Poster Sessions
Poster Session 1 & TMM Poster
Tuesday, July 9, 2019
Tuesday, July 9, 2019
P-01: Emerging Multimedia Applications and Technologies
Time: 13:30 - 15:00 PM
Room: 3rd Floor
Chair: Chun Yuan Tsinghua University, China
[ID:1] PAY BY SHOWING YOUR PALM: A STUDY OF PALMPRINT VERIFICATION ON MOBILE PLATFORMS
Yingyi Zhang1, Lin Zhang1, Xiao Liu1, Shengjie Zhao1, Ying Shen1, Yukai Yang2
1Tongji University, China, 2Uppsala University, Sweden
[ID:2] REGULARIZE NETWORK SKIP CONNECTIONS BY GATING MECHANISMS FOR ELECTRON MICROSCO- PY IMAGE SEGMENTATION
Yuze Guo, Wenjing Huang, Yajing Chen, Shikui Tu
Shanghai Jiao Tong University, China
[ID:3] CROSS MODALITY ALIGNMENT OF MEDICAL VOLUMES USING SPATIO-SEMANTIC ATTENTIVE CY- CLE-GAN
Xiaohui Lin1, Yi Xu1, Mingda Wang1, Bingbing Ni1, Xiaokang Yang1, Guangyu Tao2, Xiaodan Ye2
1Shanghai Jiao Tong University, China, 2Shanghai Chest Hospital, China
[ID:4] A NEW APPROACH TO AUTOMATIC CLOTHING MATTING FROM MANNEQUINS
Bin Yuan1, Zongqing Lu1, Jing-Hao Xue2, Qingmin Liao1
1Tsinghua University Graduate School at Shenzhen, China, 2University College London, UK
[ID:5] CLUSTERING AND DYNAMIC SAMPLING BASED UNSUPERVISED DOMAIN ADAPTATION FOR PERSON RE-IDENTIFICATION
Jinlin Wu1,2, Shengcai, Liao3, Zhen Lei1,2, Xiaobo Wang4, Yang Yang1,2, Stan Z. Li1,2
1Institute of Automation Chinese Academy of Sciences, China, 2University of Chinese Academy of Sciences, China, 3Inception
Institute of Artificial Intelligence, China, 4JD AI Research, China
[ID:6] SEMANTIC-EMBEDDING AND SHAPE-AWARE U-NET FOR ULTRASOUND EYEBALL SEGMENTATION
Fanchao Lin, Chuanbin Liu, Hongtao Xie, Zheng-Jun Zha, Yongdong Zhang
University of Science and Technology of China, China
[ID:7] LECTURE2NOTE: AUTOMATIC GENERATION OF LECTURE NOTES FROM SLIDE-BASED EDUCATIONAL VIDEOS
Chengpei Xu1, Ruomei Wang1, Shujin Lin1, Xiaonan Luo2, Baoquan Zhao2, Lijie Shao1, Mengqiu Hu1
1Sun Yat-sen University, China, 2Guilin University of Electronic Technology, China
[ID:8] DATA-ADAPTIVE PACKING METHOD FOR COMPRESSION OF DYNAMIC POINT CLOUD SEQUENCES
Jianqiang Liu, Jian Yao, Jingmin Tu, Junhao Cheng
Wuhan University, China
[ID:9] SEMANTIC GAN: APPLICATION FOR CROSS-DOMAIN IMAGE STYLE TRANSFER
Pengfei Li, Meng Yang
Sun Yat-sen University, China
[ID:10] IMPROVING EXTREME LOW-LIGHT IMAGE DENOISING VIA RESIDUAL LEARNING
Paras Maharjan1, Li Li1, Zhu Li1, Ning Xu2, Chongyang Ma3, Yue Li4
1University of Missouri-Kansas City, USA, 2Amazon Go, USA, 3Kwai Inc., China, 4University of Science and Technology of China, China
[ID:11] USER PROFILING WITH CAMPUS WI-FI ACCESS TRACE AND NETWORK TRAFFIC
Yang Gao, Jun Tao, Li Zeng, Xiaoming Fang, Qian Fang, Xiaoyan Li
Southeast University, China
[ID:12] A NEW VISUAL INTERFACE FOR SEARCHING AND NAVIGATING SLIDE-BASED LECTURE VIDEOS
Baoquan Zhao1, Songhua Xu2, Shujin Lin3, Ruomei Wang3 and Xiaonan Luo1
1Guilin University of Electronic Technology, China, 2University of South Carolina, Columbia, USA, 3Sun Yat-sen University, China
P-02: Media Classification and Segmentation I
Time: 13:30 - 15:00 PM
Room: 3rd Floor
Chair: Toshihiko Yamasaki University of Tokyo, Japan
[ID:13] SELF-ATTENTIVE NETWORKS FOR ONE-SHOT IMAGE RECOGNITION
Pin Fang1, Yisen Wang2, Yuan Luo1
1Shanghai Jiao Tong University, China, 2JD AI Research, China
[ID:14] TREE-STRUCTURED KRONECKER CONVOLUTIONAL NETWORK FOR SEMANTIC SEGMENTATION
Tianyi Wu1,2, Sheng Tang1, Rui Zhang1,2, Juan Cao1, Jintao Li1
1Institute of Computing Technology, Chinese Academy of Sciences, China, 2University of Chinese Academy of Sciences, China
[ID:15] PART-BASED CONVOLUTIONAL NETWORK FOR IMBALANCED AGE ESTIMATION
Yixin Zhu, Jun-Yong Zhu, Wei-Shi Zheng
Sun Yat-sen University, China
[ID:16] LEARNING TO DISTINGUISH: A GENERAL METHOD TO IMPROVE COMPARE-BASED ONE-SHOT LEARNING FRAMEWORKS FOR SIMILAR CLASSES
Qiuzheng Chen, Ruoyu Yang
Nanjing University, China
[ID:17] PREDICTABILITY ANALYZING: DEEP REINFORCEMENT LEARNING FOR EARLY ACTION RECOGNI- TION
Xiaokai Chen1,2, Ke Gao1, Juan Cao1
1Institute of Computing Technology, Chinese Academy of Sciences, China, 2University of Chinese Academy of Sciences, China
[ID:18] A FAST END-TO-END METHOD WITH STYLE TRANSFER FOR ROOM LAYOUT ESTIMATION
Junming Chen, Jie Shao, Dongyang Zhang, Xuehui Wu
University of Electronic Science and Technology of China, China
[ID:19] RESOLVING INTRA-CLASS IMBALANCE FOR GAN-BASED IMAGE AUGMENTATION
Lijyun Huang, Kate Ching-Ju Lin, Yu-Chee Tseng
National Chiao Tung University, Taiwan
[ID:20] END-TO-END PANOPTIC SEGMENTATION WITH PIXEL-LEVEL NON-OVERLAPPING EMBEDDING
Weitong Zhang1,2,4, Qieshi Zhang1,2, Jun Cheng1,2, Cong Bai3, Pengyi Hao3
1Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China, 2The Chinese University of Hong Kong,
China, 3Zhejiang University of Technology, China 4Shaanxi Normal University, China
[ID:21] ROBUST EMBEDDING FRAMEWORK WITH DYNAMIC HYPERGRAPH FUSION FOR MULTI-LABEL CLASSIFICATION
Kaixiang Wang
Nanjing Normal University, China
P-03: Oral-05 to Oral-12
Time: 13:30 - 15:00 PM
Room: 3rd Floor
Chair: Jian Zhang University of Technology Sydney, Australia
[ID:22] PARTICLE SWARM LOSS FOR LIGHTWEIGHT OBJECT DETECTION
Peizhen Zhang1,2, Feng Zheng3, Junlong Du2, Jun Zhang2, Xiaowei Guo2, Wei-Shi Zheng1
1Sun Yat-sen University, China, 2Youtu Lab, Tencent, China, 3Southern University of Science and Technology, China
[ID:23] INCORPORATING CATEGORY TAXONOMY IN DEEP REINFORCEMENT LEARNING BASED IMAGE HASHING
Qiang Fu1, Linsen Dong2, Ziyuan Liu2, Yong Luo2, Yonggang Wen2, Ying Li1, Ling-Yu Duan3
1Peking University, China, 2Nanyang Technological University, Singapore, 3Peking University, China
[ID:24] TRUNCATED GRADIENT CONFIDENCE-WEIGHTED BASED ONLINE LEARNING FOR IMBALANCE STREAMING DATA
Ji Hu1, Chenggang Yan1, Xing Liu1, Jiyong Zhang1, Dongliang Peng1, Yi Yang2
1HangZhou DianZi University, China, 2UTS, Australia
[ID:25] UAV TARGET TRACKING BY DETECTION VIA DEEP NEURAL NETWORKS
Mohamed A. Kassab1, Ali Maher2, Fathy Elkazzaz3, Zhang Baochang1,4
1Beihang University, China, 2Military Technical college, Egypt, 3 Benha University, Egypt, 4Shenzhen Academy of Aerospace Technology, China
[ID:26] QUARTER-POINT CODEWORD EXPANSION FOR PRODUCT QUANTIZATION
Shan An1,2, Zhibiao Huang1, Guangfu Che1, Xianglong Liu2, Xin Ma3, Yu Chen1
1Department of Data Intelligence, JD.com, China, 2Beihang University, China, 3Shandong University, China
[ID:27] CONTEXT-AWARE AFFECTIVE GRAPH REASONING FOR EMOTION RECOGNITION
Minghui Zhang, Yumeng Liang, Huadong Ma
Beijing University of Posts and Telecommunications, China
[ID:28] SPL: EXPLOITING UNLABELED DATA FOR MULTI-LABEL IMAGE CLASSIFICATION
Weibo Zhang1,2, Fuqing Zhu1, Jiao Dai1, Songlin Hu1, Jizhong Han1, Tao Guo1
1Institute of Information Engineering, Chinese Academy of Sciences, China, 2School of Cyber Security, University of Chinese Academy of Sciences, China
[ID:29] MLTS: A MULTI-LANGUAGE SCENE TEXT SPOTTER
Yu Zhou1, Shancheng Fang2, Hongtao Xie1, Zheng-Jun Zha1, Yongdong Zhang1
1University of Science and Technology of China, China, 2Institute of Information Engineering, Chinese Academy of Sciences,
China
[ID:30] UNSUPERVISED MONOCULAR DEPTH ESTIMATION BASED ON DUAL ATTENTION MECHANISM AND DEPTH-AWARE LOSS
Xinchen Ye1, Mingliang Zhang1,2, Rui Xu1, Wei Zhong1, Xin Fan1, Zhu Liu1, Jiaao Zhang1
1Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province, China, 2Dalian University of Technolo- gy of Liaoning Province, China
[ID:31] TOWARDS HIGH-QUALITY INTRINSIC IMAGES IN THE WILD
Gang Fu1, Qing Zhang2, Chunxia Xiao1
1Wuhan University, China, 2Sun Yat-sen University, China
[ID:32] UNSUPERVISED LEARNING FOR OPTICAL FLOW ESTIMATION USING PYRAMID CONVOLUTION LSTM
Shuosen Guan1,3, Haoxin Li2,3, Wei-Shi Zheng1,3
1School of Data and Computer Science, Sun Yat-sen University, China, 2School of Electronics and Information Technology, Sun Yat-sen University, China, 3Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education,
China
[ID:33] MAST: MASK-ACCELERATED SHEARLET TRANSFORM FOR DENSELY-SAMPLED LIGHT FIELD RECONSTRUCTION
Yuan Gao1, Robert Bregovic2, Atanas Gotchev2, Reinhard Koch1
1Kiel University, Germany, 2Tampere University, Finland
[ID:34] CODA: COUNTING OBJECTS VIA SCALE-AWARE ADVERSARIAL DENSITY ADAPTION
Li Wang1, Yongbo Li2, Xiangyang Xue1
1Fudan University, China, 2Megvii Inc (Face++), China
[ID:35] PDNET: PRIOR-MODEL GUIDED DEPTH-ENHANCED NETWORK FOR SALIENT OBJECT
Chunbiao Zhu, Xing Cai, Kan Huang, Thomas H Li, Ge Li
SECE, Shenzhen Graduate School, Peking University, China
[ID:36] CONTINUOUS SCALE ADAPTION FOR EFFICIENT BOX-BASED SCENE TEXT
Qi Yuan, Bingwang Zhang, Haojie Li, Zhihui Wang, Zhongxuan Luo, Wei Zhong
Dalian University of Technology, China
[ID:37] MASK-MOST NET: MASK APPROXIMATION BASED MULTI-ORIENTED SCENE TEXT DETECTION NETWORK
Xiaobao Guo1, Jinxing Li2, Bingzhi Chen1, Guangming Lu1
1Harbin Institute of Technology (Shenzhen), China, 2The Chinese University of Hong Kong(Shenzhen), China
[ID:38] DMPR-PS: A NOVEL APPROACH FOR PARKING-SLOT DETECTION USING DIRECTIONAL MARK- ING-POINT REGRESSION
Junhao Huang1, Lin Zhang1, Ying Shen1, Huijuan Zhang1, Shengjie Zhao1, Yukai Yang2
1Tongji University, China, 2Uppsala University, Sweden
[ID:39] ADAPTING SEMANTIC SEGMENTATION OF URBAN SCENES VIA MASK-AWARE GATED DISCRIM- INATOR
