Workshops
Monday, July 8, 2019
Monday, July 8, 2019
W-01: Multimedia Services and Technologies for Smart-health(MUST-SH)
Time: 8:30 AM - 17:00 PM
Room: 5F
Organizers: Shamim Hossain King Saud University, Saudi Arabia Stefan Goebel KOM, TU Darmstadt, Germany
Yin Zhang Zhongnan University of Economics and Law, China
8:30 - 8:35 Opening Remarks:
Yin Zhang Zhongnan University of Economics and Law, China
8:35 - 9:30 Keynote Talk:
Huimin Lu Kyushu Institute of Technology, Japan
9:30 - 10:00 Oral Session 1:
Session Chair: Shamim Hossain King Saud University, Saudi Arabia
FULLY CONVOLUTIONAL NETWORK FOR 3D HUMAN SKELETON ESTIMATION FROM A SIN- GLE VIEW FOR ACTION ANALYSIS
Wen-Nung Lie1, Guan-Han Lin1, Lung-Sheng Shih1, YuLing Hsu1, Thang Huu Nguyen2, Quynh Nguyen Quang Nhu2
1National Chung Cheng University, Taiwan, 2The University of Danang, University of Science and Technology, Vietnam
10:00 - 10:30 Coffee Break
10:30 - 12:00 Oral Session 2:
Session Chair: Stefan Goebel KOM, TU Darmstadt, Germany
10:30 - 11:00
ATTENTION BASED SEMI-SUPERVISED DICTIONARY LEARNING FOR DIAGNOSIS OF AU- TISM SPECTRUM DISORDERS
Meng Yang1,2, Qin Zhong1, Lin Chen3, Fanglin Huang4, Baiying Lei4
1Sun Yat-sen University, Guangzhou, China, 2Key Laboratory of Machine Intelligence and Advanced Comput- ing(SYSU), Ministry of Education, 3Sogou, China, 4Shenzhen University, China
11:00 - 11:30
RT-ADI: FAST REAL-TIME VIDEO REPRESENTATION FOR MULTI-VIEW HUMAN FALL DETEC- TION
Qianggang Ding, Fan Yang, Jiawei Li, Sifan Wu, Bowen Zhao, Zhi Wang, Shutao Xia
Tsinghua University, China
11:30 - 12:00
A NEW IMAGE WATERMARKING SCHEME FOR EFFICIENT TAMPER DETECTION, LOCALIZA- TION AND RECOVERY
Faranak Tohidi, Manoranjan Paul
Charles Sturt University, Australia
12:00 - 13:30 Lunch Break
13:30 - 15:00 Oral Session 3:
Session Chair: Yin Zhang Zhongnan University of Economics and Law, China
13:30 - 14:00
PREDICTING HUMAN GRASP LOCATIONS ON CUP HANDLES BY USING DEEP NEURAL NET- WORKS TO INFER HEAT SIGNATURES FROM DEPTH DATA
Yijun Jiang, Sean Banerjee, Natasha Kholgade Banerjee
Clarkson University, USA
14:00 - 14:30
HIERARCHICAL FUZZY INFERENCE SYSTEM FOR DIAGNOSING DENGUE DISEASE
Mubarak Alrashoud
King Saud University, Saudi Arabia
14:30 - 15:00
HUMAN-INTERACTION WEAKLY-SUPERVISED DEEP NETWORKS FOR SEMANTIC SEGMEN- TATION
Wenfeng Luo1, Meng Yang1,2
1Sun Yat-sen University, China, 2Key Laboratory of Machine Intelligence and Advanced Computing (SYSU), Ministry of Educationl, China
15:00 - 15:30 Coffee Break
15:30 - 17:00 Oral Session 4:
Session Chair: Shamim Hossain King Saud University, Saudi Arabia
15:30 - 16:15
THE PREDICTION MODEL OF BLOOD GLUCOSE CONCENTRATION FOR SMART HEALTH
Han Yu, Jianmin Lu, Yue JIn, Binglei Yue, Xiao Ma Zhongnan University of Economics and Law, China 16:15 - 17:00
PREDICTING SPINE SURGERY COMPLICATIONS USING MACHINE LEARNING
Mohamad Hoda1, Abdulmotaleb EI Saddik1, Eugene Wai2, Philippe Phan3
1University of Ottawa, Canada, 2The Ottawa Hospital, Canada, 3The Ottawa Hospital, Canada
W-02: International Joint Workshop on Multimedia Artworks Analysis and Attractiveness Computing in Multimedia (MMArt-ACM)
Time: 8:30 AM - 12:00 PM
Room: 5H
Organizers: Wei-Ta Chu National Chung Cheng University, Taiwan
Norimichi Tsumura Graduate School of Engineering, Chiba University, Japan Shoji Yamamoto Tokyo Metropolitan College of Industrial Technology, Japan Toshihiko Yamasaki University of Tokyo, Japan
8:30 - 8:35 Opening Remarks:
Session Chair: Toshihiko Yamasaki
8:35 - 9:50 Oral Session 1: Multimedia Artworks Analysis
Session Chair: Norimichi Tsumura, Toshihiko Yamasaki
8:35 - 8:50
DEEPIR: A DEEP SEMANTICS DRIVEN FRAMEWORK FOR IMAGE RETARGETING
