Oral Sessions


Tuesday, July 9, 2019

Tuesday, July 9, 2019


Best Paper Session

Time: 10:00 - 11:00 AM


Room: 3CD


Chair: Yonggang Wen Nanyang Technological University, Singapore Marta Mrak BBC, UK


10:00 AN END-TO-END ARCHITECTURE FOR CLASS-INCREMENTAL OBJECT DETECTION WITH KNOWLEDGE 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


10:15 REAL-TIME INDOOR SCENE RECONSTRUCTION WITH RGBD AND INERTIAL IN PUT


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 Science and Technology of China, China


10:30 DOUBLY SEMI-SUPERVISED MULTIMODAL ADVERSARIAL LEARNING FOR CLASSIFICATION, GENERATION AND RETRIEVAL


Changde Du1, Changying Du2, Huiguang He1


1Institute of Automation Chinese Academy of Sciences, China, 2Qihoo 360 Search Lab, China


10:45 TOWARDS DIGITAL RETINA IN SMART CITIES: A MODEL GENERATION, UTILIZATION AND COM- MUNICATION PARADIGM


Yihang Lou1,4, Ling-Yu Duan1,4, Yong Luo1,4, Ziqian Chen1,4, Tongliang Liu2, Shiqi Wang3, Wen Gao1,4


1Peking University, China, 2University of Sydney, Australia, 3City University of Hongkong, China,

4The Peng Cheng Laboratory, Shenzhen, China


O-01: Content Recommendation and Cross-modal Hashing


Time: 14:00 - 15:00 PM


Room: 3CD


Chair: Chengcui Zhang University of Alabama at Birmingham, USA


14:00 SDP: AN IMPROVED BASELINE ESTIMATION MODEL BASED ON STANDARD DEVIATION PRO- PORTION


Zhenhua Tan, Danke Wu, Liangliang He, Qiuyun Chang, Bin Zhang


Northeastern University, China


14:15 CITATION RECOMMENDATION BASED ON WEIGHTED HETEROGENEOUS IN FORMATION NET- WORK CONTAINING SEMANTIC LINKING


Jie Chen, Yang Liu, Shu Zhao, Yanping Zhang


Anhui University, China


14:30 FUSION-SUPERVISED DEEP CROSS-MODAL HASHING


Li Wang, Lei Zhu, En Yu, Jiande Sun, Huaxiang Zhang


Shandong Normal University, China


14:45 DOMAIN UNCERTAINTY BASED ON INFORMATION THEORY FORCROSS-MODAL HASH RETRIEV- AL

Wei Chen1, Nan Pu1, Yu Liu2, Erwin M. Bakker1, Michael S. Lew1,


1Leiden University, Holland, 2ESAT-PSI, KU Leuven, Belgium


O-02: Development of Multimedia Standards and Related Research


Time: 14:00 - 15:00 PM

Room: 3HI

Chair: Cheolkon Jung Xidian University, China


14:00 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


14:15 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


14:30 TWO-STAGE FAST MULTIPLE TRANSFORM SELECTION ALGORITHM FOR VVC INTRA COD- ING


Ting Fu1, Hao Zhang 1, Fan Mu1, Huanbang Chen2


1Central South University, China, 2Huawei Base, China


14:45 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., San Diego CA. 92122 USA, USA


O-03: Classification and Low Shot Learning


Time: 14:00 - 15:00 PM


Room: 5BC


Chair: Yu-Gang Jiang Fudan University, China


14:00 AMS-SFE: TOWARDS AN ALIGNMENT OF MANIFOLD STRUCTURES VIA SEMANTIC FEATU- REEXPANSION FOR ZERO-SHOT LEARNING


Jingcai Guo, Song Guo


The Hong Kong Polytechnic University, China


14:15 LOW-SHOT PALMPRINT RECOGNITION BASED ON META-SIAMESE NET WORK


Xuefeng Du1, Dexing Zhong1,2, Pengna Li1


1Xi’an Jiaotong University, China, 2Research Institute of Xi’an Jiaotong University, China


14:30 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, 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