Yong-Xiang Lin1, Daniel Stanley Tan1, Wen-Huang Cheng2, Kai-Lung Hua1
1National Taiwan University of Science and Technology, Taiwan, 2National Chiao Tung University, Taiwan
[ID:40] STOCHASTIC VIDEO GENERATION WITH DISENTANGLED REPRESENTATIONS
Maomao Li1, Chun Yuan1, Zhihui Lin1,2, Zhuobin Zheng1,2, Yangyang Cheng1,2
1Graduate School at Shenzhen, Tsinghua University, China, 2Tsinghua University, China
[ID:41] Z-ORDER RECURRENT NEURAL NETWORKS FOR VIDEO PREDICTION
Jianjin Zhang, Yunbo Wang, Mingsheng Long, Jianmin Wang, and Philip S. Yu
Tsinghua University, China
[ID:42] ENERGY-BASED RECURRENT MODEL FOR STOCHASTIC MODELING OF MUSIC
Yingru Liu1, Dongliang Xie2, Xin Wang1
1Stony Brook University, USA, 2Beijing University of Posts and Telecommunications
[ID:43] RESIDUAL FRAME FOR NOISY VIDEO CLASSIFICATION ACCORDING TO PERCEPTUAL QUALITY IN CONVOLUTIONAL NEURAL NETWORKS
Huaixuan Zhang1, Yuhai Lan3, Tao Dai1,2, Ruizhi Qiao4, Ying Xu1, Yao Yao1, Shu-Tao Xia1,2
1Graduate School at Shenzhen, Tsinghua University, China, 2PCL Research Center of Networks and Communications, Peng Cheng Laboratory, China, 3Harbin Institute of Technology, China, 4Tencent Youtu Lab, China
[ID:44] RESIDUAL DILATED NETWORK WITH ATTENTION FOR IMAGE BLIND DENOISING
Guanqun Hou1, Yujiu Yang1, Jing-Hao Xue2
1Graduate School at Shenzhen, Tsinghua University, China, 2University College London, UK
[ID:45] COLLABORATIVE DEEP REINFORCEMENT LEARNING FOR IMAGE CROPPING
Zhuopeng Li, Xiaoyan Zhang
Shenzhen University, China
[ID:46] SIMILARITY-AWARE DEEP ADVERSARIAL LEARNING FOR FACIAL AGE ESTIMATION
Penghui Sun, Hao Liu, Xing Wang, Zhenhua Yu1, Suping Wu
Ningxia University, China
[ID:47] LEARNING TRANSMISSION FILTERING NETWORK FOR IMAGE-BASED PM2.5 ESTIMATION
Yinghong Liao1, Bin Qiu1, Zhuo Su1, Ruomei Wang1, Xiangjian He2,3
1Sun Yat-sen University, China, 2Minjiang University, China, 3University of Technology Sydney, Australia
[ID:48] VIDEO-BASED EARLY ASD DETECTION VIA TEMPORAL PYRAMID NETWORKS
Yuan Tian, Xiongkou Min, Guangtao Zhai, Zhiyong Gao
Shanghai Jiao Tong Unversity, China
[ID:49] AUTOMATIC USER CATEGORIZATION THROUGH LARGE TRANSACTION DATA
Ying Zhang, YinJia Zhang, Qinpei Zhao, Weixiong Rao
Tongji University, China
[ID:50] FEATURE PRESERVING AND UNIFORMITY-CONTROLLABLE POINT CLOUD SIMPLIFICATION ON GRAPH
Junkun Qi, WeiHu, Zongming Guo
Peking University, China
[ID:51] 360SRL: A SEQUENTIAL REINFORCEMENT LEARNING APPROACH FOR ABR TILE-BASED 360 VIDEO STREAMING
Jun Fu, Xiaoming Chen, Zhizheng Zhang, Shilin Wu, Zhibo Chen
University of Science and Technology of China, China
[ID:52] CONTENT-AWARE PERSPECTIVE PROJECTI ON OPTIMIZATION FOR VIEWPORT RENDERING OF 360° IMAGES
Falah Jabar, Joao Ascenso, Maria Paula Queluz
Universidade de Lisboa, Portugal
[ID:53] AN AR BENCHMARK SYSTEM FOR INDOOR PLANAR OBJECT TRACKING
Ziming Wu1, Jiabin Guo2, Shuangli Zhang2, Chen Zhao2, Xiaojuan Ma1
1Hong Kong University of Science and Technology, China, 2Netease AR, China
Tuesday, July 9, 2019
Tuesday, July 9, 2019
TMM Poster
Time: 13:30 - 15:00 PM
Room: 3rd Floor
[ID:54] ENHANCING IMAGE WATERMARKING WITH ADAPTIVE EMBEDDING PARAMETER AND PSNR GUAR- ANTEE
Baoning Niu
Taiyuan University of Technology, China
Poster Session 2
Tuesday, July 9, 2019
Tuesday, July 9, 2019
P-04: Multimedia Analysis, Search and Recommendation
Time: 15:30 - 17:00 PM
Room: 3rd Floor
Chair: Kate Ching-Ju Lin National Chiao Tung University, Taiwan
[ID:1] MULTI-SCALE SCENE TEXT DETECTION VIA RESOLUTION TRANSFORM
Peirui Cheng, Weiqiang Wang, Yuanqiang Cai
University of Chinese Academy of Sciences, China
[ID:2] TOWARDS ACCURATE INSTANCE-LEVEL TEXT SPOTTING WITH GUIDED ATTENTION
Haiyan Wang, Xuejian Rong, Yingli Tian
The City College of New York, USA
[ID:3] MULTI-SCALE GEM POOLING WITH N-PAIR CENTER LOSS FOR FINE-GRAINED IMAGE SEARCH
Youming Deng, Xianming Lin, Run Li, Rongrong Ji
Xiamen University, China
[ID:4] SEMI-SUPERVISED SEMANTIC-PRESERVING HASHING FOR EFFICIENT CROSS-MODAL RETRIEVAL
Xingzhi Wang1,2, Xin Liu1,2, Zhikai Hu1, Nannan Wang2, Wentao Fan1, Ji-Xiang Du1
1Huaqiao University, China, 2Xidian University, China
[ID:5] ROBUST MULTI-VIEW HASHING FOR CROSS-MODAL RETRIEVAL
Haitao Wang, Hui Chen, Min Meng, JiGang Wu
Guangdong University of Technology, China
[ID:6] SCENE TEXT RECOGNITION VIA GATED CASCADE ATTENTION
Siwei Wang, Yongtao Wang, Xiaoran Qin, Qijie Zhao, Zhi Tang
Peking University, China
[ID:7] TEXT-ATTENTIONAL CONDITIONAL GENERATIVE ADVERSARIAL NETWORK FOR SUPER-RESOLU- TION OF TEXT IMAGES
Yuyang Wang, Feng Su and Ye Qian
Nanjing University, China
[ID:8] ONLINE LEARNING TO RANK IN A LISTWISE APPROACH FOR INFORMATION RETRIEVAL
Fan Ma1, Haoyun Yang2, Haibing Yin2, Xiaofeng Huang2, Chenggang Yan2, Xiang Meng2
1University of Technology Sydney, Australia, 2Hangzhou Dianzi University, China
P-05: Pose and Action Recognition I
Time: 15:30 - 17:00 PM
Room: 3rd Floor
Chair: Yicong Zhou University of Macau, China
[ID:9] RECOGNIZING MICRO ACTIONS IN VIDEOS: LEARNING MOTION DETAILS VIA SEGMENT-LEVEL TEM- PORAL PYRAMID
Yang Mi1, Song Wang1,2
1University of South Carolina, USA, 2Tianjin University, China
[ID:10] ENTANGLEMENT LOSS FOR CONTEXT-BASED STILL IMAGE ACTION RECOGNITION
Miao Xin1, Shuhang Wang2, Jian Cheng1
1Institute of Automation, Chinese Academy of Sciences, China, 2Harvard University, USA
[ID:11] BI-DIRECTIONAL MESSAGE PASSING BASED SCANET FOR HUMAN POSE ESTIMATION
Lu Zhou, Yingying Chen, Jinqiao Wang, Ming Tang and Hanqing Lu
Institute of Automation, Chinese Academy of Sciences, China
[ID:12] SPATIAL MASK CONVLSTM NETWORK AND INTRA-CLASS JOINT TRAINING METHOD FOR HUMAN ACTION RECOGNITION IN VIDEO
Jingjun Chen, Yonghong Song, Yuanlin Zhang
Xi’an Jiaotong University, China
[ID:13] SELF-ATTENTION GUIDED DEEP FEATURES FOR ACTION RECOGNITION
Renyi Xiao1, Yonghong Hou1, Zihui Guo1, Chuankun Li1, Pichao Wang2, Wanqing Li3
1Tianjin University, China, 2Alibaba Group (U.S.) Inc., USA, 3University of Wollongong, Australia
[ID:14] LEARNING SHAPE-MOTION REPRESENTATIONS FROM GEOMETRIC ALGEBRA SPATIO-TEMPORAL MODEL FOR SKELETON-BASED ACTION RECOGNITION
Yanshan Li1, Rongjie Xia1, Xing Liu1, Qinghua Huang2
1Shenzhen University, China, 2Northwestern Polytechnical University, China
[ID:15] ACPNET: ANCHOR-CENTER BASED PERSON NETWORK FOR HUMAN POSE ESTIMATION AND IN- STANCE SEGMENTATION
Yang Bai, Weiqiang Wang
University of Chinese Academy of Sciences, China
[ID:16] SPATIO-TEMPORAL MULTI-SCALE SOFT QUANTIZATION LEARNING FOR SKELETON-BASED HUMAN ACTION RECOGNITION
Jianyu Yang1, Chen Zhu1, Junsong Yuan2
1Soochow University, China, 2State University of New York at Buffalo, USA
[ID:17] LPHD: A LARGE-SCALE HEAD POSE DATASET FOR RGB IMAGES
Wei Sun1, Yezhao Fan1, Xiongkuo Min1, Shihao Peng1, Siwei Ma2 and Guangtao Zhai1
1Shanghai Jiao Tong University, China, 2Peking University, China
P-06: Person and Emotion Understanding
Time: 15:30 - 17:00 PM
Room: 3rd Floor
Chair: Zheng Wang National Institute of Informatics, Japan
[ID:18] HUMAN-CENTERED EMOTION RECOGNITION IN ANIMATED GIFS
Zhengyuan Yang, Yixuan Zhang, Jiebo Luo
University of Rochester, USA
[ID:19] DEEP SEMI-SUPERVISED PERSON RE-IDENTIFICATION WITH EXTERNAL MEMORY
Qize Yang, Ancong Wu, Wei-Shi Zheng
Sun Yat-sen University, China
[ID:20] CONVOLUTIONAL TEMPORAL ATTENTION MODEL FOR VIDEO-BASED PERSON RE-IDENTIFICATION
Tanzila Rahman1, Mrigank Rochan2, Yang Wang2
1University of British Columbia, Canada, 2University of Manitoba, Canada
[ID:21] POOLING MAP ADAPTATION IN CONVOLUTIONAL NEURAL NETWORK FOR FACIAL EXPRESSION RECOGNITION
Zhiyuan Li1, Shizhong Han2, Ahmed Shehab Khan1, Jie Cai1, Zibo Meng3, James O’Reilly1, Yan Tong1
1University of South Carolina, USA, 212Sigma Technologies, China, 3Innopeak Technology Inc., USA
[ID:22] FAST PERSON SEARCH PIPELINE
Jianheng Li, Fuhang Liang, Yuanxun Li, Wei-Shi Zheng
Sun Yat-sen University, China
[ID:23] DYNAMIC REGION DIVISION FOR ADAPTIVE LEARNING PEDESTRIAN COUNTING
Gaoqi He1, Zhenwei Ma2, Binhao Huang2, Bin Sheng3, Yubo Yuan2
1East China Normal University, China, 2East China University of Science and Technology, China, 3Shanghai Jiao Tong Uni- versity, China
[ID:24] ANOTHER DIMENSION: TOWARDS MULTI-SUBNET NEURAL NETWORK FOR IMAGE SENTIMENT ANALYSIS
Jing Zhang, Han Sun, Zhe Wang, Tong Ruan
East China University of Science and Technology, China
[ID:25] TWO-STAGE MODEL FOR SOCIAL RELATIONSHIP UNDERSTANDING FROM VIDEOS
Pilin Dai, Jinna Lv, Bin Wu
Beijing University of Posts and Telecommunications, China
[ID:26] FPN++: A SIMPLE BASELINE FOR PEDESTRIAN DETECTION
Junhao Hu, Lei Jin, Shenghua Gao
ShanghaiTech University, China
[ID:27] AN END-TO-END LEARNING APPROACH FOR MULTIMODAL EMOTION RECOGNITION: EXTRACTING COMMON AND PRIVATE INFORMATION
Fei Ma, Wei Zhang, Yang Li, Shao-Lun Huang, Lin Zhang
Tsinghua-Berkeley Shenzhen Institute, Tsinghua University, China
P-07: Best Papers and Oral-01 to Oral-04
Time: 15:30 - 17:00 PM
Room: 3rd Floor
Chair: Xiaoping Zhang Ted Rogers School of Management, Ryerson University, Canada
[ID:28] AN END-TO-END ARCHITECTURE FOR CLASS-INCREMENTAL OBJECT DETECTION WITH KNOWL- EDGE DISTILLATION
Yu Hao1, Yanwei Fu1, Yu-Gang Jiang1,2, Qi Tian3
1Fudan University, China, 2Jilian Technology Group(Video++) ,China, 3Huawei Noah’s Ark Lab, China
[ID:29] REAL-TIME INDOOR SCENE RECONSTRUCTION WITH RGBD AND INERTIAL INPUT