Jianxin Lin, Tiankuang Zhou, Zhibo Chen
University of Science and Technology of China, China
8:50 - 9:05
MULTI-DEPTH DILATED NETWORK FOR FASHION LANDMARK DETECTION
Zeng Kai, Jun Feng, Richard F E Sutcliffe, Wang Xiaoyu, Bu Qirong
NorthWest University, China
9:05 - 9:20
SALIENCY-GUIDED IMAGE STYLE TRANSFER
Xiuwen Liu, Zhi Liu, Xiaofei Zhou, Minyu Chen
Shanghai University, China
9:20 - 9:35
A MULTIMEDIA-BASED MOVIE STYLE MODEL
Priyankar Choudhary, Neeraj Goel, Mukesh Saini
Indian Institute of Technology Ropa, India
9:35 - 9:50
NEURAL STYLE TRANSFER WITH CONTENT DISCRIMINATION
Xiyu Yan, Yeli Xing, Zihao He, Tao Dai, Yong Jiang, Shutao Xia
Tsinghua University, China
10:00 - 10:30 Coffee Break
10:30 - 11:30 Keynote talk by Prof. Jia Jia
Session Chair: Toshihiko Yamasaki
11:30 - 12:00 Oral Session 2: Attractiveness Computing in Multimedia
Session Chair: Wei-Ta Chu
11:30 - 11:45
PREDICTING THE ATTRACTIVENESS OF REAL-ESTATE IMAGES BY PAIRWISE COMPARISON USING DEEP LEARNING
Xueting Wang, Yuki Takada, Youiti Kado, Toshihiko Yamasaki
The University of Tokyo, Japan
11:45 - 12:00
VIDEO-BASED STRESS LEVEL MEASUREMENT USING IMAGING PHOTOPLETHYSMOGRA- PHY
Ryota Mitsuhashi1, Kaito Iuchi1, Takashi Goto2, Akira Matsubara2, Takahiro Hirayama2, Hideki Hashizume2, Norimichi Tsumura1
1Chiba University, Japan, 2Daikin Industries LTD, Japan
W-03: Visual Emotion Analysis: Theories and Applications
Time: 13:30 - 17:30 PM
Room: 5H
Organizers: Lifang Wu Beijing University of Technology, China Jufeng Yang Nankai University, China
Rongrong Ji Xiamen University, China
13:30 - 13:35 Opening Remarks
13:35 - 14:30 Keynote: Computation of Emotion (Jiebo Luo)
14:30 - 15:00 Invited Talk 1: Affective and aesthetic computing on social images (Jia Jia)
15:00 - 15:30 Coffee Break
15:30 - 16:00 Invited Talk 2: Visual sentiment analysis and beyond (Yanwei Fu)
16:00 - 16:30 Invited Talk 3: Weakly supervised coupled networks for visual sentiment analysis (Dongyu She) 16:30 -16:50
FEAFA: A WELL ANOATED DATABASE FOR FACIAL EXPRESSION ANALYSIS AND 3D FACIAL ANIMATION
Yanfu Yan1, Ke Lu1, Jian Xue1, Pengcheng Gao1, Jiayi Lyu2
1University of Chinese Academy of Sciences, China 2Capital Normal University, China
16:50 - 17:10
CROSS-DATABASE MICRO-EXPRESSION RECOGNITION: A STYLE AGGREGATED AND AT- TENTION TRANSFER APPROACH
Ling Zhou, Qirong Mao, Luoyang Xue
Jiangsu University, China
17:10 -17:30
THE FUSION KNOWLEDGE OF FACE, BODY AND CONTEXT FOR EMOTION RECOGNITION
Jingjing Wu, Yong Zhang, Li Ning
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, China
W-04: 1st International Workshop on Big Surveillance Data Analysis and Pro- cessing
Time: 8:30 AM - 12:00 PM
Room: 5I
Organizers: Weiyao Lin Shanghai Jiao Tong University, China John See Multimedia University, Malaysia
Michael Ying Yang University of Twente, the Netherlands
8:30 - 10:00 Oral Session 1: Object Motion Analysis in Big Surveillance Videos
Session Chair: Weiyao Lin, Michael Ying Yang
8:30 - 8:45
DEFORMATION SAMPLE GENERATED NETWORK FOR ROBUST VISUAL TRACKING
Zizi Li, Yuan Zhou, Chunping Hou
Tianjin University, China
8:45 - 9:00
PRESERVING STRUCTURAL RELATIONSHIPS FOR PERSON RE-IDENTIFICATION
Liqiang Bao1, Bingpeng Ma1, Hong Chang2, Xilin Chen2
1University of Chinese Academy of Sciences, China 2Chinese Academy of Sciences, China
9:00 - 9:15
ADAPTIVE UPDATING SIAMESE NETWORK WITH LIKE-HOOD ESTIMATION FOR SURVEIL- LANCE VIDEO OBJECT TRACKING
Zhenxian Zheng, Yang Yi, Jinlong Shen, Jiahao Zhang
Sun Yat-sen University, China
9:15 - 9:30
A MULTIMODAL LOSSLESS CODING METHOD FOR SKELETONS IN VIDEOS
Xiaoyi He, Mingzhou Liu, Weiyao Lin, Xintong Han, Yanmin Zhu, Hongtao Lu, Hongkai Xiong