14:45 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


O-04: 3D Media Computing


Time: 14:00 - 15:00 PM


Room: 5DE


Chair: Dan Zeng Shanghai University, China


14:00 FEATURE-AWARE AND CONTENT-WISE DENOISING OF 3D STATIC AND DY NAMIC MESHES USING DEEP AUTOENCODERS


Gerasimos Arvanitis1, Aris S. Lalos2, and Konstantinos Moustakas1


1University of Patras, Greece, 2“ATHENA” Research Center, Greece


14:15 REAL-TIME MONOCULAR VISUAL SLAM BY COMBINING POINTS AND LINES


Xinyu Wei, Jun Huang, Xiaoyuan Ma


Shanghai Advanced Research Institute, China


14:30 F-NUMBER ADAPTATION FOR MAXIMIZING THE SENSOR USAGE OF LIGHT FIELD CAMER- AS


Chuanpu Li, Xin Jin, Junke Li and Qionghai Dai


Shenzhen Key Lab of Broadband Network and Multimedia, China


14:45 BLIND CALIBRATION FOR FOCUSED PLENOPTIC CAMERAS


Xufu Sun, Xin Jin, Pei Wang, Yanqin Chen and Qionghai Dai


Shenzhen Key Lab of Broadband Network and Multimedia, China


O-05: Special Session "Pedestrian Detection, Tracking and Re-identification in

Videos"


Time: 15:30 - 16:30 PM


Room: 3CD


Chair: Guiguang Ding Tsinghua University, China


Sicheng Zhao University of California, Berkeley, USA Jungong Han Lancaster University, UK


15:30 PARTICLE SWARM LOSS FOR LIGHTWEIGHT OBJECT DETECTION


Peizhen Zhang1,2,4, Feng Zheng3, Junlong Du2, Jun Zhang2, Xiaowei Guo2, Wei-Shi Zheng1,4


1Sun Yat-sen University, China, 2Youtu Lab, Tencent, China, 3Southern University of Science and Technology, China,

4Key Laboratory of Machine Intelligence and Advanced Computing, China, Ministry of Education, China


15:45 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


16:00 TRUNCATED GRADIENT CONFIDENCE-WEIGHTED BASED ONLINE LEARNING FOR IMBAL- ANCE STREAMING DATA


Ji Hu1, Chenggang Yan1, Xing Liu1, Jiyong Zhang1, Dongliang Peng1, Yi Yang2


1HangZhou DianZi University, China, 2UTS, Australia


16:15 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, 3Benha University, Egypt, 4Shenzhen Academy of Aerospace Technology, China


O-06: Special Session "Multimedia Technologies Empowering Retail Experi- ences"


Time: 15:30 - 16:30 PM


Room: 3HI


Chair: Wu Liu JD AI Research, China


Liang Zheng Australian National University, Australia Yi Yang University of Technology Sydney, Australia Lexing Xie Australian National University, Australia


15:30 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


15:45 CONTEXT-AWARE AFFECTIVE GRAPH REASONING FOR EMOTION RECOGNITION


Minghui Zhang, Yumeng Liang, Huadong Ma


Beijing University of Posts and Telecommunications, China


16:00 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


16:15 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


O-07: 3D and Low Level Vision


Time: 15:30 - 16:30 PM


Room: 5BC


Chair: Wei Hu Peking University, China


15:30 UNSUPERVISED MONOCULAR DEPTH ESTIMATION BASED ON DUAL ATTENTION MECHA- NISM 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 Technology of Liaoning Province, China


15:45 TOWARDS HIGH-QUALITY INTRINSIC IMAGES IN THE WILD


Gang Fu1, Qing Zhang2, Chunxia Xiao1


1Wuhan University, China, 2Sun Yat-sen University, China


16:00 UNSUPERVISED LEARNING FOR OPTICAL FLOW ESTIMATION USING PYRAMID CONVOLU- TION 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 Tech- nology, Sun Yat-sen University, China, 3Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China


16:15 MAST: MASK-ACCELERATED SHEARLET TRANSFORM FOR DENSELY-SAMPLED LIGHT FIELD RECONSTRUCTION


Yuan Gao1, Robert Bregovic2, Atanas Gotchev2, Reinhard Koch1


1Kiel University, German, 2Tampere University, Finland


O-08: Object Detection I


Time: 15:30 - 16:30 PM


Room: 5DE


Chair: Wengang Zhou University of Science and Technology of China, China


15:30 CODA: COUNTING OBJECTS VIA SCALE-AWARE ADVERSARIAL DENSITY ADAPTION


Li Wang1, Yongbo Li2, Xiangyang Xue1


1Fudan University, China, 2Megvii Inc (Face++), China


15:45 PDNET: PRIOR-MODEL GUIDED DEPTH-ENHANCED NETWORK FOR SALIENT OBJECT


Chunbiao Zhu, Xing Cai, Kan Huang, Thomas H Li, Ge Li


SECE, China, Shenzhen Graduate School, China, Peking University, China


16:00 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


16:15 MASK-MOST NET: MASK APPROXIMATION BASED MULTI-ORIENTED SCENE TEXT DETEC- TION NETWORK


Xiaobao Guo1, Jinxing Li2, Bingzhi Chen1, Guangming Lu1


1Harbin Institute of Technology (Shenzhen), China, 2The Chinese University of Hong Kong (Shenzhen), China