Zunjie Zhu1, Feng Xu2, Chenggang Yan1, Xinhong Hao3, Xiangyang Ji2, Yongdong Zhang4 ,Qionghai Dai2
1Hangzhou Dianzi University, China, 2Tsinghua University, China, 3Beijing Institute of Technology, China, 4University of Sci- ence and Technology of China, China
[ID:30] DOUBLY SEMI-SUPERVISED MULTIMODAL ADVERSARIAL LEARNING FOR CLASSIFICATION, GENER- ATION AND RETRIEVAL
Changde Du1, Changying Du2, Huiguang He1
1Institute of Automation Chinese Academy of Sciences, China, 2Huawei Noah’s Ark Lab, China
[ID:31] TOWARDS DIGITAL RETINA IN SMART CITIES: A MODEL GENERATION, UTILIZATION AND COMMU- NICATION PARADIGM
Yihang Lou1, Ling-Yu Duan1, Yong Luo1, Ziqian Chen1, Tongliang Liu2, Shiqi Wang3, Wen Gao1
1Peking University, China, 2University of Sydney, Australia, 3City University of Hongkong, China, 4The Peng Cheng Labora- tory, China
[ID:32] SDP: AN IMPROVED BASELINE ESTIMATION MODEL BASED ON STANDARD DEVIATION PROPOR- TION
Zhenhua Tan, Danke Wu, Liangliang He, Qiuyun Chang, Bin Zhang
Northeastern University, China
[ID:33] CITATION RECOMMENDATION BASED ON WEIGHTED HETEROGENEOUS INFORMATION NETWORK CONTAINING SEMANTIC LINKING
Jie Chen, Yang Liu, Shu Zhao, Yanping Zhang
Anhui University, China
[ID:34] FUSION-SUPERVISED DEEP CROSS-MODAL HASHING
Li Wang, Lei Zhu, En Yu, Jiande Sun, Huaxiang Zhang
Shandong Normal University, China
[ID:35] DOMAIN UNCERTAINTY BASED ON INFORMATION THEORY FORCROSS-MODAL HASH RETRIEVAL
Wei Chen1, Nan Pu1, Yu Liu2, Erwin M. Bakker1, Michael S. Lew1
1 Leiden University, Holland, 2 ESAT-PSI, KU Leuven, Belgium
[ID:36] ADAPTIVE PLANE PROJECTION FOR VIDEO-BASED POINT CLOUD CODING
Eurico Lopes, João Ascenso, Catarina Brites, Fernando Pereira
Instituto Superior Técnico, Universidade de Lisboa - Instituto de Telecomunicações, Lisboa, Portugal
[ID:37] FAST CU PARTITIONING ALGORITHM FOR H.266/VVC INTRA-FRAME CODING
Ting Fu1, Hao Zhang 1, Fan Mu1, Huanbang Chen2
1Central South University, China, 2Huawei Base, China
[ID:38] TWO-STAGE FAST MULTIPLE TRANSFORM SELECTION ALGORITHM FOR VVC INTRA CODING
Ting Fu1, Hao Zhang 1, Fan Mu1, Huanbang Chen2
1Central South University, China, 2Huawei Base, China
[ID:39] HISTORY-BASED MOTION VECTOR PREDICTION FOR FUTURE VIDEO CODING
Junru Li1, Meng Wang2, Li Zhang3, Kai Zhang3, Hongbin Liu3, Shiqi Wang2, Siwei Ma1, Wen Gao1
1Peking University, China, 2City University of Hong Kong, China, 3Bytedance Inc., USA
[ID:40] AMS-SFE: TOWARDS AN ALIGNMENT OF MANIFOLD STRUCTURES VIA SEMANTIC FEATURE EX- PANSION FOR ZERO-SHOT LEARNING
Jingcai Guo, Song Guo
The Hong Kong Polytechnic University, China
[ID:41] LOW-SHOT PALMPRINT RECOGNITION BASED ON META-SIAMESE NETWORK
Xuefeng Du1, Dexing Zhong1,2, Pengna Li1
1Xi’an Jiaotong University, China, 2Research Institute of Xi’an Jiaotong University, China
[ID:42] SR-GAN: SEMANTIC RECTIFYING GENERATIVE ADVERSIAL NETWORK FOR ZERO-SHOT LEARNING
Zihan Ye1,5, Fan Lyu1,2, Linyan Li3, Qiming Fu1,6, Jinchang Ren4, Fuyuan Hu1,7
1Suzhou University of Science and Technology, China, 2Tianjin University, China, 3Suzhou Institute of Trade & Commerce, China, 4University of Strathclyde, UK, 5Virtual Reality Key Laboratory of Intelligent Interaction and Application Technology of Suzhou, China, 6Key Laboratory of Intelligent Building Energy Efficiency, China, 7Suzhou Key Laboratory for Big Data and Information Service, China
[ID:43] COMPARE MORE NUANCED: PAIRWISE ALIGNMENT BILINEAR NETWORK FOR FEW-SHOT FINE- GRAINED LEARNING
Huaxi Huang, Junjie Zhang, Jian Zhang, Qiang Wu, Jingsong Xu
University of Technology Sydney, Australia
[ID:44] FEATURE-AWARE AND CONTENT-WISE DENOISING OF 3D STATIC AND DYNAMIC MESHES US- ING DEEP AUTOENCODERS
Gerasimos Arvanitis1, Aris S. Lalos2, and Konstantinos Moustakas1
1University of Patras, Greece, 2"ATHENA" Research Center, Greece
[ID:45] REAL-TIME MONOCULAR VISUAL SLAM BY COMBINING POINTS AND LINES
Xinyu Wei, Jun Huang, Xiaoyuan Ma
Shanghai Advanced Research Institute, China
[ID:46] F-NUMBER ADAPTATION FOR MAXIMIZING THE SENSOR USAGE OF LIGHT FIELD CAMERAS
Chuanpu Li, Xin Jin, Junke Li and Qionghai Dai
Graduate School at Shenzhen, Tsinghua University, China
[ID:47] BLIND CALIBRATION FOR FOCUSED PLENOPTIC CAMERAS
Xufu Sun, Xin Jin, Pei Wang, Yanqin Chen and Qionghai Dai
Graduate School at Shenzhen, Tsinghua University, China
Poster Session 3 & Demo Session 1
Wednesday, July 10, 2019
Wednesday, July 10, 2019
P-08: Multimedia Creation and Enhancement
Time: 13:30 - 15:00 PM
Room: 3rd Floor
Chair: Jing-Hao Xue University College London, UK
[ID:1] BOUNDARY AWARE MULTI-FOCUS IMAGE FUSION USING DEEP NEURAL NETWORK
Haoyu Ma, Juncheng Zhang, Shaojun Liu, Qingmin Liao
Graduate School at Shenzhen, Tsinghua University, China
[ID:2] A MULTI-LEVEL AGGREGATED NETWORK FOR IMAGE RESTORATION
Chenxi Ma, Weimin Tan, Bahetiyaer Bare, and Bo Yan
Fudan University, China
[ID:3] UNSUPERVISED FACIAL IMAGE SYNTHESIS USING TWO-DISCRIMINATOR ADVERSARIAL AUTOEN- CODER NETWORK
Xuehui Wu, Jie Shao, Dongyang Zhang, Junming Chen
University of Electronic Science and Technology of China, China
[ID:4] FACIAL IMAGE INPAINTING USING MULTI-LEVEL GENERATIVE NETWORK
Jie Liu, Cheolkon Jung
Xidian University, China
[ID:5] A VIDEO POST-FILTER DEBLOCKING METHOD BASED ON TEMPORAL BOOSTING RESIDUAL NET- WORKS
Jianyu Wang1, Shaohui Liu1,2, Feng Jiang1,2, Xiaoshuai Sun1, Yongliang Liu3
1Harbin Institute of Technology, China, 2Pengcheng Laboratory, China, 3Alibaba Group, China
[ID:6] DISTILLING WITH RESIDUAL NETWORK FOR SINGLE IMAGE SUPER RESOLUTION
Xiaopeng Sun, Wen Lu, Rui Wang, Furui Bai
Xidian University, China
[ID:7] RDGAN: RETINEX DECOMPOSITION BASED ADVERSARIAL LEARNING FOR LOW-LIGHT ENHANCE- MENT
Junyi Wang, Weimin Tan, Xuejing Niu and Bo Yan
Fudan University, China
[ID:8] SINGLE IMAGE DE-RAINING VIA GENERATIVE ADVERSARIAL NETS
Shichao Li, Yonghong Hou, Huanjing Yue, Zihui Guo
Tianjin University, China
[ID:9] SWITCHGAN FOR MULTI-DOMAIN FAICAL IMAGE TRANSLATION
Yuanlue Zhu, Mengchao Bai, Linlin Shen, Zhiwei Wen
Shenzhen University, China
[ID:10] A FEATURE-BASED APPROACH FOR LIGHT FIELD VIDEO ENHANCEMENT
Michele Brizzi, Federica Battisti, Alessandro Neri
Roma Tre University, Italy
P-09: Multimedia and Vision I
Time: 13:30 - 15:00 PM
Room: 3rd Floor
Chair: Qixiang Ye University of Chinese Academy of Sctiences, China
[ID:11] EASY TRANSFER LEARNING BY EXPLOITING INTRA-DOMAIN STRUCTURES
Jindong Wang1, Yiqiang Chen1, Han Yu2, Meiyu Huang3, Qiang Yang4
1Chinese Academy of Sciences, China, 2Nanyang Technological University, Singapore, 3China Academy of Space Technology,
China, 4Hong Kong University of Science and Technology, China
[ID:12] SKELETON-BASED ACTION RECOGNITION WITH SYNCHRONOUS LOCAL AND NON-LOCAL SPA- TIO-TEMPORAL LEARNING AND FREQUENCY ATTENTION
Guyue Hu1,2, Bo Cui1,2, Shan Yu1,2
1Institute of Automation Chinese Academy of Sciences, China, 2University of Chinese Academy of Sciences, China
[ID:13] DEEP GEOMETRY EMBEDDING NETWORKS FOR ROBUST FACIAL LANDMARK DETECTION
Meilu Zhu, Daming Shi
Shenzhen University, China
[ID:14] JOINT PROJECTION AND SUBSPACE LEARNING FOR ZERO-SHOT RECOGNITION
Guangzhen Liu, Jiechao Guan, Manli Zhang, Jianhong Zhang, Zihao Wang, Zhiwu Lu
Renmin University of China, China
[ID:15] PART-PRESERVING POSE MANIPULATION FOR PERSON IMAGE SYNTHESIS
Haoye Dong1, Xiaodan Liang1, Chenxing Zhou1, Hanjiang Lai1, Jia Zhu2, Jian Yin1
1Sun Yat-sen University, China, 2South China Normal University, China
[ID:16] BREGMAN-TANIMOTO BASED METHOD FOR CONTRAST PRESERVING DECOLORIZATION
He Chen, Faming Fang
East China Normal University, China
[ID:17] TDCC: TOP-DOWN SEMANTIC AGGREGATION FOR COLOR CONSTANCY
Xiaoqiang Li, Yaqin Zhu, Jiayue Han, Jide Li, Weiqin Tong
Shanghai University, China
[ID:18] FROM MARKET TO DISH: MULTI-INGREDIENT IMAGE RECOGNITION FOR PERSONALIZED RECIPE RECOMMENDATION
Lin Zhang1, Jianbo Zhao2, Si Li2, Boxin Shi1,3, Ling-Yu Duan1,3
1Peking University, China, 2Beijing University of Posts and Telecommunications, China, 3Peng Cheng Laboratory, China
[ID:19] IMPROVING OPEN SET DOMAIN ADAPTATION USING IMAGE-TO-IMAGE TRANSLATION
Hongjie Zhang1, Ang Li2, Xu Han1, Zhaoming Chen1, Yang Zhang1, Yanwen Guo1
1Nanjing University, China, 2DeepMind, Mountain View, USA
[ID:20] STRUCTURE GENERATION AND GUIDANCE NETWORK FOR UNSUPERVISED MONOCULAR DEPTH ESTIMATION
Chaoqun Wang, Xuejin Chen, Shaobo Min, Feng Wu
University of Science and Technology of China, China
[ID:21] A CONDITIONAL BAYESIAN BLOCK STRUCTURE INFERENCE MODEL FOR OPTIMIZED AV1 ENCOD- ING
Xinyao Chen1, Bichuan Guo1, Minhao Tang1, Yuxing Han2, Jiangtao Wen1
1Tsinghua University, China, 2South China Agriculture University, China
[ID:22] LEARNING TO REMOVE REFLECTIONS FOR TEXT IMAGES
Ce Wang1, Renjie Wan2, Feng Gao3, Boxin Shi1,4, Ling-Yu Duan1,4
1Peking University, China, 2Nanyang Technological University, Singapore,3Tsinghua University, China, 4Peng Cheng Labora- tory, China
P-10: Oral-17 to Oral-24
Time: 13:30 - 15:00 PM
Room: 3rd Floor
Chair: Roger Zimmermann National University of Singapore, Singapore
[ID:23] VIDEO EMOTION RECOGNITION WITH CONCEPT SELECTION
Baohan Xu1, Yingbin Zheng2, Hao Ye2, Caili Wu3, Heng Wang1, Gufei Sun1
1Zhongan Technology, China, 2Videt Tech, USA, 3East China Normal University, China
[ID:24] GRAPH CONVOLUTIONAL LSTM MODEL FOR SKELETON-BASED ACTION RECOGNITION