Shanghai Jiao Tong University, China
9:30 - 9:45
EFFICIENT SEMANTIC-BASED VEHICLE RETRIEVAL IN LONG-TERM CAR PARK VIDEOS
Clarence Weihan Cheong, Ryan Woei-Sheng Lim, John See, Lai-Kuan Wong, Ian Kim Teck Tan
Multimedia University, Malaysia
9:45 - 10:00
SINGLE IMAGE HAZE REMOVAL BY FEATURE MAPPING
Feiniu Yuan1, Yu Zhou2, Xue Xia2, Ya Li2
1Shanghai Normal University, China, 2Jiangxi University of Finance and Economics, China
10:00 - 10:30 Coffee Break
10:30 - 12:00 Oral Session 2: Human & Action Sensing for Big Surveillance Videos
Session Chair: Weiyao Lin, Michael Ying Yang
10:30 - 10:45
MOTION-LET CLUSTERING FOR SKELETON-BASED ACTION RECOGNITION
Jianyu Yang1, Chen Zhu1, Junsong Yuan2
1Soochow University, China, 2State University of New York at Buffalo, USA
10:45 - 11:00
DEEP KEY CLIPS-VIDEO FEATURE FUSION FRAMEWORK FOR ACTION RECOGNITION
Chao Li1, Yue Ming1, Yuan Shen2, Hui Yu3
1Beijing University of Posts and Telecommunications, China 2Tencent Technology (Beijing) Co., Ltd, China
3University of Portsmouth, UK
11:00 - 11:15
HUMAN IDENTIFICATION RECOGNITION IN SURVEILLANCE VIDEOS
Kai Jin, Xuemei Xie, Fangyu Wang, Xiao Han, Guangming Shi
Xidian University, China
11:15 - 11:30
AGE ESTIMATION FOR LOW-QUALITY FACIAL IMAGES: FROM SEPARATE DCNNS TO A DE- CISION FUSER
Kuan-Hsien Liu1, Pak Ki Chan2, Tsung-Jung Liu3, Hsiu-An Her1
1National Taichung University of Science and Technology, Taiwan, 2China Medical University Hospital,China
3National Chung Hsing University, Taiwan
11:30 - 11:45
SEMANTIC SEGMENTATION OF SATELLITE IMAGES USING A U-SHAPED FULLY CONNECT- ED NETWORK WITH DENSE RESIDUAL BLOCKS
Eric R Narciso Molina, Zenghui Zhang Shanghai Jiao Tong University, China 11:45 - 12:00
MTCNN WITH WEIGHTED LOSS PENALTY AND ADAPTIVE THRESHOLD LEARNING FOR FA- CIAL ATTRIBUTE PREDICTION
Xingting He, Pingyu Wang, Zhicheng Zhao, Yanyun Zhao, Fei Su
Beijing University of Posts and Telecommunications, China
W-05: Multimedia for Robot, Unmanned Aerial Vehicle and Driverless Car
Time: 13:30 - 17:00 PM
Room: 5I
Organizers: Dong Zhao Beijing University of Posts and Telecommunications, China Chenqiang Gao Chongqing University of Posts and Telecommunications, China Jiayi Ma Wuhan University, China
Quan Zhou Nanjing University of Posts and Telecommunications, China Ji Zhao TuSimple, China
Yu Zhou Beijing University of Posts and Telecommunications, China
13:30 - 13:35 Opening Remarks:
Yu Zhou Huazhong University of Science and Technology, China
13:35 - 14:10 Keynote Talk:
Yiqun Li Huazhong University of Science and Technology, China
14:10 - 14:45 Keynote Talk:
Chen Chen University of North Carolina at Charlotte, USA
14:45 - 15:05 Oral Session 1:
Session Chair: Dong Zhao
14:45 -15:05
MULTI-PATH FUSION NETWORK FOR HIGH-RESOLUTION HEIGHT ESTIMATION FROM A SINGLE ORTHOPHOTO
Yiteng Zhang, Xuejin Chen
University of Science and Technology of China, China
15:05 - 15:25 Coffee Break
15:25 - 16:00 Keynote Talk:
Lin Zhang Tongji University, China
16:00 - 17:00 Oral Session 2:
Session Chair：Jiayi Ma
16:00 - 16:20
FACE ANTI-SPOOFING BASED ON MULTI-LAYER DOMAIN ADAPTATION
Fengshun Zhou1,2, Chenqiang Gao1,2, Fang Chen1,2, Chaoyu Li1,2, Xindou L1,2, Feng Yang1,2, Yue Zhao1,2
1Chongqing University of Posts and Telecommunications, Chongqing, China, 2Chongqing Key Laboratory of Signal and Information Processing, Chongqing 400065, China
16:20 - 16:40
SELF-ATTENTION RELATION NETWORK FOR FEW-SHOT LEARNING
Binyuan Hui, Pengfei Zhu, Qinghua Hu, Qilong Wang
Tianjin University, China
16:40 - 17:00
BISE-RESNET: COMBINE SEGMENTATION AND CLASSIFICATION NETWORKS FOR ROAD FOLLOWING ON UNMANNED AERIAL VEHICLE
