into pieces for action recognition. Ying ZhengHongxun YaoXiaoshuai SunXuesong JiangFatih Porikli Multim. Tools Appl. 76(21): 22195-22212 Guest Editorial Introduction to the Special Issue on Group and Crowd Behavior Analysis for Intelligent Multicamera Video Surveillance. Hongxun YaoAndrea CavallaroThierry BouwmansZhengyou Zhang IEEE Trans. Circuits Syst. Video Technol. 27(3): 405-408 Deep Feature Fusion for VHR Remote Sensing Scene Classification. Souleyman ChaibHuan LiuYanfeng GuHongxun Yao IEEE Trans. Geosci. Remote. Sens. 55(8): 4775-4784 Continuous Probability Distribution Prediction of Image Emotions via Multitask Shared Sparse Regression. Sicheng ZhaoHongxun YaoYue GaoRongrong JiGuiguang Ding IEEE Trans. Multim. 19(3): 632-645 Dancelets Mining for Video Recommendation Based on Dance Styles. Tingting HanHongxun YaoChenliang XuXiaoshuai SunYanhao ZhangJason J. Corso IEEE Trans. Multim. 19(4): 712-724 A Biologically Inspired Appearance Model for Robust Visual Tracking. Shengping ZhangXiangyuan LanHongxun YaoHuiyu ZhouDacheng TaoXuelong Li IEEE Trans. Neural Networks Learn. Syst. 28(10): 2357-2370 Online multi-target tracking via depth range segmentation. Hongyang YuLei QinQingming HuangHongxun YaoLiang Li GlobalSIP 2017: 691-695 Non-rigid Object Tracking via Deformable Patches Using Shape-Preserved KCF and Level Sets. Xin SunNgai-Man CheungHongxun YaoYiluan Guo ICCV 2017: 5496-5504 Gated additive skip context connection for object detection. Haoran LiHongxun YaoYuxin HouXiaoshuai Sun ICIP 2017: 680-684 Dancing like a superstar: Action guidance based on pose estimation and conditional pose alignment. Yuxin HouHongxun YaoHaoran LiXiaoshuai Sun ICIP 2017: 1312-1316 The shortest matching path based on novel cycle consistency. Wei YuYi TaoHongxun Yao ICIP 2017: 1975-1979 Part-based fine-grained bird image retrieval respecting species correlation. Cheng PangHongdong LiAnoop CherianHongxun Yao ICIP 2017: 2896-2900 Object Discovery and Cosegmentation Based on Dense Correspondences. Yasi WangHongxun YaoWei YuXiaoshuai Sun PCM (2) 2017: 119-128 Trajectory-Pooled 3D Convolutional Descriptors for Action Recognition. Xiusheng LuHongxun YaoXiaoshuai SunShengping ZhangYanhao Zhang PCM (1) 2017: 247-257 Multi-level Semantic Representation for Flower Classification. Chuang LinHongxun YaoWei YuWenbo Tang PCM (1) 2017: 325-335 Image Decomposition Based Nighttime Image Enhancement. Xuesong JiangHongxun YaoDilin Liu PCM (2) 2017: 683-692 Shallow and Deep Model Investigation for Distinguishing Corn and Weeds. Yu XiaHongxun YaoXiaoshuai SunYanhao Zhang PCM (1) 2017: 693-702 Multi-scale Discriminative Patches for Fined-Grained Visual Categorization. Wenbo TangHongxun YaoXiaoshuai SunWei Yu PCM (1) 2017: 712-721 Style Transfer with Content Preservation from Multiple Images. Dilin LiuWei YuHongxun Yao PCM (1) 2017: 783-791 Sketch Based Model-Like Standing Style Recommendation. Ying ZhengHongxun YaoDong Wang PCM (1) 2017: 825-833 Multi-modal Emotion Recognition Based on Speech and Image. Yongqiang LiQi HeYongping ZhaoHongxun Yao PCM (1) 2017: 844-853 Unsupervised discovery of crowd activities by saliency-based clustering. Tingting HanHongxun YaoXiaoshuai SunSicheng ZhaoYanhao Zhang Neurocomputing 171: 347-361 Auto-encoder based dimensionality reduction. Yasi WangHongxun YaoSicheng Zhao Neurocomputing 184: 232-242 An Informative Feature Selection Method Based on Sparse PCA for VHR Scene Classification. Souleyman ChaibYanfeng GuHongxun Yao IEEE Geosci. Remote. Sens. Lett. 13(2): 147-151 Multi-modal microblog classification via multi-task learning. Sicheng ZhaoHongxun YaoSendong ZhaoXuesong JiangXiaolei Jiang Multim. Tools Appl. 75(15): 8921-8938 Facial action unit recognition under incomplete data based on multi-label learning with missing labels. Yongqiang LiBaoyuan WuBernard GhanemYongping ZhaoHongxun YaoQiang Ji Pattern Recognit. 