Han Zhang, Yonghong Song, Yuanlin Zhang
Xi’an Jiaotong University, China
[ID:25] LEARNING RECURRENT STRUCTURE-GUIDED ATTENTION NETWORK FOR MULTI-PERSON POSE ES- TIMATION
Zhongwei Qiu1, Kai Qiu2, Jianlong Fu2, Dongmei Fu1
1University of Science and Technology Beijing, China, 2Microsoft Reasearch, China
[ID:26] PCPCAD: PROPOSAL COMPLEMENTARY ACTION DETECTOR
Zhenying Fang1, Suguo Zhu1, Jun Yu1, Qi Tian2,3
1Hangzhou Dianzi University, China, 2Huawei Noah’s Ark Lab, China, 3The University of Texas at San Antonio, USA
[ID:27] PERSONALITY DRIVEN MULTI-TASK LEARNING FOR IMAGE AESTHETIC ASSESSMENT
Leida Li1,2, Hancheng Zhu2, Sicheng Zhao3, Guiguang Ding4, Hongyan Jiang2, Allen Tan5
1Xidian University, China, 2China University of Mining and Technology, China, 3University of California Berkeley, USA, 4Ts- inghua University, China, 5Tencent, China
[ID:28] VIDEO QUALITY TEMPORAL POOLING USING A VISIBILITY MEASURE
Chen Bai, Amy R. Reibman
Purdue University, USA
[ID:29] IMAGE QUALITY ASSESSMENT OF MULTI-EXPOSURE IMAGE FUSION FOR BOTH STATIC AND DY- NAMIC SCENES
Yuming Fang1, Yan Zeng1, Hanwei Zhu1, Guangtao Zhai2
1Jiangxi University of Finance and Economics, China, 2Shanghai Jiao Tong University, China
[ID:30] NO-REFERENCE STEREOSCOPIC IMAGE QUALITY ASSESSMENT BASED ON LOCAL TO GLOBAL FEA- TURE REGRESSION
Sumei Li, Jianwei Xue, Yongtian Han
Tianjin University, China
[ID:31] HERDING EFFECT BASED ATTENTION FOR PERSONALIZED TIME-SYNC VIDEO RECOMMENDATION
Wenmian Yang1,2, Wenyuan Gao1, Xiaojie Zhou1, Weijia Jia1,2, Shaohua Zhang1,2, Yutao Luo1
1Shanghai JiaoTong University, China, 2University of Macau, China
[ID:32] SEQUENTIAL BEHAVIOR MODELING FOR NEXT MICRO-VIDEO RECOMMENDATION WITH COLLABO- RATIVE TRANSFORMER
Shang Liu, Zhenzhong Chen
Wuhan University, China
[ID:33] BUTTONTIPS: DESIGNING WEB BUTTONS WITH SUGGESTIONS
Dawei Liu, Ying Cao, Rynson W.H. Lau, Antoni B. Chan
City University of Hongkong, China
[ID:34] KNOWING USER BETTER: MICRO-VIDEO RECOMMENDER SYSTEM BY JOINTLY OPTIMIZING TO CLICK-THROUGH AND PLAYTIME
Shengjie Ma, Zhengjun Zha, Feng Wu
University of Science and Technology of China, China
[ID:35] ADVERSARIAL CROSS-MODAL RETRIEVAL VIA LEARNING AND TRANSFERRING SINGLE-MODAL SIMILARITIES
Xin Wen1, Zhizhong Han1,2, Xinyu Yin1, Yu-Shen Liu1
1Tsinghua University, China, 2University of Maryland, USA
[ID:36] SEMI-SUPERVISED COMPATIBILITY LEARNING ACROSS CATEGORIES FOR CLOTHING MATCHING
Zekun Li, Zeyu Cui, Shu Wu, Xiaoyu Zhang, Liang Wang
Chinese Academy of Sciences, China
[ID:37] ADVERSARIAL LEARNING FOR FINE-GRAINED IMAGE SEARCH
Kevin Lin1, Fan Yang2, Qiaosong Wang2, Robinson Piramuthu2
1University of Washington, USA, 2eBay Inc., USA
[ID:38] A MASK BASED DEEP RANKING NEURAL NETWORK FOR PERSON RETRIEVAL
Lei Qi1, Jing Huo1, Lei Wang2, Yinghuan Shi1, Yang Gao1
1Nanjing University, China, 2University of Wollongong, Australia
[ID:39] DISCO: DEPTH INFERENCE FROM STEREO USING CONTEXT
Kunal Swami, Kaushik Raghavan, Nikhilanj Pelluriy, Rituparna Sarkar, Pankaj Bajpai
Samsung Research Institute Bangalore, India
[ID:40] PANET: A CONTEXT BASED PREDICATE ASSOCIATION NETWORK FOR SCENE GRAPH GENERATION
Yunian Chen1, Yanjie Wang3, Yang Zhang1, Yanwen Guo1,2
1Nanjing University, China, 2The 28th Research Institute of China Electronics Technology Group Corporation, China, 3Zheji-
ang University, China
[ID:41] UNTARGETED ADVERSARIAL ATTACK VIA EXPANDING THE SEMANTIC GAP
Aming Wu1, Yahong Han1, Quanxin Zhang2, Xiaohui Kuang3
1Tianjin University, China, 2Beijing Institute of Technology, China, 3National Key Laboratory of Science and Technology on Information System Security, China
[ID:42] LEARNING GOAL-ORIENTED VISUAL DIALOG AGENTS: IMITATING AND SURPASSING ANALYTIC EX- PERTS
Yen-Wei Chang, Wen-Hsiao Peng
National Chiao Tung University, Taiwan
[ID:43] GAN-BASED MULTI-LEVEL MAPPING NETWORK FOR SATELLITE IMAGERY SUPER-RESOLUTION
Kui Jiang, Zhongyuan Wang, Peng Yi, Junjun Jiang, Guangcheng Wang, Zhen Han, Tao Lu
Wuhan University, China
[ID:44] QUALITY-GATED CONVOLUTIONAL LSTM FOR ENHANCING COMPRESSED VIDEO
Ren Yang3, Xiaoyan Sun1, Mai Xu2 and Wenjun Zeng1
1Microsoft Research, USA, 2Beihang University, China, 3ETH, Switzerland
[ID:45] COMPOUNDED LAYER-PRIOR UNROLLING: A UNIFIED TRANSMISSION-BASED IMAGE ENHANCE- MENT FRAMEWORK
Risheng Liu, Minjun Hou, Jinyuan Liu, Xin Fan, Zhongxuan Luo
Dalian University of Technology, China
[ID:46] DEEP PYRAMID VARIATION LEARNING FOR IMAGE INTERPOLATION
Fu Qiang, Wenhan Yang, Ying Li, and Jiaying Liu
Peking University, China
[ID:47] CLOTHES KEYPOINTS LOCALIZATION AND ATTRIBUTE RECOGNITION VIA PRIOR KNOWLEDGE
Zhangxuan Gu, Jianfu Zhang, Ziqi Pan, Haohua Zhao, Liqing Zhang
Shanghai Jiao Tong University, China
[ID:48] SPATIO-TEMPORAL MULTI-FACTOR DISCRIMINANT ANALYSIS FOR INDIVIDUAL IDENTIFICATION
Yong Su, Zhiyong Feng
Tianjin University, China
[ID:49] CHANNEL-WISE TEMPORAL ATTENTION NETWORK FOR VIDEO ACTION RECOGNITION
Jianjun Lei1, Yalong Jia1,Bo Peng1, Qingming Huang2
1Tianjin University, China, 2University of Chinese Academy of Sciences, China
[ID:50] LOCALIZATION GUIDED FIGHT ACTION DETECTION IN SURVEILLANCE VIDEOS
Qichao Xu1, John See2, Weiyao Lin1
1Shanghai Jiao Tong University, China, 2Multimedia University, Malaysia
[ID:51] RECURSIVE MULTI-STAGE UPSCALING NETWORK WITH DISCRIMINATIVE FUSION FOR SUPER-RES- OLUTION
Yue Lu1, Zhuqing Jiang1, Guodong Ju2, Liangheng Shen2, Aidong Men1
1Beijing University of Posts and Telecommunications, China, 2GuangDong TUS-TuWei Technology Co.,Ltd, China
[ID:52] IMPROVING IMAGE SUPER-RESOLUTION VIA FEATURE RE-BALANCING FUSION
Yuanfei Huang, Jie Li, Xinbo Gao, Wen Lu, Yanting Hu
Xidian University, China
[ID:53] DIFFICULTY-AWARE IMAGE SUPER RESOLUTION VIA DEEP ADAPTIVE DUAL-NETWORK
Jinghui Qin, Ziwei Xie, Yukai Shi, Wushao Wen
Sun Yat-sen University, China
[ID:54] DENSE-CONNECTED RESIDUAL NETWORK FOR VIDEO SUPER-RESOLUTION
Xiaoting Du, Yuan Zhou, Yanfang Chen, Yeda Zhang, Jianxing Yang and Dou Jin
Tianjin University, China
Wednesday, July 10, 2019
Wednesday, July 10, 2019
Demo Session 1
Time: 13:30 - 15:00 PM
Room: 3rd Floor
Chair: Dong Liu University of Science and Technology of China, China
[ID:55] BASEBALL PLAYER BEHAVIOR RECOGNITION SYSTEM USING MULTIMODAL FEATURES WITH AN AUGMENTED REALITY DISPLAY ON A SMART GLASS
Wei-Chen Yen1, Chih-Chieh Fang2, Shih-Wei Sun1, Kai-Lung Hua3, and Huang-Chia Shih4
1Department of New Media Art, Taipei National University of the Arts, Taiwan,2Graduate Institute of Dance Theory, Taipei National University of the Arts, Taiwan, 3Dept. Computer Science and Information Engineering, Natl. Taiwan Univ. of Sci. and Tech., Taiwan,4Dept. Electrical Engineering, Yuan Ze University, Taiwan
[ID:56] PRACTICAL IMAGE OBFUSCATION WITH PROVABLE PRIVACY
Liyue Fan
University at Albany SUNY, USA
[ID:57] SMART ADVERTISING IN VIDEOS BASED ON COMPREHENSIVE CONTENT ANALYTICS
Yi Zhang, Fan Luan, Yu-Gang Jiang
Jilian Technology Group (Video++), Shanghai, China
[ID:58] LIVE DEMONSTRATION: HIGH PERFORMANCE FOCUSED PLENOPTIC CAMERA
Chuanpu Li, Xufu Sun, Xin Jin, Qionghai Dai
Graduate School at Shenzhen, Tsinghua University, Shenzhen, China
Poster Session 4 & Demo Session 2
Wednesday, July 10, 2019
Wednesday, July 10, 2019
P-11: Multimedia and Language I
Time: 15:30 - 17:00 PM
Room: 3rd Floor
Chair: Liyue Fan University at Albany, USA
[ID:1] DYNAMIC PSEUDO LABEL DECODING FOR CONTINUOUS SIGN LANGUAGE RECOGNITION
Hao Zhou, Wengang Zhou, Houqiang Li
University of Science and Technology of China, China
[ID:2] DECOUPLING LOCALIZATION AND CLASSIFICATION IN SINGLE SHOT TEMPORAL ACTION DETEC- TION
Yupan Huang1, Qi Dai2, Yutong Lu1
1Sun Yat-sen University, China, 2Microsoft Research, USA
[ID:3] IMAGE-TO-TREE: A TREE-STRUCTURED DECODER FOR IMAGE CAPTIONING
Zhiming Ma, Chun Yuan, Yangyang Cheng, Xinrui Zhu
Tsinghua University, China
[ID:4] MULTIMODAL SEMANTIC ATTENTION NETWORK FOR VIDEO CAPTIONING
Liang Sun1, Bing Li2, Chunfeng Yuan2, Zhengjun Zha1, Weiming Hu2
1University of Science and Technology of China, China, 2Chinese Academy of Sciences, China
[ID:5] CONCRETE IMAGE CAPTIONING BY INTEGRATING CONTENT SENSITIVE AND GLOBAL DISCRIMINA- TIVE OBJECTIVE
Jie Wu1, Tianshui Chen1,2, Hefeng Wu1,3, Zhi Yang1, Qing Wang1,2, Liang Lin1,2
1Sun Yat-sen University, China, 2DarkMatter AI Research, United Arab Emirates, 3Guangdong University of Foreign Studies,
China
[ID:6] REVNET: BRING REVIEWING INTO VIDEO CAPTIONING FOR A BETTER DESCRIPTION
Huidong Li, Dandan Song, Lejian Liao, Cuimei Peng
Beijing Institute of Technology, China
[ID:7] MULTIMODAL IMAGE CAPTIONING THROUGH COMBINING REINFORCED CROSS ENTROPY LOSS AND STOCHASTIC DEPRECATION
Xi Meng, Hao Kong, Dongqi Tang, Tong Lu
Nanjing University, China
P-12: Advances in Artificial Intelligence
Time: 15:30 - 17:00 PM
Room: 3rd Floor
Chair: Baoning Niu Taiyuan University of Technology, China
[ID:8] INVERSENET: SOLVING INVERSE PROBLEMS WITH SPLITTING NETWORKS
Qi Wei1, Kai Fan2, Wenlin Wang3, Tianhang Zheng4, Amit Chakraborty5, Katherine Heller3, Changyou Chen4, Kui Ren4,6
1J.P. Morgan, USA, 2Alibaba DAMO Academy, China, 3Duke University, USA, 4SUNY at Buffalo, USA, 5Siemens Corporate Technology, China, 6Zhejiang University, China
[ID:9] HIGH-RESOLUTION DRIVING SCENE SYNTHESIS USING STACKED CONDITIONAL GANS AND SPEC- TRAL NORMALIZATION