Dian Lyu, Peng Cheng, Ruizhou Liu, Liang Liu
Beijing University of Posts and Telecommunication, China
W-06: Information Theory and Multimedia Computing (ITMC)
Time: 8:30 AM - 16:30 PM
Room: 5J
Organizers: Ran He Chinese Academy of Sciences, China Xiaotong Yuan Nanjing University, China Jitao Sang Beijing Jiaotong University, China
8:50 - 9:00 Opening
9:00 - 10:00 Keynote Talk: Ran He
10:00 - 10:15 Coffee Break
10:15 - 11:45 Oral Session 1:
Session Chair: Ran He
10:15 – 10:30
HYBRID DEFENSE FOR DEEP NEURAL NETWORKS: AN INTEGRATION OF DETECTING AND CLEANING ADVERSARIAL PERTURBATIONS
Weiqi Fan, Guangling Sun, Yuying Su, Zhi Liu, Xiaofeng Lu
Shanghai University, China
10:30 – 10:45
SKETCH-BASED IMAGE RETRIEVAL VIA A SEMI-HETEROGENEOUS CROSS-DOMAIN NET- WORK
Chuo Li, Yuan Zhou, Jianxing Yang Tianjin University, Tianjin, China 10:45 – 11:00
QUESTION SPLITTING AND UNBALANCED MULTI-MODAL POOLING FOR VQA
Mengfei Li, Huan Shao, Yi Ji, Yang Yang, ChunPing Liu
Soochow University Suzhou, Jiangsu, China
11:00 – 11:15
AI-GAN: SIGNAL DE-INTERFERENCE VIA ASYNCHRONOUS INTERACTIVE GENERATIVE AD- VERSARIAL NETWORK
Xin Jin, Zhibo Chen, Jianxin Lin, Wei Zhou, Jiale Chen, Chaowei Shan
University of Science and Technology of China, Hefei, China
11:15 – 11:30
Visual object tracking via Graph Convolutional Representation
Zhengzheng Tu, Ajian Zhou, Bo Jiang, Bin Luo
Anhui University, China
11:30 – 11:45
MOIRE PATTERN REMOVAL WITH MULTI-SCALE FEATURE ENHANCING NETWORK
Tian yu Gao1, Yanqing Guo1, Xin Zheng1, Qianyu Wang1, Xiangyang Luo2
1Dalian University of Technology, China 2The State Key Laboratory of Mathematical Engineering and Advanced Computing, China
12:00 - 13:30 Lunch Break
13:30 - 15:00 Oral Session 2:
Session Chair: Yi Li
13:30 – 13:45
DEEP COLOR IMAGE DEMOSAICKING WITH FEATURE PYRAMID CHANNEL ATTENTION.
Qi Kang, Ying Fu, Hua Huang Beijing Institute of Technology, China 13:45 – 14:00
REAL-WORLD IMAGE DENOISING VIA WEIGHTED LOW RANK APPROXIMATION.
Yuenan Guo, Ying Fu, Hua Huang Beijing Institute of Technology, China 14:00 – 14:15
TWO-STRE SPARSE NETWORK FOR ACCURATE IMAGE SUPER-RESOLUTION.
Ling Hu1,2, Shuhui Wang1, Liang Li1, Qingming Huang1,2
1Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS, China, 2University of Chinese Academy of Sci- ences, Beijing, 100049, China
14:15 – 14:30
EMBEDDING NON-LOCAL MEAN IN SQUEEZE-AND-EXCITATION NETWORK FOR SINGLE IMAGE DERAINING.
Cong Wang, Hongyan Wang, Zhixun Su, Yan Yang
Dalian University of Technology, China
14:30 – 14:45
RELATIVE DEPTH ESTIMATION PRIOR FOR SINGLE IMAGE DEHAZING.
Jinbao Wang1, Ke Lu1, Jian Xue1, Yutong Kou2
1University of Chinese Academy of Sciences, China 2Huazhong University of Science & Technology, China
14:45 – 15:00
LOW-LIGHT IMAGE ENHANCEMENT WITH ATTENTION AND MULTI-LEVEL FEATURE FU- SION.
Lei Wang1, guangtao fu2, zhuqing jiang1, Guodong Ju3, aidong men1
1Beijing University of Posts and Telecommunications, China, 2Academy of Broadcasting Science, China,
3GuangDong TUS-TuWei Technology Co, Ltd, China
15:00 - 15:30 Coffee Break
15:30 - 16:30 Oral Session 3:
Session Chair: Yi Li
15:30 – 15:45
BLIND MESH QUALITY ASSESSMENT METHOD BASED ON CONCAVE, CONVEX AND STRUC- TURAL FEATURES ANALYSES.
Yaoyao Lin, Mei Yu, Ken Chen, Gangyi Jiang, Zongju Peng, Fen Chen
Faculty of Information Science and Engineering, Ningbo University, Ningbo, China
15:45 – 16:00
K-COVERS FOR ACTIVE LEARNING IN IMAGE CLASSIFICATION.
Yeji Shen1, Yuhang Song1, Hanhan Li2, Shahab Kamali2, Bin Wang1, C.-C. Jay Kuo1
1University of Southern California, USA, 2Google Research, USA
16:00 – 16:15
DISTRIBUTION DISCREPANCY MAXIMIZATION FOR IMAGE PRIVACY PRESERVING.