O-09: Emerging Applications of Deep Learning


Time: 16:45 - 17:45 PM


Room: 3CD


Chair: Aris Lalos Industrial System Institute, Greece


16:45 DMPR-PS: A NOVEL APPROACH FOR PARKING-SLOT DETECTION USING DIRECTIONAL MARKING-POINT REGRESSION


Junhao Huang1, Lin Zhang1, Ying Shen1, Huijuan Zhang1, Shengjie Zhao1, Yukai Yang2


1Tongji University, China, 2Uppsala University, Sweden


17:00 ADAPTING SEMANTIC SEGMENTATION OF URBAN SCENES VIA MASK- AWARE GATED DIS- CRIMINATOR


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


17:15 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


17:30 Z-ORDER RECURRENT NEURAL NETWORKS FOR VIDEO PREDICTION


Jianjin Zhang, Yunbo Wang, Mingsheng Long, Jianmin Wang, and Philip S. Yu


Tsinghua University, China


O-10: Multimedia Quality Assessment and Enhancement


Time: 16:45 - 17:45 PM


Room: 3HI


Chair: Chun-Shien Lu Academia Sinica, China


16:45 ENERGY-BASED RECURRENT MODEL FOR STOCHASTIC MODELING OF MUSIC


Yingru Liu1, Dongliang Xie2, Xin Wang1


1Stony Brook University, USA, 2Peking University, China


17:00 RESIDUAL FRAME FOR NOISY VIDEO CLASSIFICATION ACCORDING TO PERCEPTUAL QUALITY IN CONVOLUTIONAL NEURAL NETWORKS


Huaixuan Zhang1, Yuhai Lan3, Tao Dai1,2, Ruizhi Qiao 4, Ying Xu 1, Yao Yao 1, 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


17:15 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


17:30 COLLABORATIVE DEEP REINFORCEMENT LEARNING FOR IMAGE CROPPING


Zhuopeng Li, Xiaoyan Zhang


Shenzhen University, China


O-11: Multimedia for Society and Health

Time: 16:45 - 17:45 PM


Room: 5BC


Chair: Wolfgang Hürst Utrecht University, Holland


16:45 SIMILARITY-AWARE DEEP ADVERSARIAL LEARNING FOR FACIAL AGE ESTIMATION


Penghui Sun, Hao Liu, Xing Wang, Zhenhua Yu1, Suping Wu


Ningxia University, Yinchuan, China


17:00 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


17:15 VIDEO-BASED EARLY ASD DETECTION VIA TEMPORAL PYRAMID NETWORKS


Yuan Tian, Xiongkou Min, Guangtao Zhai, Zhiyong Gao


Shanghai Jiao Tong Unversity, China


17:30 AUTOMATIC USER CATEGORIZATION THROUGH LARGE TRANSACTION DATA


Ying Zhang, YinJia Zhang, Qinpei Zhao, Weixiong Rao


Tongji University, China


O-12: Immersive Media

Time: 16:45 - 17:45 PM


Room: 5DE


Chair: Fernando Pereira Instituto Superior Técnico, Portugal


16:45 FEATURE PRESERVING AND UNIFORMITY-CONTROLLABLE POINT CLOUD SIMPLIFICATION ON GRAPH


Junkun Qi, WeiHu, Zongming Guo


Peking University, China


17:00 360SRL: A SEQUENTIAL REINFORCEMENT LEARNING APPROACH FOR ABR TILE-BASED 360 VID- EO STREAMING


Jun Fu, Xiaoming Chen, Zhizheng Zhang, Shilin Wu, Zhibo Chen


University of Science and Technology of China, China


17:15 CONTENT-AWARE PERSPECTIVE PROJECTION OPTIMIZATION FOR VIEWPORT RENDERING OF

360° IMAGES


Falah Jabar, Joao Ascenso, Maria Paula Queluz


Universidade de Lisboa, Portugal


17:30 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


O-13: 3D and Stereo Computing

Time: 14:00 - 15:00 PM


Room: 3CD


Chair: Joao Ascenso Instituto Superior Técnico, Portugal


14:00 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


14:15 A LIGHT-WEIGHTED NETWORK FOR FACIAL LAND MARK DETECTION VIA COMBINED HEAT- MAP 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


14:30 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., 3University of Wollongong, Australia