Shaobo Lin1, Long Chen1, Qin Zou2, Wei Tian3
1Sun Yat-sen University, China, 2Wuhan University, China, 3Karlsruhe Institute of Technology, Germany
[ID:10] ZERO-SHOT LEARNING WITH FEW SEEN CLASS SAMPLES
Yuqi Huo, Jiechao Guan, Jianhong Zhang, Manli Zhang, Ji-Rong Wen, Zhiwu Lu
Renmin University of China, China
[ID:11] ATTENTIONDROP FOR CONVOLUTIONAL NEURAL NETWORKS
Zhihao Ouyang1, Yan Feng1,2, Zihao He1, Tianbo Hao1, Tao Dai1,2, Shu-Tao Xia1,2
1Tsinghua University, China, 2Peng Cheng Laboratory, China
[ID:12] MULTI-VIEW CLUSTERING VIA SIMULTANEOUSLY LEARNING GRAPH REGULARIZED LOW-RANK TENSOR REPRESENTATION AND AFFINITY MATRIX
Yongyong Chen, Xiaolin Xiao, Yicong Zhou
University of Macau, China
[ID:13] DATA AUGMENTATION FOR MONAURAL SINGING VOICE SEPARATION BASED ON VARIATIONAL AU- TOENCODER-GENERATIVE ADVERSARIAL NETWORK
Boxin He1, Shengbei Wang1, Weitao Yuan1, Jianming Wang1, Masashi Unoki2
1Tianjin Polytechnic University, China, 2Japan Advanced Institute of Science and Technology, Japan
[ID:14] TOWARDS BETTER UNCERTAINTY SAMPLING: ACTIVE LEARNING WITH MULTIPLE VIEWS FOR DEEP CONVOLUTIONAL NEURAL NETWORK
Tao He1, Xiaoming Jin1, Guiguang Ding1, Lan Yi2, Chenggang Yan3
1Tsinghua University, China, 2Cisco, USA, 3Hangzhou Dianzi University, China
[ID:15] LOCAL METRIC LEARNING BASED ON ANCHOR POINTS FOR MULTIMEDIA ANALYSIS
Chunbin Gu, Jiajun Bu, Keyue Shi, Zhi Yu, Beidou Wang, Liangcheng Li
Zhejiang University, China
[ID:16] SPARSE REGRESSION-BASED MULTIPLE SEQUENCE ALIGNMENT
Tung Doan1, Takasu Atsuhiro2
1SOKENDAI (The Graduate University for Advanced Studies), Japan, 2National Institute of Informatics, Japan
P-13: Multimedia Security, Privacy and Forensics I
Time: 15:30 - 17:00 PM
Room: 3rd Floor
Chair: Qieshi Zhang Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China
[ID:17] SINGLE IMAGE DERAINING USING A RECURRENT MULTI-SCALE AGGREGATION AND ENHANCE- MENT NETWORK
Youzhao Yang, Hong Lu
Fudan University, China
[ID:18] NEURAL NETWORK BASED PHASE COMPENSATION METHODS ON MONAURAL SPEECH SEPARA- TION
Chunpeng Wang, Jie Zhu
Shanghai Jiao Tong University, China
[ID:19] PALMGAN FOR CROSS-DOMAIN PALMPRINT ECOGNITION
Huikai Shao, Dexing Zhong, Yuhan Li
Xi’an Jiaotong University, China
[ID:20] EVENT-BASED VISION ENHANCED: A JOINT DETECTION FRAMEWORK IN AUTONOMOUS DRIVING
Jianing Li1, Siwei Dong1, Zhaofei Yu1,2, Yonghong Tian1,2, Tiejun Huang1,2
1Peking University, China, 2Pengcheng Laboratory, China
[ID:21] MULTI-DOMAIN EMBEDDING STRATEGIES FOR VIDEO STEGANOGRAPHY BY COMBINING PARTI- TION MODES AND MOTION VECTORS
Liming Zhai, Lina Wang, Yanzhen Ren
Wuhan University, China
[ID:22] Real-Time Indoor 3D Human Imaging Based on MIMO Radar Sensing
Hanqing Guo1, Nan Zhang1, Wenjun Shi1, Saeed AlQarni1, Shaoen Wu1, Honggang Wang2
1Ball State University, USA, 2University of Massachusetts Dartmouth, USA
[ID:23] MULTI-SPEAKERS SPEECH SEPARATION BASED ON MODIFIED ATTRACTOR POINTS ESTIMATION AND GMM CLUSTERING
Shanfa Ke1, Ruimin Hu1, Gang Li1, Tingzhao Wu1, Xiaochen Wang1,2, Zhongyuan Wang1
1Wuhan University, China, 2Collaborative Innovation Center of Geospatial Technolog, China
[ID:24] LEARNING A DEEP CONVOLUTIONAL NETWORK FOR SUBBAND IMAGE DENOISING
Jing Zhao1, Ruiqin Xiong1, Jizheng Xu2, Feng Wu3, Tiejun Huang1
1Peking University, China, 2ByteDance, USA, 3University of Science and Technology of China, China
[ID:25] MULTI-TASK CONVOLUTIONAL NEURAL NETWORK FOR HYPERSPECTRAL IMAGE CLASSIFICATION
Zhijie Lin, Sen Jia, Bin Deng
Shenzhen University, China
[ID:26] A RETINA-INSPIRED SAMPLING METHOD FOR VISUAL TEXTURE RECONSTRUCTION
Lin Zhu1, Siwei Dong1, Tiejun Huang1,2, Yonghong Tian1,2
1Peking University, China, 2Pengcheng Laboratory, China
P-14: Machine Learning Applications in Image and Video Coding II
Time: 15:30 - 17:00 PM
Room: 3rd Floor
Chair: Dan Zeng Shanghai University, China
[ID:27] LEARNED SCALABLE IMAGE COMPRESSION WITH BIDIRECTIONAL CONTEXT DISENTANGLEMENT NETWORK
Zhizheng Zhang, Zhibo Chen, Jianxin Lin, Weiping Li
University of Science and Technology of China, China
[ID:28] AN ATTENTION RESIDUAL NEURAL NETWORK WITH RECURRENT GREEDY APPROACH AS LOOP FIL- TER FOR INTER FRAMES
Jiabao Yao, Li Wang, Fangdong Chen, Chaoyi Lin, Shiliang Pu
Hikvision Research Institute, China
[ID:29] BAYESIAN NONNEGATIVE MATRIX FACTORIZATION WITH A TRUNCATED SPIKE-AND-SLAB PRIOR
Yuhang Liu1,2, Wenyong Dong1, Wanjuan Song1, Lei Zhang3
1Wuhan University, China, 2The University of Adelaide, Australia, 3Inception Institute of Artificial Intelligence, United Arab
Emirates
[ID:30] ENCODING COMPLEXITY CONTROL FOR LIVE VIDEO APPLICATIONS: AN INTERPRETABLE MACHINE LEARNING APPROACH
Chao Huang, Zongju Peng, Fen Chen, Qiuping Jiang, Xin Cui, Gangyi Jiang
Ningbo University, China
[ID:31] ENHANCED RESIDUAL DENSE INTRINSIC NETWORK FOR INTRINSIC IMAGE DECOMPOSITION
Risheng Liu1,2,3, Cheng Yang1,3, Long Ma1,3, Miao Zhang1,3, Xin Fan1,3, Zhongxuan Luo1,3
1Dalian University of Technology, China, 2Xidian University, China, 3Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province, China
[ID:32] NON-CONVEX TRANSFER SUBSPACE LEARNING FOR UNSUPERVISED DOMAIN ADAPTATION
Zhipeng Lin1, Zhenyu Zhao1, Tingjin Luo1, Wenjing Yang1, Yongjun Zhang2, Yuhua Tang1
1National University of Defense Technology, China, 2National Innovation Institute of Defense Technology, China
[ID:33] DISCRIMINATIVE GROUP COLLABORATIVE COMPETITIVE REPRESENTATION FOR VISUAL CLASSIFI- CATION
Jianping Gou1, Lei Wang1, Zhang Yi2, Yunhao Yuan3, Weihua Ou4, Qirong Mao1
1Jiangsu University, China, 2Sichuan University, China, 3Yangzhou University, China, 4Guizhou Normal University, China
P-15: Multimedia and Vision II
Time: 15:30 - 17:00 PM
Room: 3rd Floor
Chair: Shao-Yi Chien National Taiwan University, Taiwan
[ID:34] LARGE-SCALE DATASETS FOR GOING DEEPER IN IMAGE UNDERSTANDING
Jiahong Wu1,2, He Zheng3, Bo Zhao4, Yixin Li4, Baoming Yan4, Rui Liang1, Wenjia Wang4, Shipei Zhou4,5, Guosen Lin2, Yan- wei Fu6, Yizhou Wang4, Yonggang Wang1
1Sinovation Ventures, China, 2Ainnovation Technology Ltd, China, 3University of Chinese Academy of Sciences, China, 4Pe-
king University, China, 5Carnegie Mellon University, USA, 6Fudan University, China
[ID:35] REVISIT SURROUND-VIEW CAMERA SYSTEM CALIBRATION
Xuan Shao1, Xiao Liu1, Lin Zhang1, Shengjie Zhao1, Ying Shen1, Yukai Yang2
1Tongji University, China, 2Uppsala University, Sweden
[ID:36] DECOUPLING SEMANTIC CONTEXT AND COLOR CORRELATION WITH MULTI-CLASS CROSS BRANCH REGULARIZATION
Vishal Keshav, Tejpratap GVSL
Samsung Research Institute Bangalore, India
[ID:37] CROWD COUNTING VIA MULTI-VIEW SCALE AGGREGATION NETWORKS
Zhilin Qiu, Lingbo Liu, Guanbin Li, Qing Wang, Nong Xiao, Liang Lin
Sun Yat-sen University, China
[ID:38] PASIAM: PREDICTING ATTENTION INSPIRED SIAMESE NETWORK, FOR SPACE-BORNE SATELLITE VIDEO TRACKING
Jia Shao1, Bo Du1, Chen Wu1, Pingkun Yan2
1Wuhan University, China, 2Rensselaer Polytechnic Institute, USA
[ID:39] A RELATION NETWORK EMBEDDED WITH PRIOR FEATURES FOR FEW-SHOT CARICATURE RECOGNI- TION
Wenbo Zheng1,2, Lan Yan2,3, Chao Gou2,4, Wenwen Zhang1,2, Fei-Yue Wang2,4
1Xi’an Jiaotong University, China, 2Chinese Academy of Sciences, China, 3University of Chinese Academy of Sciences, Chi- na, 4Qingdao Academy of Intelligent Industries, China
[ID:40] A SINGLE-SHOT ORIENTED SCENE TEXT DETECTOR WITH LEARNABLE ANCHORS
Fenfen Sheng1,2, Zhineng Chen1, Tao Mei3, Bo Xu1
1Chinese Academy of Sciences, China, 2University of Chinese Academy of Sciences, China, 3JD AI Research, China
[ID:41] CONTEXT-CONSTRAINED ACCURATE CONTOUR EXTRACTION FOR OCCLUSION EDGE DETECTION
Rui Lu1, Menghan Zhou1, Anlong Ming1, Yu Zhou2
1Beijing University of Posts and Telecommunications, China, 2Huazhong University of Science and Technology, China
[ID:42] LEARNING SIMULTANEOUS FACE SUPER-RESOLUTION USING MULTISET PARTIAL LEAST SQUARES
Yun-Hao Yuan1, Jin Li1, Jianping Gou2, Yun Li1, Jipeng Qiang1, Bin Li1
1Yangzhou University, China, 2Jiangsu University, China
[ID:43] CROPPING REGION PROPOSAL NETWORK BASED FRAMEWORK FOR EFFICIENT OBJECT DETECTION ON LARGE SCALE REMOTE SENSING IMAGES
Qifeng Lin, Jianhui Zhao, Qianqian Tong, Guian Zhang, Gang Fu, Zhiyong Yuan
Wuhan University, China
[ID:44] SPECTRAL ANALYSIS NETWORK FOR DEEP REPRESENTATION LEARNING AND IMAGE CLUSTERING
Jinghua Wang1, Adrian Hilton2, Jianmin Jiang1
1Shenzhen University, China, 2University of Surrey, UK
P-16: Oral-13 to Oral-16
Time: 15:30 - 17:00 PM
Room: 3rd Floor
Chair: Lei Zhang Microsoft AI & Research, USA
[ID:45] GLOBAL AS-CONFORMAL-AS-POSSIBLE NON-RIGID REGISTRATION OF MULTI-VIEW SCANS
Zhenchao Wu1, Kun Li1, Yu-Kun Lai2, Jingyu Yang1
1Tianjin University, China, 2Cardiff University, UK
[ID:46] A LIGHT-WEIGHTED NETWORK FOR FACIAL LAND MARK DETECTION VIA COMBINED HEATMAP AND COORDINATE REGRESSION
Zhengning Wang1, Longfei Feng1, Fanwei Zeng1, Guang Hu1, Xiang Zhang1, Xia Lv1, Fengjun Zhang2
1University of Electronic Science and Techonogy of China, China, 2No.30 Institute of CETC, China
[ID:47] LIGHT WEIGHT STEREO MATCHING VIA DEEP EXTRACTION AND INTEGRATION OF LOW AND HIGH LEVEL INFORMATION
Xianzhe Xu1, Yonghong Hou1, Pichao Wang2, Zhongyu Jiang1, Wanqing Li3
1Tianjin University, China, 2Alibaba Group (U.S.) Inc., China, 3University of Wollongong, Australia