Sen Liu, Jianxin Lin, Zhibo Chen
University of Science and Technology of China, China
16:15 – 16:30
A NOVEL DISTANCE LEARNING FOR ELASTIC CROSS MODAL AUDIO-VISUAL MATCHING.
Rui Wang1, Huaibo Huang2,3, Xufeng Zhang1, Jixin Ma4, Aihua Zheng1
1Anhui University, China, 2University of Chinese Academy of Sciences, China, 3CASIA, China, 4University of Greenwich, UK
W-07: 6th IEEE International Workshop on Mobile Multimedia Computing (MMC)
Time: 8:30 AM - 12:00 PM
Room: 5F
Organizers: Tian Gan Shandong University, China
Wen-Huang Cheng National Chiao Tung University, Taiwan
Kai-Lung Hua National Taiwan University of Science and Technology, Taiwan
Klaus Schoeffmann Klagenfurt University, Austria
Vladan Velisavljevic University of Bedfordshire, UK
Christian von der Weth National University of Singapore, Singapore
8:30 - 9:00 Opening & Keynotes
9:00 - 10:00 Oral Session 1:
Session Chair: Wen-Huang Cheng
9:00 - 09:15
FINE DETECTION AND CLASSIFICATION OF MULTI-CLASS BARCODE IN COMPLEX ENVI- RONMENTS
Jiahe Zhang1, Jun Jia1, Zehao Zhu1, Xiongkuo Min1, Guangtao Zhai1, Xiao-Ping Zhang2
1Shanghai Jiao Tong University, China, 2Ryerson University, Canada
9:15 - 09:30
DEEP LEARNING BASED METHOD FOR PRUNING DEEP NEURAL NETWORKS
Lianqiang Li1, Jie Zhu1, Ming-Ting Sun2
Shanghai Jiao Tong University, China, 2University of Washington, USA
9:30 - 09:45
ALPS 1.0: Towards Automated Lecture Profiling System
Pratibha Kumari1, Prakhar Jain1, Swarna Sahay1, Gan Tian2, Mukesh Saini1 1Indian Institute of Technology Ropar, India, 2Shandong University, China 9:45 - 10:00
VAS360: QOE-DRIVEN VIEWPORT ADAPTIVE STREAMING FOR 360 VIDEO
Yuxiang Hu, Yu Liu, Yumei wang
Beijing University Posts and Telecommunications, China
10:00 - 10:30 Coffee Break
10:30 - 11:30 Oral Session 2:
Session Chair: Tian Gan
10:30 - 10:45
FUSING GEOGRAPHIC INFORMATION INTO LATENT FACTOR MODEL FOR PICK-UP REGION RECOMMENDATION
Zhuhua Liao, Jian Zhang, Yizhi Liu
Hunan University of Science & Technology, China
10:45 - 11:00
A FLEXIBLE VIEWPORT-ADAPTIVE PROCESSING MECHANISM FOR REAL-TIME VR VIDEO TRANSMISSION
Anyue Xu, Xinyu Chen, Yu Liu, Yumei Wang
Beijing University Posts and Telecommunications, China
11:00 - 11:15
OBJECTIVE QUALITY ASSESSMENT METHOD FOR STEREOSCOPIC IMAGE RETARGETING
Salah Addin Mohammed M Mohammed, Ya Zhou, Zhibo Chen, Houqiang Li
University of Science and Technology of China, China
11:15 - 11:30
OPTIMAL MULTI-CODEC ADAPTIVE BITRATE STREAMING
Yuriy Reznik, Xinagbo Li, Karl Lillevold, Abhijith Jagannath, Justin Greer
Brightcove Inc. USA
11:30 - 12:00
Best Paper Award Announcement
W-08: Time-sequenced Multimedia Computing
Time: 13:30 - 17:45 PM
Room: 5F
Organizers: Wei Li Fudan University, China
Mengyao Zhu Shanghai University, China
Bing-Kun Bao Nanjing University of Posts and Telecommunications, Nanjing, China Min Xu University of Technology Sydney, Australia
Xi Shao Nanjing University of Posts and Telecommunications, Nanjing, China
13:30 - 13:55
AUDIO SCENE CLASSIFICATION WITH DISCRIMINATIVELY-TRAINED SEGMENT-LEVEL FEA- TURES
Haichuan Bai1,2, Hangting Chen1,2, Yonghong Yan1,2
1Chinese Academy of Sciences, China, 2University of Chinese Academy of Sciences, China
13:55 - 14:20
EFFICIENT IMPLICIT FOURIER COMPRESSION BASED CONVOLUTIONAL FEATURES FOR VISUAL TRACKING
Ridong Zhu, Xiaoyuan Yang, Jingkai Wang, Zhengze Li
Beihang University, China
14:20 - 14:45
AUDIO2FACE: GENERATING SPEECH/FACE ANIMATION FROM SINGLE AUDIO WITH ATTEN- TION-BASED BIDIRECTIONAL LSTM NETWORKS
Guanzhong Tian1, Yi Yuan2, Yong Liu1
1Zhejiang University, China, 2Fuxi AI Lab, Netease, China