14:45 JUSTLOOKUP: ONE MILLISECOND DEEP FEATURE EXTRACTION FOR POINT CLOUDS BY LOOK- UP TABLES


Hongxin Lin1,2, Zelin Xiao1,2, Yang Tan1,2, Hongyang Chao1, Shengyong Ding1


1Sun Yat-sen University, China, 2Pixtalks Tech, China


O-14: Machine Learning Applications in Image and Video Coding I

Time: 14:00 - 15:00 PM


Room: 3HI


Chair: Frederic Dufaux Universite Paris-Saclay, France


14:00 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


14:15 QUANNET: JOINT IMAGE COMPRESSION AND CLASSIFICATION OVER CHANNELS WITH LIMIT- ED BANDWIDTH


Lahiru Dulanjana Chamain Hewa Gamage1, Sen-ching S Cheung2, Zhi Ding1


1University of Califirnia Davis, USA, 2University of Kentucky, USA


14:30 HIGH EFFICIENCY LIGHT FIELD COMPRESSION VIA VIRTUAL REFERENCE AND HIERARCHI- CAL MV-HEVC


Jiawen Gu, Bichuang Guo, Jiangtao Wen


Tsinghua University, China


14:45 SELF-PACED SUBSPACE CLUSTERING


Youfa Liu, Bo Du, Lefei Zhang


Wuhan University, China


O-15: Vision, Language and Text Processing


Time: 14:00 - 15:00 PM


Room: 5BC


Chair: Jiande Sun Shandong University, China


14:00 COLLOQUIAL IMAGE CAPTIONING


Xuri Ge, Fuhai Chen, Chen Shen, Rongrong Ji


Xiamen University, China


14:15 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, China, 3Carnegie Mellon University, USA


14:30 FRAMERANK: A TEXT PROCESSING APPROACH TO VIDEO SUMMARIZATION


Zhuo Lei1,2, Chao Zhang1,2, Qian Zhang2, Guoping Qiu3,4


1International Doctoral Innovation Center, UK 2The University of Nottingham Ningbo China, China, 3Shenzhen Uni- versity, China, 4University of Nottingham, UK


14:45 CHARACTER IMAGE SYNTHESIS BASED ON SELECTED CONTENT AND REFERENC ED STYLE EMBEDDING


Anna Zhu, Qiyang Zhang, Xiongbo Lu, Shengwu Xiong


Wuhan University of Technology, China


O-16: Media Classification and Segmentation II


Time: 14:00 - 15:00 PM


Room: 5DE


Chair: Zhu Li University of Missouri, USA


14:00 QUERY-FREE EMBEDDING ATTACK AGAINST DEEP LEARNING


Yujia Liu, Weiming Zhang, Nenghai Yu


University of Science and Technology of China, China


14:15 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


14:30 MAXIMAL CORRELATION EMBEDDING NETWORK FOR MULTILABEL LEARNING WITH MISS- ING LABELS


Lu Li, Yang Li, Xiangxiang Xu, Shao-Lun Huang, Lin Zhang


Tsinghua university, China


14:45 SELF-ADAPTION MULTI-CLASSIFIER FUSION NETWORKS FOR IMAGE RECOGNITION


Zengyuan Guo, Xinzhu Ma, Haojie Li, Zhihui Wang, Pengbo Zhang


Dalian University of Technology, China


O-17: AI for Human Understanding

Time: 15:30 - 16:30 PM


Room: 3CD


Chair: Bin Liu University of Science and Technology of China, China


15:30 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


15:45 GRAPH CONVOLUTIONAL LSTM MODEL FOR SKELETON-BASED ACTION RECOGNITION


Han Zhang, Yonghong Song, Yuanlin Zhang


Xi’an Jiaotong University, China


16:00 LEARNING RECURRENT STRUCTURE-GUIDED ATTENTION NETWORK FOR MULTI-PERSON POSE ESTIMATION


Zhongwei Qiu1, Kai Qiu2, Jianlong Fu2, Dongmei Fu1


1University of Science and Technology Beijing, China, 2Microsoft Reasearch, China


16:15 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


O-18: Image Quality Metrics

Time: 15:30 - 16:30 PM

Room: 3HI

Chair: Patrick Le Callet Universite de Nantes, France


15:30 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, 4Tsinghua University, China, 5Tencent, China


15:45 VIDEO QUALITY TEMPORAL POOLING USING A VISIBILITY MEASURE


Chen Bai, Amy R. Reibman


Purdue University, USA

16:00 IMAGE QUALITY ASSESSMENT OF MULTI-EXPOSURE IMAGE FUSION FOR BOTH STATIC AND DYNAMIC SCENES


Yuming Fang1, Yan Zeng1, Hanwei Zhu1, Guangtao Zhai2


1Jiangxi University of Finance and Economics, China, 2Shanghai Jiao Tong University, China