[ID:48] JUSTLOOKUP: ONE MILLISECOND DEEP FEATURE EXTRACTION FOR POINT CLOUDS BY LOOKUP TABLES
Hongxin Lin1,2, Zelin Xiao1,2, Yang Tan1,2, Hongyang Chao1, Shengyong Ding1
1Sun Yat-sen University, China, 2Pixtalks Tech, China
[ID:49] MULTIPLE GRAPH CONVOLUTIONAL NETWORKS FOR CO-SALIENCY DETECTION
Bo Jiang1, Xingyue Jiang1, Jin Tang1, Bin Luo1, Shilei Huang2
1Anhui University, China, 2PKU-HKUST Shenzhen Hong Kong Institution, China
[ID:50] QUANNET: JOINT IMAGE COMPRESSION AND CLASSIFICATION OVER CHANNELS WITH LIMITED BANDWIDTH
Lahiru Dulanjana Chamain Hewa Gamage1, Sen-ching S Cheung2, Zhi Ding1
1University of Califirnia Davis, USA, 2University of Kentucky, USA
[ID:51] HIGH EFFICIENCY LIGHT FIELD COMPRESSION VIA VIRTUAL REFERENCE AND HIERARCHICAL MV- HEVC
Jiawen Gu, Bichuang Guo, Jiangtao Wen
Tsinghua University, China
[ID:52] SELF-PACED SUBSPACE CLUSTERING
Youfa Liu, Bo Du, Lefei Zhang
Wuhan University, China
[ID:53] COLLOQUIAL IMAGE CAPTIONING
Xuri Ge, Fuhai Chen, Chen Shen, Rongrong Ji
Xiamen University, China
[ID:54] IMPROVING CAPTIONING FOR LOW-RESOURCE LANGUAGES BY CYCLE CONSISTENCY
Yike Wu1, Shiwan Zhao2, Jia Chen3, Yinng Zhang1, Xiaojie Yuan1, Zhong Su2
1Nankai University, China, 2IBM Research, USA, 3Carnegie Mellon University, USA
[ID:55] FRAMERANK: A TEXT PROCESSING APPROACH TO VIDEO SUMMARIZATION
Zhuo Lei1,2, Chao Zhang1,2, Qian Zhang2, Guoping Qiu3,4
1International Doctoral Innovation Center, China, 2The University of Nottingham Ningbo China, China, 3Shenzhen Universi- ty, China, 4University of Nottingham, UK
[ID:56] CHARACTER IMAGE SYNTHESIS BASED ON SELECTED CONTENT AND REFERENC ED STYLE EM- BEDDING
Anna Zhu, Qiyang Zhang, Xiongbo Lu, Shengwu Xiong
Wuhan University of Technology, China
[ID:57] QUERY-FREE EMBEDDING ATTACK AGAINST DEEP LEARNING
Yujia Liu, Weiming Zhang, Nenghai Yu
University of Science and Technology of China, China
[ID:58] GRAPH ATTENTION NEURAL NETWORKS FOR POINT CLOUD RECOGNITION
Zongmin li, Jun Zhang, Guanlin Li, Yujie Liu, Siyuan Li
China University of Petroleum (East China), China
[ID:59] MAXIMAL CORRELATION EMBEDDING NETWORK FOR MULTILABEL LEARNING WITH MISSING LA- BELS
Lu Li, Yang Li, Xiangxiang Xu, Shao-Lun Huang, Lin Zhang
Tsinghua University, China
[ID:60] SELF-ADAPTION MULTI-CLASSIFIER FUSION NETWORKS FOR IMAGE RECOGNITION
Zengyuan Guo, Xinzhu Ma, Haojie Li, Zhihui Wang, Pengbo Zhang
Dalian University of Technology, China
Wednesday, July 10, 2019
Wednesday, July 10, 2019
Demo Session 2
Time: 15:30 - 17:00 PM
Room: 3rd Floor
Chair: Dong Liu University of Science and Technology of China, China
[ID:61] DEMONSTRATION OF APPLICATIONS IN COMPUTER VISION AND NLP ON ULTRA POWER-EFFICIENT CNN DOMAIN SPECIFIC ACCELERATOR WITH 9.3TOPS/WATT
Baohua Sun, Lin Yang, Wenhan Zhang, Patrick Dong, Charles Young, Jason Dong, Michael Lin
Gyrfalcon Technology Inc., USA
[ID:62] LIGHT FIELD RECONSTRUCTION USING SHEARLET TRANSFORM IN TENSORFLOW
Yuan Gao1, Reinhard Koch1, Robert Bregovic2, Atanas Gotchev2
1Kiel University, Germany, 2Tampere University, Finland
[ID:63] AUTOMATIC LONG-TERM DECEPTION DETECTION IN GROUP INTERACTION VIDEOS
Chongyang Bai1, Maksim Bolonkin1, Judee Burgoon3, Chao Chen1, Norah Dunbar4, Bharat Singh2, V. S. Subrahmanian1, Zhe Wu2
1Dartmouth College, USA, 2Univerity of Maryland, USA, 3University of Arizona, USA, 4University of California Santa Barba- ra, USA
Poster Session 5 & Grand Challenge
Thursday, July 11, 2019
Thursday, July 11, 2019
P-17: Multimedia Understanding and Mixed Reality
Time: 13:30 - 15:00 PM
Room: 3rd Floor
Chair: Robert Bregovic Tampere University of Technology, Finland
[ID:1] SALIENT OBJECT DETECTION VIA RECURRENTLY AGGREGATING SPATIAL ATTENTION WEIGHTED CROSS-LEVEL DEEP FEATURES
Chang Tang1, Xinzhong Zhu2, Xinwang Liu3, Pichao Wang4
1China University of Geosciences, China, 2Zhejiang Normal University, China, 3National University of Defense Technology,
China, 4Alibaba Group (U.S.), China
[ID:2] FAST REGISTRATION FOR CROSS-SOURCE POINT CLOUDS BY USING WEAK REGIONAL AFFINITY AND PIXEL-WISE REFINEMENT
Xiaoshui Huang1, Lixin Fan2, Qiang Wu1, Jian Zhang1,4, Chun Yuan3
1University of Technology Sydney, Australia, 2Nokia Technologies, Finland, 3Graduate School at Shenzhen, Tsinghua Univer- sity, China, 4Peng Cheng Laboratory, China
[ID:3] 3D FACE REPRENTATION AND RECONSTRUCTION WITH MULTI-SCALE GRAPH CONVOLUTIONAL AU- TOENCODERS
Cunkuan Yuan1, Kun Li1, Yu-Kun Lai2, Yebin Liu3, Jingyu Yang1
1Tianjin University, China, 2Cardiff University, UK, 3Tsinghua University, China
[ID:4] VISUAL DIALOG WITH TARGETED OBJECTS
Qiang Wang, Yahong Han
Tianjin University, China
[ID:5] A NEW OBJECT SCENE FLOW ALGORITHM BASED ON SUPPORT POINTS SELECTION AND ROBUST MOVING OBJECT PROPOSAL
Zhengyang Sun1, Zongqing Lu1, Jing-Hao Xue2, Qingmin Liao1
1Graduate School at Shenzhen, Tsinghua University, China, 2University College London, UK
[ID:6] REFINING PROPOSALS WITH NEIGHBORING CONTEXTS FOR TEMPORAL ACTION DETECTION
Dashan Guo, Wei Li, Ning Xu, Jianhui Sun and Xiangzhong Fang
Shanghai Jiao Tong University, China
[ID:7] A DATA-DRIVEN FRAMEWORK FOR APPEARANCE EDITING OF MEASURED MATERIALS
Yanjun Chen1, Jie Guo1, Bingyang Hu1, Yanwen Guo1,2, Jingui Pan1
1Nanjing University, China, 2The 28th Research Institute of China Electronics Technology Group Corporation, China
[ID:8] ACTIVE SEMANTIC LABELING OF STREET VIEW POINT CLOUDS
Yang Zhou1,2, Shuhan Shen1,2, Zhanyi Hu1,2
1NLPR, Institute of Automation, Chinese Academy of Sciences, China, 2University of Chinese Academy of Sciences, China
[ID:9] VIDEO PREDICTION WITH TEMPORAL-SPATIAL ATTENTION MECHANISM AND DEEP PERCEPTUAL SIMILARITY BRANCH
Qian Wu, Wenmin Wang, Xiongtao Chen, Weimian Li
Peking University, China
[ID:10] AUTOMATIC LONG-TERM DECEPTION DETECTION IN GROUP INTERACTION VIDEOS
Chongyang Bai1, Maksim Bolonkin1, Judee Burgoon3, Chao Chen1, Norah Dunbar4, Bharat Singh2, V. S. Subrahmanian1, Zhe Wu2
1Dartmouth College, USA, 2Univerity of Maryland, USA, 3University of Arizona, USA, 4University of California Santa Barba- ra, USA
[ID:11] A NEW ROTATION-INVARIANT DEEP NETWORK FOR 3D OBJECT RECOGNITION
Yachi Zhang1, Zongqing Lu1, Jing-Hao Xue2, Qingmin Liao1
1Graduate School at Shenzhen, Tsinghua University, China, 2University College London, UK
[ID:12] LOCAL OPTICAL FLOW CONSIDERING OBJECT BOUNDARIES BY ADAPTIVE WINDOW POSITIONING
Andreas Kah, Matthias Narroschke
RheinMain University of Applied Sciences, Germany
[ID:13] MULTI-GRANULARITY REASONING FOR SOCIAL RELATION RECOGNITION FROM IMAGES
Meng Zhang1, Xinchen Liu2, Wu Liu2, Anfu Zhou1, Huadong Ma1, Tao Mei2
1Beijing University of Posts and Telecommunications, China, 2JD AI Research, China
P-18: Media Classification and Segmentation IV
Time: 13:30 - 15:00 PM
Room: 3rd Floor
Chair: Jianyu Yang Soochow University, China
[ID:14] MULTI-TIMESCALE CONTEXT ENCODING FOR SCENE PARSING PREDICTION
Xin Chen, Yahong Han
Tianjin University, China
[ID:15] PORTRAIT INSTANCE SEGMENTATION FOR MOBILE DEVICES
Lingyu Zhu1, Tinghuai Wang2, Emre Aksu2, Joni-Kristian Kamarainen1
1Tampere University, Finland, 2Nokia Technologies, Finland
[ID:16] LEARNING TO SEGMENT UNSEEN CATEGORY OBJECTS USING GRADIENT GAUSSIAN ATTENTION
Pengbo Zhang1, Zhihui Wang1, Xinzhu Ma1, Haojie Li1, Jianjun Li2
1Dalian University of Technology, China, 2Hangzhou Dianzi University, China
[ID:17] TEMPORAL SEGMENT CONVOLUTIONAL KERNEL NETWORKS FOR SEQUENCE MODELING OF VID- EOS
Fei Pan1, Yanwen Guo1, Zhicheng Yan2, Jie Guo1
1Nanjing University, China, 2Facebook Research, USA
[ID:18] SVNET: A SINGLE VIEW NETWORK FOR 3D SHAPE RECOGNITION
Shaoshuai Li, Fuyan Liu
Shanghai University, China
[ID:19] SPFUSIONNET: SKETCH SEGMENTATION USING MULTI-MODAL DATA FUSION
Fei Wang1, Shujin Lin1, Hefeng Wu2, Hanhui Li3, Ruomei Wang1, Xiaonan Luo3, Xiangjian He4
1Sun Yat-sen University, China, 2Guangdong University of Foreign Studies, China, 3Guilin University of Electronic Technolo- gy, China, 4University of Technology Sydney, Australia
[ID:20] ADAPTIVE COMPONENT EMBEDDING FOR UNSUPERVISED DOMAIN ADAPTATION
Mengmeng Jing1, Jingjing Li1, Ke Lu1, Jieyan Liu1, Zi Huang2
1University of Electronic Science and Technology of China, China, 2The University of Queensland, Australia
[ID:21] ACOUSTIC SCENE CLASSIFICATION WITH MISMATCHED RECORDING DEVICES USING MIXTURE OF EXPERTS LAYER
Truc Nguyen, Franz Pernkopf
Graz University of Technology, Germany
[ID:22] SELF-REPRESENTATION CONVOLUTIONAL NEURAL NETWORKS
Hongchao Gao1,2, Xi Wang1, Yujia Li1,2, Jizhong Han1, Songlin Hu1, Ruixuan Li3
1Institute of Information Engineering, Chinese Academy of Sciences, China, 2University of Chinese Academy of Sciences, China, 3Huazhong University of Science and Technology, China
P-19: Oral-29 to Oral-35
Time: 13:30 - 15:00 PM
Room: 3rd Floor
Chair: Honggang Wang University of Massachusetts (UMass) Dartmouth, USA
[ID:23] PEDESTRIAN RE-IDENTIFICATION BASED ON TREE BRANCH NETWORK WITH LOCAL AND GLOBAL LEARNING
Hui Li1, Meng Yang2, Zhihui Lai1, Weishi Zheng2, Zitong Yu3
1Shenzhen University, China, 2Sun Yat-sen University, China, 3University of Oulu, Finland
[ID:24] ADVERSARIAL BINARY CODING FOR EFFICIENT PERSON RE-IDENTIFICATION
Zheng Liu1, Jie Qin2, Annan Li1, Yunhong Wang1, and Luc Van Gool3
1Beihang University, China, 2Inception Institute of Artificial Intelligence, United Arab Emirates, 3Computer Vision Laborato- ry, ETH Zurich, Switzerland