14:45 - 15:10
DEEP VOCODER: LOW BIT RATE COMPRESSION OF SPEECH WITH DEEP AUTOENCODER
Gang Min1, Changqing Zhang 1, Xiongwei Zhang 2, Wei Tan1
1National University of Defense Technology, China 2Army Engineering University of PLA, China
15:10 - 15:30 Coffee Break
15:30 - 15:55
BLIND ESTIMATION OF REVERBERATION TIME USING BINAURAL COMPLEX IDEAL RATIO MASK
MingYang Chai1, TianTian Li1, MengYao Zhu1, Tao Wang1, Wen Zhang2
1Shanghai University, China, 2Northwestern Polytechnical University, China
15:55 - 16:20
OPV: BIAS CORRECTION BASED OPTIMAL PROBABILISTIC VIEWPORT-ADAPTIVE STREAMING FOR 360-DEGREE VIDEO
Weihong Lin, Xinggong Zhang, Zongming Guo, Wei Hu
Peking University, China
16:20 - 16:45
SVD-BASED CHANNEL PRUNING FOR CONVOLUTIONAL NEURAL NETWORK IN ACOUSTIC SCENE CLASSIFICATION MODEL
Jun Wang1, Shengchen Li1, Wenwu Wang2
1Beijing University of Posts and Telecommunications, China, 2University of Surrey, UK
16:45 - 17:10
MULTI-LEVEL ATTENTION MODEL WITH DEEP SCATTERING SPECTRUM FOR ACOUSTIC SCENE CLASSIFICATION
Zhitong Li1, Yuanbo Hou2, Xiang Xie1,3, Shengchen Li2, Liqiang Zhang1, Shixuan Du1, Wei Liu1
1Beijing Institute of Technology, China, 2Beijing University of Posts and Telecommunications, China, 3Beijing
Institute of Technology, China
17:10 - 17:45
A MULTI-CRITERIA SUBJECTIVE EVALUATION METHOD FOR BINAURAL AUDIO RENDERING TECHNIQUES IN VIRTUAL REALITY APPLICATIONS
Zhaoyu Yan, Jing Wang, Zhuoran Li
Beijing Institute of Technology, China
W-09: Smart Camera（Gigavision）
Time: 8:30 AM - 12:00 PM
Room: 5I
Organizers: Lu Fang Associate Professor, Tsinghua-Berkeley Shenzhen Institute, China David J. Brady Duke University, USA
Shenghua Gao Assistant Professor, ShanghaiTech University, China Yuchen Guo Tsinghua University, China
8:30 - 8:35 Opening Remarks:
Lu Fang Tsinghua University, China
8:35 - 9:15 Plenary Talk:
David J. Brady Duke University, USA
9:15 - 9:40 Keynote Talk:
Lu Fang Tsinghua University, China
9:40 - 10:05 Oral Session 1:
Session Chair: Lu Fang
SCALE-ADAPTIVE CNN BASED CROWD COUNTING AND DYNAMIC SUPERVISION
Zhengxin Li1, Jing Li1, Ling Xie1, Jianli Liu2
1ShanghaiTech University, Shanghai, China, 2Jiangnan University, Wuxi, China
SPATIAL-TEMPORAL CODEC ACCURACY CALIBRATION FOR MULTI-SCALE GIGA-PIXEL MACRO- SCOPE
Lei WANG, Jinli SUO, Jingtao FAN
Tsinghua University, China
10:05 - 10:20 Coffee Break
10:20 - 10:45 Keynote Talk:
Zhan Ma Nanjing University, China
10:45 - 11:10 Keynote Talk:
Shenghua Gao ShanghaiTech University, China
11:10 - 11:35 Keynote Talk:
Xing Lin Tsinghua University, China
11:35 - 12:00 Oral Session 2:
Session Chair: Lu Fang
SEGMENTATION OF BUILDING FOOTPRINTS WITH XCEPTION AND IOULOSS
Kepeng Xu1, Yunye Zhang1, Wenxin Yu1, Zhiqiang Zhang1, Jingwei Lu2, Yibo Fan3, Gang He4, Zhuo Yang5
1Southwest University of Science and Technology, China, 2Cadence Design Systems, Inc, 3Fudan University, China 4Xidian University, China 5Guangdong University of Technology, China
GIGAPIXEL-LEVEL IMAGE CROWD COUNTING USING CSRNET
Zhijie Cao1, Renyou Yan2, Yiyong Huang3, Zhiru Shi4
1Shanghai Jiao Tong University, China, 2ShanghaiTech University, China, 3Shanghai University, China, 4Yoke
Intelligence, China
W-10: Cross-media Big Data Analysis for Semantic Knowledge Understanding
Time: 13:30 AM - 18:00 PM
Room: 5I
Organizers: Yang Yang University of Electronic Science and Technology of China, China.
Yang Wang Dalian University of Technology, China.
Xing Xu University of Electronic Science and Technology of China, China. Zi Huang University of Queensland, Australia.