60: 890-900 User-Centric Affective Computing of Image Emotion Perceptions. Sicheng ZhaoHongxun YaoWenlong XieXiaolei Jiang AAAI 2016: 4284-4285 Affective Computing and Applications of Image Emotion Perceptions. Sicheng ZhaoHongxun Yao AAAI 2016: 4321-4323 Hedged Deep Tracking. Yuankai QiShengping ZhangLei QinHongxun YaoQingming HuangJongwoo LimMing-Hsuan Yang CVPR 2016: 4303-4311 Mining representative actions for actor identification. Wenlong XieHongxun YaoXiaoshuai SunSicheng ZhaoTingting HanCheng Pang ICASSP 2016: 1253-1257 Tree-guided Group Sparse based Representation for Person Re-identification. Shangchen ZhouHongxun YaoWei YuYasi Wang ICIMCS 2016: 14-17 Crowd video retrieval via deep attribute-embedding graph ranking. Yanhao ZhangLei QinSicheng ZhaoRongrong JiXiusheng LuHongxun YaoQingming Huang ICME 2016: 1-6 A VHR scene classification method integrating sparse PCA and saliency computing. Souleyman ChaibYanfeng GuHongxun YaoSicheng Zhao IGARSS 2016: 2742-2745 From Seed Discovery to Deep Reconstruction: Predicting Saliency in Crowd via Deep Networks. Yanhao ZhangLei QinQingming HuangKuiyuan YangJun ZhangHongxun Yao ACM Multimedia 2016: 72-76 Predicting Personalized Emotion Perceptions of Social Images. Sicheng ZhaoHongxun YaoYue GaoRongrong JiWenlong XieXiaolei JiangTat-Seng Chua ACM Multimedia 2016: 1385-1394 Exploring Discriminative Views for 3D Object Retrieval. Dong WangBin WangSicheng ZhaoHongxun YaoHong Liu MMM (1) 2016: 755-766 Strategy for aesthetic photography recommendation via collaborative composition model. Yanhao ZhangQingming HuangLei QinSicheng ZhaoXiusheng LuXiaoshuai SunHongxun Yao IET Comput. Vis. 9(5): 691-698 Strategy for dynamic 3D depth data matching towards robust action retrieval. Sicheng ZhaoLujun ChenHongxun YaoYanhao ZhangXiaoshuai Sun Neurocomputing 151: 533-543 深度学习中的自编码器的表达能力研究 (Representation Ability Research of Auto-encoders in Deep Learning). Yasi WangHongxun YaoXiaoshuai SunPengfei XuSicheng Zhao 计算机科学 42(9): 56-60 Adaptive NormalHedge for robust visual tracking. Shengping ZhangHuiyu ZhouHongxun YaoYanhao ZhangKuanquan WangJun Zhang Signal Process. 110: 132-142 View-based 3D object retrieval via multi-modal graph learning. Sicheng ZhaoHongxun YaoYanhao ZhangYasi WangShaohui Liu Signal Process. 112: 110-118 Social Attribute-Aware Force Model: Exploiting Richness of Interaction for Abnormal Crowd Detection. Yanhao ZhangLei QinRongrong JiHongxun YaoQingming Huang IEEE Trans. Circuits Syst. Video Technol. 25(7): 1231-1245 Non-Rigid Object Contour Tracking via a Novel Supervised Level Set Model. Xin SunHongxun YaoShengping ZhangDong Li IEEE Trans. Image Process. 24(11): 3386-3399 Learning Cross Space Mapping via DNN Using Large Scale Click-Through Logs. Wei YuKuiyuan YangYalong BaiHongxun YaoYong Rui IEEE Trans. Multim. 17(11): 2000-2007 Learning a discriminative dictionary for facial expression recognition. Yongqiang LiYongping ZhaoHongxun YaoQiang Ji ACII 2015: 838-844 Dual-mode video stabilization based on adaptive motion clustering. Dong WangBin WangSicheng ZhaoXiaoshuai SunHongxun YaoHong Liu ICIMCS 2015: 6:1-6:4 Boost sparse coding based abnormal event detection via explicitly applying temporal continuity constraint. Yinghao HuangHongxun YaoXiaoshuai SunSicheng Zhao ICIMCS 2015: 29:1-29:4 Why does the sketch look so vivid. Ying ZhengHongxun YaoSicheng ZhaoYasi Wang ICIMCS 2015: 37:1-37:4 Dimensionality reduction strategy based on auto-encoder. Yasi WangHongxun YaoSicheng ZhaoYing Zheng ICIMCS 2015: 63:1-63:4 Distinctive action sketch. Ying ZhengHongxun YaoXiaoshuai SunSicheng Zhao ICIP 2015: 576-580 Histograms of locally aggregated oriented gradients. Xiusheng LuShengping ZhangHongxun YaoXin SunYanhao Zhang ICIP 2015: 1270-1274 Predicting discrete probability distribution of image emotions. Sicheng ZhaoHongxun YaoXiaolei JiangXiaoshuai Sun ICIP 2015: 2459-2463 Formation Period Matters: Towards Socially Consistent Group Detection via Dense Subgraph Seeking. Yanhao ZhangLei QinShengping ZhangHongxun YaoQingming Huang ICMR 2015: 475-478 Predicting Continuous Probability Distribution of Image Emotions in Valence-Arousal Space. Sicheng ZhaoHongxun YaoXiaolei Jiang ACM Multimedia 2015: 879-882 Clustering of Dancelets: Towards Video Recommendation Based on Dance Styles. Tingting HanHongxun YaoXiaoshuai SunYanhao ZhangSicheng ZhaoXiusheng LuYinghao HuangWenlong Xie ACM Multimedia 2015: 915-918 Efficient Face Image Deblurring via Robust Face Salient Landmark Detection. Yinghao HuangHongxun YaoSicheng ZhaoYanhao Zhang PCM (1) 2015: 13-22 Blur Detection Using Multi-method Fusion. Yinghao HuangHongxun YaoSicheng Zhao PCM (1) 2015: 383-392 Part-Aware Segmentation for Fine-Grained Categorization. Cheng PangHongxun YaoZhiyuan YangXiaoshuai SunSicheng ZhaoYanhao Zhang PCM (1) 2015: 538-548