[ID:25] PERSON RE-IDENTIFICATION WITH GRADUAL BACKGROUND SUPPRESSION
Yingzhi Tang, Xi Yang, Nannan Wang, Xinrui Jiang, Bin Song, Xinbo Gao
Xidian University, China
[ID:26] MULTI-BRANCH CONTEXT-AWARE NETWORK FOR PERSON RE-IDENTIFICATION
Yingxin Zhu1, Xiaoqiang Guo2, Jianlei Liu1, Zhuqing Jiang1
1Beijing University of Posts and Telecommunications, China, 2Academy of Broadcasting Science, China
[ID:27] POST-PROCESSING OF WORD REPRESENTATIONS VIA VARIANCE NORMALIZATION AND DYNAMIC EMBEDDING
Bin Wang1, Fenxiao Chen1, Angela Wang2 and C.-C. Jay Kuo1
1University of Southern California, USA, 2University of California, Berkeley, USA
[ID:28] MULTI-MODAL LANGUAGE ANALYSIS WITH HIERARCHICAL INTERACTION-LEVEL AND SELEC- TION-LEVEL ATTENTION
Dong Zhang, Liangqing Wu, Shoushan Li, Qiaoming Zhu, Guodong Zhou
Soochow University, China
[ID:29] MODELING THE CLAUSE-LEVEL STRUCTURE TO MULTIMODAL SENTIMENT ANALYSIS VIA REIN-
FORCEMENT LEARNING
Dong Zhang, Shoushan Li, Qiaoming Zhu, Guodong Zhou
Soochow University, China
[ID:30] TWICE OPPORTUNITY KNOCKS SYNTACTIC AMBIGUITY: A VISUAL QUESTION ANSWERING MODEL WITH YES/NO FEEDBACK
Jianming Wang, Wei Deng, Yukuan Sun, Yuanyuan Li, Kai Wang, Guanghao Jin
Tianjin Polytechnic University, China
[ID:31] GEOCAPSNET: GROUND TO AERIAL VIEW IMAGE GEO-LOCALIZATION USING CAPSULE NETWORK
Bin Sun1, Chen Chen2, Yingying Zhu1, Jianmin Jiang1
1Shenzhen University, China, 2University of North Carolina at Charlotte, USA
[ID:32] IMPROVING ROBUSTNESS OF DASH AGAINST NETWORK UNCERTAINTY
Bo Wang1,2, Fengyuan Ren1,2
1Beijing National Research Center for Information Science and Technology, China, 2Tsinghua University, China
[ID:33] HYBRID CONTROL-BASED ABR: TOWARDS LOW-DELAY LIVE STREAMING
Bo Wang1,2, Fengyuan Ren1,2, Chao Zhou3
1Beijing National Research Center for Information Science and Technology, China, 2Tsinghua University, China, 3Beijing
Kuaishou Technology Co., Ltd. , China
[ID:34] TAXI ORIGIN-DESTINATION DEMAND PREDICTION WITH CONTEXTUALIZED SPATIAL-TEMPORAL NETWORK
Zhilin Qiu, Lingbo Liu, Guanbin Li, Qing Wang, Nong Xiao, Liang Lin
Sun Yat-sen University, China
[ID:35] FAST IMAGE CLUSTERING BASED ON CAMERA FINGERPRINT ORDERING
Sahib Khan, Tiziano Bianchi
Politecnico di Torino, Italy
[ID:36] ENFORCING ACCESS CONTROL IN DISTRIBUTED VERSION CONTROL SYSTEMS
Xin Xu1,2, Quanwei Cai1,2, Jingqiang Lin1,2, Shiran Pan1,2, Liangqin Ren1,2
1Institute of Information Engineering, Chinese Academy of Sciences, China, 2University of Chinese Academy of Sciences, China
[ID:37] ATTRIBUTE-BASED ACCOUNTABLE ACCESS CONTROL FOR MULTIMEDIA CONTENT WITH IN-NET- WORK CACHING
Peixuan He1, Kaiping Xue1, Jie Xu1, Qiudong Xia1, Jianqing Liu2, Hao Yue3
1University of Science and Technology of China, China, 2University of Alabama in Huntsville, USA, 3San Francisco State University, USA
[ID:38] PRACTICAL IMAGE OBFUSCATION WITH PROVABLE PRIVACY
Liyue Fan
University at Albany, State University of New York, USA
[ID:39] JOINTLY SOLVING DEBLURRING AND SUPER-RESOLUTION PROBLEMS WITH DUAL SUPERVISED NETWORK
Zhenwen Liang, Dongyang Zhang, Jie Shao
University of Electronic Science and Technology of China, China
[ID:40] TWO-STAGED ACOUSTIC MODELING ADAPTION FOR ROBUST SPEECH RECOGNITION BY THE EX- AMPLE OF GERMAN ORAL HISTORY INTERVIEWS
Michael Gref 1,2, Christoph Schmidt1, Sven Behnke1,3, Joachim Köhler1
1Fraunhofer Institute for Intelligent Analysis and Information Systems, Germany, 2Niederrhein University of Applied Scienc- es, Germany, 3University of Bonn, Germany
[ID:41] AN ADAPTIVE AFFINITY GRAPH WITH SUBSPACE PURSUIT FOR NATURAL IMAGE SEGMENTATION
Yang Zhang1, Huiming Zhang1, Yanwen Guo1, Kai Lin2, Jingwu He1
1Nanjing University, China, 2Hubei University of Technology, China
[ID:42] PHASE TIME-FREQUENCY MASKING BASED SPEECH ENHANCEMENT ALGORITHM USING CIRCU- LAR MICROPHONE ARRAY
Li He, Yi Zhou, Hongqing Liu
Chongqing University of Posts and Telecommunications, China
[ID:43] LOCALITY-CONSTRAINED SPATIAL TRANSFORMER NETWORK FOR VIDEO CROWD COUNTING
Yanyan Fang1, Biyun Zhan1, Wandi Cai1, Shenghua Gao2, Bo Hu1
1Fudan University, China, 2ShanghaiTech University, China
[ID:44] SPATIAL-AWARE NON-LOCAL ATTENTION FOR FASHION LANDMARK DETECTION
Yixin Li1, Shengqin Tang2, Yun Ye3, Jinwen Ma1
1Peking University, China, 2Xi’an Jiaotong University, China, 3JD AI Research, China
[ID:45] RELATIONAL NETWORK FOR SKELETON-BASED ACTION RECOGNITION
Wu Zheng1,2, Lin Li1,2, Zhaoxiang Zhang1,2, Yan Huang1,2, Liang Wang1,2
1Institute of Automation, Chinese Academy of Sciences, China, 2University of Chinese Academy of Sciences, China
[ID:46] MULTI-VIEW LEARNING FOR VEHICLE RE-IDENTIFICATION
Weipeng Lin1, Yidong Li1, Xiaoliang Yang1, Peixi Peng2, Junliang Xing2
1Beijing Jiaotong University, China, 2Institute of Automation, Chinese Academy of Sciences, China
[ID:47] MANY COULD BE BETTER THAN ALL: A NOVEL INSTANCE-ORIENTED ALGORITHMFOR MULTI-MOD- AL MULTI-LABEL PROBLEM
Yi Zhang, Cheng Zeng, Hao Cheng, Chongjun Wang, Lei Zhang
Nanjing University, China
[ID:48] AFFECTIVE VIDEO CONTENT ANALYSES BY USING CROSS-MODAL EMBEDDING LEARNING FEA- TURES
Benchao Li1,3, Zhenzhong Chen2, Shan Li3, WeiShi Zheng1,4
1Sun Yat-Sen University, China, 2Wuhan University, China, 3Tencent, China, 4Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, ,China
[ID:49] LEARNING A 3D GAZE ESTIMATOR WITH IMPROVED ITRACKER COMBINED WITH BIDIRECTIONAL LSTM
Xiaolong Zhou, Jianing Lin, Jiaqi Jiang, Shengyong Chen
Zhejiang University of Technology, China
[ID:50] DETECTION OF OCCLUDED ROAD SIGNS ON AUTONOMOUS DRIVING VEHICLES
Jingda Guo, Xianwei Cheng, Qi Chen, Qing Yang
University of North Texas, USA
Thursday, July 11, 2019
Thursday, July 11, 2019
Grand Challenge
Time: 13:30 - 15:00 PM
Room: 3rd Floor
Chair: Jiaying Liu Peking University, China
[ID:51] SALIENCY PREDICTION VIA MULTI-LEVEL FEATURES AND DEEP SUPERVISION FOR CHILDREN WITH AUTISM SPECTRUM DOISORDER
Weijie Wei1, Zhi Liu1, Lijin Huang1, Alexis Nebout2, Olivier Le Meur2
1Shanghai University, China, 2 University of Rennes 1, France
[ID:52] VISUAL ATTENTION MODELING FOR AUTISM SPECTRUM DISORDER BY U-NET
Yuming Fang, Hanqin Huang, Boyang Wan, and Yifan Zuo
Jiangxi University of Finance and Economics, China
[ID:53] PREDICTING SALIENCY MAPS FOR ASD PEOPLE
Alexis Nebout1, Weijie Wei2, Zhi Liu2, Lijin Huang2, Olivier Le Meur1
1University of Rennes 1, France, 2Shanghai University, China
[ID:54] CLASSIFYING AUTISM SPECTRUM DISORDER BASED ON SCANPATHS AND SALIENCY
Mikhail Startsev, Michael Dorr
Technical University of Munich, Germany
[ID:55] EXPLOITING VISUAL BEHAVIOUR FOR AUTISM SPECTRUM DISORDER IDENTIFICATION
Giuliano Arru, Pramit Mazumdar, Federica Battisti
Roma Tre University, Italy
[ID:56] SP-ASDNET: CNN-LSTM BASED ASD CLASSIFICATION MODEL USING OBSERVER SCANPATHS
Yudong Tao, Mei-Ling Shyu
University of Miami, USA
[ID:57] PREDICTING AUTISM DIAGNOSIS USING IMAGE WITH FIXATIONS AND SYNTHETIC SACCADE PATTERNS
Chongruo Wu1, Sidrah Liaqat2, Sen-ching Cheung2, Chen-Nee Chuah1, Sally Ozonoff1
1University of California, Davis, USA, 2University of Kentucky, USA
[ID:58] A SIMPLE BUT USEFUL MODEL FOR CLASSIFYING ASD AND NORMAL VIEWERS USING GAZE DATA AND LINEAR REGRESSION
S. Xu, J. Yan, M. Hu
Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, China
Poster Session 6
Thursday, July 11, 2019
Thursday, July 11, 2019
P-20: Multimedia Communications, Networking and Mobility
Time: 15:30 - 17:00 PM
Room: 3rd Floor
Chair: Tsung-Jung Liu National Chung Hsing University, Taiwan
[ID:1] TIYUNTSONG: A SELF-PLAY REINFORCEMENT LEARNING APPROACH FOR ABR VIDEO STREAMING
Tianchi Huang, Xin Yao, Chenglei Wu, Rui-Xiao Zhang, Zhengyuan Pang, Lifeng Sun
Tsinghua University, China
[ID:2] EDGE-BOOST: ENHANCING MULTIMEDIA DELIVERY WITH MOBILE EDGE CACHING IN 5G-D2D NET- WORKS
Venkatraman Balasubramanian1, Mu Wang1, Martin Reisslein1, Changqiao Xu2
1Arizona State University, USA, 2University of Posts and Telecommunications, China
[ID:3] 3D MESH BASED INTER-IMAGE PREDICTION FOR IMAGE SET COMPRESSION
Hao Wu1, Xiaoyan Sun2, Jingyu Yang1, Feng Wu3
1Tianjin University, China, 2Microsoft Research Asia, China, 3University of Science and Technology of China, China
[ID:4] FAST INTER MODE PREDICTIONS FOR SHVC
Dayong Wang1, Yu Sun2, Weisheng Li1, Ce Zhu3, Frederic Dufaux4
1Chongqing University of Posts and Telecommunications, China, 2University of Central Arkansas, USA, 3University of Elec- tronic Science and Technology of China, China, 4CNRS - CentraleSupélec – Université Paris-Sud, France
[ID:5] HIT RATIO DRIVEN MOBILE EDGE CACHING SCHEME FOR VIDEO ON DEMAND SERVICES
Xing Chen, Lijun He, Shang Xu, Shibo Hu, Qingzhou Li, Guizhong Liu
Xi’an Jiao Tong University, China
[ID:6] QOE-DRIVEN MOBILE STREAMING: A LOCATION-AWARE APPROACH
Fang Liu, Wei Zhang, Yonggang Wen
Nanyang Technological University, Singapore
[ID:7] ENERGY EFFICIENT TRANSMISSION OF 3D MESHES OVER MMWAVE-BASED MASSIVE MIMO SYS- TEMS
Aris Lalos1, Gerasimos Arvanitis2, Evangelos Vlachos3, Konstantinos Moustakas2
1Industrial System Institute, Greece, 2University of Patras, Greece, 3University of Edinburgh, UK
[ID:8] IDENTIFYING INFLUENTIAL USERS IN MOBILE DEVICE-TO-DEVICE SOCIAL NETWORKS TO PROMOTE OFFLINE MULTIMEDIA CONTENT PROPAGATION