13:30 - 13:35 Opening Remarks
13:35 - 14:05 Keynote 1: Tentative
14:05 - 15:35 Oral Session 1: Knowledge Transfer Methods in Vision and Language
Session Chair: Yang Yang
14:05 - 14:20
MASK-GUIDED STYLE TRANSFER NETWORK FOR PURIFYING REAL IMAGES
Tongtong Zhao, Yuxiao Yan, Jinjia Peng, Huibing Wang, Xianping Fu
Dalian Maritime University, China
14:20 - 14:35
IMITATION LEARNING FOR SENTENCE GENERATION WITH DILATED CONVOLUTIONS USING ADVERSARIAL TRAINING
JianWei Peng1, MinChun Hu1, ChuanWang Chang2
1National Cheng Kung University, Taiwan, 2Kun Shan University, Taiwan
14:35 - 14:50
NON-RIGID 3D SHAPE RETRIEVAL BASED ON MULTI-VIEW METRIC LEARNING
Haohao Li, Shengfa Wang, Nannan Li, Zhixun Su, Ximin
Dalian University of Technology, China
14:50 - 15:05
WHAT TOPICS DO IMAGES SAY: A NEURAL IMAGE CAPTIONING MODEL WITH TOPIC REPRESEN- TATION
Feng Chen, Songxian Xie, Xinyi Li, Shasha Li, Jintao Tang, Ting Wang
National University of Defense Technology, China
15:05 - 15:30 Coffee Break
15:30 - 16:00 Keynote 2: Tentative
16:00 - 16:30 Oral Session 1: Knowledge Transfer Methods in Vision and Language
Session Chair: Yang Yang
16:00 - 16:15
CROSS DOMAIN KNOWLEDGE TRANSFER FOR UNSUPERVISED VEHICLE RE-IDENTIFICATION
Jinjia Peng, Huibing Wang, Tongtong Zhao and Xianping Fu
Dalian Maritime University, China
16:15 - 16:30
CYCLE-CONSISTENT DIVERSE IMAGE SYNTHESIS FROM NATURAL LANGUAGE
Zhi Chen, Yadan Luo
The University of Queensland, Australia
16:30 - 18:00 Session 2: Knowledge Transfer Related Application
Session chair: Yang Wang
16:30 - 16:45
SELF-WEIGHTED MULTIVIEW METRIC LEARNING BY MAXIMIZING THE CROSS CORRELATIONS
Huibing Wang, Jinjia Peng and Xianping Fu
Dalian Maritime University, China
16:45 - 17:00
CAUSATION-DRIVEN VISUALIZATIONS FOR INSURANCE RECOMMENDATION
Zhixiu Liu1, Chengxi Zang2, Kun Kuang1, Hao Zou1, Hu Zheng3, Peng Cui1
1Tsinghua University, China, 2Cornell University, USA, 3Datebao Insurance Ltd, China
17:00 - 17:15
CROSS-MODAL TRANSFER HASHING BASED ON COHERENT PROJECTION
En Yu1,2, Jiande Sun1, Li Wang1, Xiaojun Chang3, Huaxiang Zhang1, Alexander G. Hauptmann2 1Shandong Normal University, China, 2Carnegie Mellon University, USA, 3Monash University, Australia 17:15 - 17:30
17:30 - 17:45
RELATION NETWORK FOR HYPERSPECTRAL IMAGE CLASSIFICATION
Bin Deng (Shenzhen University)*; Daming Shi (College of Computer Science and Software Engineering, Shen- zhen University)
Tianjin University, China
17:45 - 18:00
ANNOTATING 3D MODELS AND THEIR PARTS VIA DEEP FEATURE EMBEDDING
Kouki Omata, Takahiko Furuya, Ryutarou Ohbuchi
University of Yamanashi, Japan
W-11: AI TechThology for Visual FashioTh ComputiThg
Time: 8:30 - 9:50 AM
Room: 5J
Organizers: Wei Zhang JD AI Research, China Ting Yao JD AI Research, China
Wen-Huang Cheng National Chiao Tung University, Taiwan
8:30 - 8:35 Opening Remarks
Session Chairs: Wei Zhang JD AI Research, China
8:35 - 9:00
DISENTANGLED HUMAN ACTION VIDEO GENERATION VIA DECOUPLED LEARNING
Lingbo Yang1, Zhenghui Zhao1, Shiqi Wang2, Shanshe Wang1, Siwei Ma1, Wen Gao1
1Peking University, China, 2City University of Hong Kong, China
9:00 - 9:25
PERSONALIZED IMAGE RECOMMENDATION WITH PHOTO IMPORTANCE AND USER-ITEM IN- TERACTIVE ATTENTION
Wan Zhang, Zepeng Wang, Tao Chen Hefei University of Technology, China 9:25 - 9:50
PARTIALLY OCCLUDED HEAD POSTURE ESTIMATION FOR 2D IMAGES USING PYRAMID HOG FEATURES
Jun Wu1, Z. Shang1, K. Wang1, J. Zhai1, Y. Wang1, F. Xia1, W. Li1, J. Zhang1, Fan Zhang2
1Northwestern Polytechnical University, China, 2Zhejiang University, China
Friday, July 12, 2019
Friday, July 12, 2019
W-12: 2nd IEEE International Workshop on Faces in Multimedia(FacesMM)
Time: 10:30 - 12:00 AM
Room: 5J
Organizers: Yun Fu Northeastern University, China
Joseph P Robinson Northeastern University, China Ming Shao University of Massachusetts, Dartmouth Siyu Xia Southeast University, China
10:30 - 10:35 Opening Remarks: Joseph P Robinson
10:35 - 11:15 Keynote Talk: Di Huang Beihang University, China 11:15 - 11:30
ADAPTIVE SALIENCE PRESERVING POOLING FOR DEEP CONVOLUTIONAL NEURAL NETWORKS
Yu Zhenyu1, Dai Shiyu1, Xing Yuxiang2
1Nuctech Company Limited, China, 2Tsinghua University, China
11:30 - 11:45
FULLY AUTOMATIC PHOTOREALISTIC FACIAL EXPRESSION AND EYE GAZE TRANSFER WITH A SINGLE IMAGE
Wanxin Xu, Sen-ching Cheung
University of Kentucky, USA
11:45 - 12:00
DEEP DOMAIN ADAPTATION FOR ASIAN FACE RECOGNITION VIA ADA-IBN
Chen Qian, Yi Jin, Yidong Li, Congyan Lang, Songhe Feng, Tao Wang
Beijing Jiaotong University, China
W-13: The Third Workshop on Human Identification in Multimedia (HIM)
Time: 13:30 - 17:30 PM
Room: 5J
Organizers: Liangliang Ren Department of Automation University of Tsinghua University, China Guangyi Chen Dept. of Automation University of Tsinghua University, China
Dr. Jiwen Lu Department of Automation Tsinghua University, China
13:30 - 13:35 Introduction
13:35 - 14:25 Invited Talk: Person Re-identification
Weishi Zheng
14:25 - 14:55 Oral Session 1: Human Identification
Session chair: Liangliang Ren
14:25 - 14:40
SIMILARITY PRESERVED CAMERA-TO-CAMERA GAN FOR PERSON RE-IDENTIFICATION
Jianlei Liu1, Yun Zhou2, Lingchuan Sun1, Zhuqing Jiang1
1Beijing University of Posts and Telecommunications, China, 2Academy of Broadcasting Science, China
14:40 - 14:55
UNSUPERVISED DOMAIN ADAPTATION FOR DISGUISED FACE RECOGNITION
Fangyu Wu1,2, Shiyang Yan3, Jeremy S. Smith2, Wenjin Lu1, Bailing Zhang4
1Xi’an Jiaotong-liverpool Universit, China, 2University of Liverpool, Liverpool, 3Queen’s University Belfast, UK, 4Zhejiang University, China
15:00 - 15:30 Coffee Break
15:30 - 16:45 Oral Session 2: Detection and Tracking
Session chair: Guangyi Chen
15:30 - 15:45
DUAL-CYCLE DEEP REINFORCEMENT LEARNING FOR STABILIZING FACE TRACKING
Congcong Zhu, Zhenhua Yu, Suping Wu, Hao Liu
Ningxia University, China
15:45 - 16:00
MULTI-TASK LEARNING FOR PEDESTRIAN BODY PARTS DETECTION AND MULTI-ATTRIBUTE
CLASSIFICATION
Miaomiao Lou1,2, Lin Chen1, Feng Guo2
1Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Science,China 2Chengdu Univer- sity of Information Technology,China
16:00 - 16:15
CONTEXT ATTENTION MODULE FOR HUMAN HAND DETECTION
Zhihuai Xie1, Shaojie Wang2, Wentian Zhao2, Zhenhua Guo1
1Department of Information Science and Technology, Graduate School at Shenzhen, Tsinghua University, China,
2Department of Computer Science, University of Rochester, USA
16:15 - 16:30
TOWARD ROBUST ONLINE ADAPTIVE VISUAL TRACKING VIA PYRAMIDAL FEATURES EX- TRACTION
Shuai Bai1, Yuan Dong1, Ting-Bing Xu2, Hongliang Bai3
1Beijing University of Posts and Telecommunications, China, 2Institute of Automation of Chinese Academy of Sciences, China, 3Beijing FaceAll Co., China
16:30 - 16:45
IMPROVING HUMAN POSE ESTIMATION WITH SELF-ATTENTION GENERATIVE ADVERSARIAL NETWORKS
Zhongzheng Cao, Rui Wang, Xiangyang Wang, Zhi Liu, Xiaoqiang Zhu
Shanghai University, China
16:45 - 17:30 Oral Session 3: Multimedia Processing
Session chair: Liangliang Ren
16:45 - 17:00
COLLABORATIVE REPRESENTATION GUIDED GRAPH LEARNING FOR VISUAL CLASSIFICATION
Sheng Huang, Yongxin Ge, Feiyu Chen, Kewen He, Xiaohong Zhang
Chongqing University, China
17:00 - 17:15
SPORTS HIGHLIGHTS GENERATION USING DECOMPOSED AUDIO INFORMATION
Muhammad Rafiqul Islam, Manoranjan Paul, Michael Antolovich, Ashad Kabir
Charles Sturt University, Australia
17:15 - 17:30
NEW BENCHMARK DATASETS AND A CHARACTER IDENTIFICATION SYSTEM ON TV SERIES
Zhuo Lei1, Qian Zhang2, Guoping Qiu3,4
1The University of Nottingh Ningbo China, 2University of Nottingh Ningbo China, 3Shenzhen University, China,
4University of Nottingham, UK