Hao Fan, Xu Tong, Qing Zhang, Tianxiang Zhang, Chenyang Wang and Xiaofei Wang
Tianjin University, China
Thursday, July 11, 2019
Thursday, July 11, 2019
P-21: Object Detection II
Time: 15:30 - 17:00 PM
Room: 3rd Floor
Chair: Ye Luo Tongji University, China
[ID:9] ACCURATE AND EFFICIENT OBJECT DETECTION WITH CONTEXT ENHANCEMENT BLOCK
Yuhao Chen1, Min Zhao1, Xin Tan2, Hong Tang1, Dihua Sun1
1Chongqing University, China, 2Shanghai Jiao Tong University, China
[ID:10] MASK GUIDED KNOWLEDGE DISTILLATION FOR SINGLE SHOT DETECTOR
Yousong Zhu1,2, Chaoyang Zhao1,2, Chenxia Han3, Jinqiao Wang1,2, Hanqing Lu1,2
1Institute of Automation, Chinese Academy of Sciences, China, 2University of Chinese Academy of Sciences, China, 3Wuhan
University, China
[ID:11] VIDEO TEXT DETECTION WITH FULLY CONVOLUTIONAL NETWORK AND TRACKING
Yang Wang, Lan Wang, Feng Su, Jiahao Shi
Nanjing University, China
[ID:12] CASCADE REGION PROPOSAL NETWORKS FOR OBJECT DETECTION IN THE WILD
DongMing Yang1,2, YueXian Zou1,2
1Peking University, China, 2Peng Cheng Laboratory, China
[ID:13] TRACKING ASSISTED FASTER VIDEO OBJECT DETECTION
Wenfei Yang, BinLiu, Weihai Li, Nenghai Yu
University of Science and Technology of China, China
[ID:14] REFINETEXT: REFINING MULTI-ORIENTED SCENE TEXT DETECTION WITH A FEATURE REFINEMENT MODULE
Pengyuan Xie, Jing Xiao, Yang Cao, Jia Zhu, Asad Khan
South China Normal University, China
[ID:15] MULTI-SCALE CAPSULE ATTENTION-BASED SALIENT OBJECT DETECTION WITH MULTI-CROSSED LAYER CONNECTIONS
Qi Qi1, Sanyuan Zhao1, Jianbing Shen1, Kin-Man Lam2
1Beijing Institute of Technology, China, 2The Hong Kong Polytechnic University, China
P-22: Artificial Intelligence for Multimedia
Time: 15:30 - 17:00 PM
Room: 3rd Floor
Chair: Kunal Swami Samsung, Korea
[ID:16] CONTINUOUS BIDIRECTIONAL OPTICAL FLOW FOR VIDEO FRAME SEQUENCE INTERPOLATION
Donghao Gu, Zhaojing Wen, Wenxue Cui, Rui Wang, Feng Jiang, Shaohui Liu
Harbin Institute of Technology, China
[ID:17] ROBUST DEEP TRACKING WITH TWO-STEP AUGMENTATION DISCRIMINATIVE CORRELATION FIL- TERS
Chunhui Zhang1,2, Shiming Ge1, Yingying Hua1,2, Dan Zeng3
1Institute of Information Engineering, Chinese Academy of Sciences, China, 2University of Chinese Academy of Sciences,
China, 3Shanghai University, China
[ID:18] EFFICIENT IMPLEMENTATION OF CONVOLUTIONAL NEURAL NETWORKS WITH END TO END INTE- GER-ONLY DATAFLOW
Yiwu Yao, Bin Dong, Yuke Li, Weiqiang Yang, Haoqi Zhu
Yidun Lab, NetEase Inc, China
[ID:19] LEARNING MOTION-AWARE POLICIES FOR ROBUST VISUAL TRACKING
Qianqian Wang, Liansheng Zhuang, Ning Wang, Wengang Zhou, Houqiang Li
University of Science and Technology of China, China
[ID:20] KNOWLEDGE DISTILLATION WITH CATEGORY-AWARE ATTENTION AND DISCRIMINANT LOGIT LOSSES
Lei Jiang, Wengang Zhou, Houqiang Li
University of Science and Technology of China, China
[ID:21] UNSUPERVISED LEARNING OF DEPTH AND EGO-MOTION WITH SPATIAL-TEMPORAL GEOMETRIC CONSTRAINTS
Anjie Wang1, Yongbin Gao1, Zhijun Fang1, Xiaoyan Jiang1, Shanshe Wang2, Siwei Ma2, Jenq-Neng Hwang3
1Shanghai University of Engineering Science, China, 2Peking University, China, 3University of Washington, USA
[ID:22] LEARNING MINIMAL INTRA-GENRE MULTIMODAL EMBEDDING FROM TRAILER CONTENT AND RE- ACTOR EXPRESSIONS FOR BOX OFFICE PREDICTION
Ming-Ya Ko, Jeng-Lin Li, Chi-Chun Lee
National Tsing Hua University, Taiwan
[ID:23] DEEP PAIRWISE RANKING WITH MULTI-LABEL INFORMATION FOR CROSS-MODAL RETRIEVAL
Yangwo Jian, Jing Xiao, Yang Cao, Asad Khan, Jia Zhu
South China Normal University, China
[ID:24] CORRELATION FILTER TRACKING WITH ADAPTIVE PROPOSAL SELECTION FOR ACCURATE SCALE ESTIMATION
Luo Xiong, Yanjie Liang, Yan Yan, Hanzi Wang
Xiamen University, China
[ID:25] SUPERVISED CONSISTENT AND SPECIFIC HASHING
Haitao Wang, Min Meng, Hui Chen, JiGang Wu
Guangdong University of Technology, China
[ID:26] MOMENTUM BASED ON ADAPTIVE BOLD DRIVER
Shengdong Li1,2, Xueqiang Lv3
1Renmin University of China, China, 2Langfang Yanjing Vocational Technical College, China, 3Beijing Information Science and Technology University, China
[ID:27] A LIGHTWEIGHT NEURAL NETWORK BASED HUMAN DEPTH RECOVERY METHOD
Meiyu Huang1, Xueshuang Xiang1, Yao Xu1, Yiqiang Chen2
1Qian Xuesen Laboratory of Space Technology, China Academy of Space Technology, China, 2Institute of Computing Tech- nology, Chinese Academy of Sciences, China
P-23: Multimedia Quality Assessment and Metrics
Time: 15:30 - 17:00 PM
Room: 3rd Floor
Chair: Federica Battisti Roma Tre University, Italy
[ID:28] EVALUATION OF DEFOGGING: A REAL-WORLD BENCHMARK DATASET, A NEW CRITERION AND BASELINES
Shiyu Zhao1, Lin Zhang1, Shuaiyi Huang2, Ying Shen1, Shengjie Zhao1, Yukai Yang3
1Tongji University, China, 2ShanghaiTech University, China, 3Uppsala University, Sweden
[ID:29] RESA: A REAL-TIME EVALUATION SYSTEM FOR ABR
Yanan Wang, Haili Wang, Jiaoyang Shang, Hu Tuo
iQIYI, Inc, China
[ID:30] BLIND IMAGE SHARPNESS ASSESSMENT AND ENHANCEMENT VIA DEEP AUXILIARY LEARNING
Qingbo Wu, Rui Ma, King N. Ngan, Hongliang Li, and Fanman Meng
University of Electronic Science and Technology of China, China
[ID:31] END-TO-END BLIND IMAGE QUALITY ASSESSMENT WITH CASCADED DEEP FEATURES
Jinjian Wu, Jupo Ma, Fuhu Liang, Weisheng Dong, Guangming Shi
Xidian University, China
[ID:32] ENCODING DISTORTIONS FOR MULTI-TASK FULL-REFERENCE IMAGE QUALITY ASSESSMENT
Chen Huang1,2, Tingting Jiang1, Ming Jiang1
1Peking University, China, 2Baidu Inc., China
[ID:33] CAUSAL ANALYSIS OF THE UNSATISFYING EXPERIENCE IN REALTIME MOBILE MULTIPLAYER GAMES IN THE WILD
Yuan Meng1,4, Shenglin Zhang2, Zijie Ye1, Benliang Wang2, Zhi Wang1, Yongqian Sun2, Qitong Liu3, Shuai Yang3, Dan Pei1,4
1Tsinghua University, China, 2Nankai University, China, 3Tencent, China, 4Beijing National Research Center for Information Science and Technology, China
Thursday, July 11, 2019
Thursday, July 11, 2019
P-24: Oral-25 to Oral-28
Time: 15:30 - 17:00 PM
Room: 3rd Floor
Chair: Kuan-Hsien Liu National Taichung University of Science and Technology, Taiwan
[ID:34] DYNAMIC CASCADED REGRESSION NETWORK WITH REINFORCEMENT LEARNING FOR ROBUST FACE ALIGNMENT
Zhihao Zhang, Liansheng Zhuang, Wengang Zhou, Houqiang Li
University of Science and Technology of China, China
[ID:35] DEEP LEARNING FACE HALLUCINATION VIA ATTRIBUTES TRANSFER AND ENHANCEMENT
Mengyan Li, Yuechuan Sun, Zhaoyu Zhang, Haonian Xie and Jun Yu
University of Science and Technology of China, China
[ID:36] EMOTION RECOGNITION FROM PHYSIOLOGICAL SIGNALS USING MULTI-HYPERGRAPH NEURAL NETWORKS
Junjie Zhu1, Xibin Zhao1, Han Hu2, Yue Gao1
1Tsinghua University, China, 2Beijing Institute of Technology, China
[ID:37] GPS: GROUP PEOPLE SEGMENTATION WITH DETAILED PART INFERENCE
Yue Liao1, Tianrui Hui1, Chen Gao1, Si Liu2, Yao Sun3, Hefei Ling4, Bo Li2
1Institute of Information Engineering, Chinese Academy of Sciences, China, 2Beihang University, China, 3iie, China,
4Huazhong University of Science and Technology, China
[ID:38] MULTI-LABEL IMAGE RECOGNITION WITH JOINT CLASS-AWARE MAP DISENTANGLING AND LABEL CORRELATION EMBEDDING
Zhao-Min Chen1,2 Xiu-Shen Wei2, Xin Jin, 2Yanwen Guo1,3
1Nanjing University, China, 2Megvii Technology, China, 3Science and Technology on Information Systems Engineering Labo- raty, China
[ID:39] REAL TIME COMPRESSED VIDEO OBJECT SEGMENTATION
Zhentao Tan, Bin Liu, Weihai Li, Nenghai Yu
University of Science and Technology of China, China
[ID:40] ACCURATE AND FAST FINE-GRAINED IMAGE CLASSIFICATION VIA DISCRIMINATIVE LEARNING
Zhihui Wang1, Shijie Wang1, Pengbo Zhang1, Haojie Li1, Bo Liu2
1Dalian University of Technology, China, 2Shanghai Jiao Tong University, China
[ID:41] POSE2BODY: POSE-GUIDED HUMAN PARTS SEGMENTATION
Zhong Li1, Xin Chen2, Wangyiteng Zhou2, Yingliang Zhang2, Jingyi Yu2
1University of Delaware, USA, 2ShanghaiTech University, China
[ID:42] RESIDUAL MAGNIFIER: A DENSE INFORMATION FLOW NETWORK FOR SUPER RESOLUTION
Zhan Shu1, Mengcheng Cheng1, Biao Yang1, Zhuo Su1, Xiangjian He2,3
1Sun Yat-sen University, China, 2Minjiang University, China, 3University of Technology Sydney, Australia
[ID:43] EVERYONE IS A CARTOONIST: SELFIE CARTOONIZATION WITH ATTENTIVE ADVERSARIAL NET- WORKS
Xinyu Li, Wei Zhang, Tong Shen, Tao Mei
JD AI Research, China
[ID:44] SCALE-AWARE DEEP NETWORK WITH HOLE CONVOLUTION FOR BLIND MOTION DEBLURRING
Jichun Li, Ke Li, Bo Yan
Fudan University, China
[ID:45] REMOVING RAIN IN VIDEOS: A LARGE-SCALE DATABASE AND A TWO-STREAM CONVLSTM AP- PROACH
Tie Liu, Mai Xu and Zulin Wang
Beihang University, China
[ID:46] TOWARDS QOS-AWARE CLOUD LIVE TRANSCODING: A DEEP REINFORCEMENT LEARNING AP- PROACH
Zhengyuan Pang, Lifeng Sun, Tianchi Huang, Zhi Wang, Shiqiang Yang
Tsinghua University, China
[ID:47] HIGH SPEED RECURRENT REGRESSION NETWORK FOR VISUAL TRACKING
Ding Ma, Xiangqian Wu
Harbin Institute of Technology, China
[ID:48] PAAE: A UNIFIED FRAMEWORK FOR PREDICTING ANCHOR LINKS WITH ADVERSARIAL EMBEDDING
Yanmin Shang1, Zhezhou Kang1, Yanan Cao1, Dongjie Zhang1, Yangxi Li2, Yang Li3, Yanbing Liu1
1Institute of Information Engineering, Chinese Academy of Sciences, China, 2National Computer Network Emergency Re- sponse technical Team, China, 3State Information Center, China
[ID:49] MANIFOLD ALIGNMENT AND DISTRIBUTION ADAPTATION FOR UNSUPERVISED DOMAIN ADAPTA- TION
Ying Li, Lin Cheng, Yaxin Peng, Zhijie Wen, Shihui Ying
Shanghai University, China