16:15 NO-REFERENCE STEREOSCOPIC IMAGE QUALITY ASSESSMENT BASED ON LOCAL TO GLOBAL FEATURE REGRESSION


Sumei Li, Jianwei Xue, Yongtian Han


Tianjin University, China


O-19: Multimedia Recommendations


Time: 15:30 - 16:30 PM


Room: 5BC


Chair: Rui Wang Tongji University, China


15:30 HERDING EFFECT BASED ATTENTION FOR PERSONALIZED TIME-SYNC VIDEO RECOMMENDA- TION

Wenmian Yang1,2, Wenyuan Gao1, Xiaojie Zhou1, Weijia Jia1,2, Shaohua Zhang1,2, Yutao Luo1


1Shanghai JiaoTong University, China, 2University of Macau, China


15:45 SEQUENTIAL BEHAVIOR MODELING FOR NEXT MICRO-VIDEO RECOMMENDATION WITH COL- LABORATIVE TRANSFORMER


Shang Liu, Zhenzhong Chen


Wuhan University, China


16:00 BUTTONTIPS: DESIGNING WEB BUTTONS WITH SUGGESTIONS


Dawei Liu, Ying Cao, Rynson W.H. Lau, Antoni B. Chan


City University of Hongkong, China


16:15 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


O-20: Search and Retrieval


Time: 15:30 - 16:30 PM


Room: 5DE


Chair: Jianquan Liu NEC Corporation, Japan


15:30 ADVERSARIAL CROSS-MODAL RETRIEVAL VIA LEARNING AND TRANSFERRING SINGLE-MOD- AL SIMILARITIES


Xin Wen1, Zhizhong Han1,2, Xinyu Yin1, Yu-Shen Liu1


1Tsinghua University, China, 2University of Maryland, USA


15:45 SEMI-SUPERVISED COMPATIBILITY LEARNING ACROSS CATEGORIES FOR CLOTHING MATCH- ING


Zekun Li, Zeyu Cui, Shu Wu, Xiaoyu Zhang, Liang Wang


Chinese Academy of Sciences, China


16:00 ADVERSARIAL LEARNING FOR FINE-GRAINED IMAGE SEARCH


Kevin Lin1, Fan Yang2, Qiaosong Wang2, Robinson Piramuthu2


1University of Washington, USA, 2eBay Inc, USA


16:15 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


O-21: Media Understanding

Time: 16:45 - 17:45 PM


Room: 3CD


Chair: Lingyu Duan Peking University, China


16:45 DISCO: DEPTH INFERENCE FROM STEREO USING CONTEXT


Kunal Swami, Kaushik Raghavan, Nikhilanj Pelluriy, Rituparna Sarkar, Pankaj Bajpai


Samsung Research Institute Bangalore, India


17:00 PANET: A CONTEXT BASED PREDICATE ASSOCIATION NETWORK FOR SCENE GRAPH GENERA- TION

Yunian Chen1, Yanjie Wang3, Yang Zhang1, Yanwen Guo1,2


1Nanjing University, China, 2The 28th Research Institute of China Electronics Technology Group Corporation, Chi- na, 3Zhejiang University, China


17:15 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 Technol- ogy on Information System Security, China


17:30 LEARNING GOAL-ORIENTED VISUAL DIALOG AGENTS: IMITATING AND SURPASSING ANALYTIC EXPERTS


Yen-Wei Chang, Wen-Hsiao Peng


National Chiao Tung University, Taiwan


O-22: Super-resolution and Enhancement

Time: 16:45 - 17:45 PM


Room: 3HI


Chair: Ge Li Peking University, China


16:45 GAN-BASED MULTI-LEVEL MAPPING NETWORK FOR SATELLITE IMAGERY SUPER-RESOLU- TION


Kui Jiang, Zhongyuan Wang, Peng Yi, Junjun Jiang, Guangcheng Wang, Zhen Han, Tao Lu


Wuhan University, China


17:00 QUALITY-GATED CONVOLUTIONAL LSTM FOR ENHANCING COMPRESSED VIDEO


Ren Yang3, Xiaoyan Sun1, Mai Xu2 and Wenjun Zeng1


1Microsoft Research, USA, 2Beihang University, China, 3ETH Zürich, Switzerland


17:15 COMPOUNDED LAYER-PRIOR UNROLLING: A UNIFIED TRANSMISSION-BASED IMAGE EN- HANCEMENT FRAMEWORK


Risheng Liu, Minjun Hou, Jinyuan Liu, Xin Fan, Zhongxuan Luo


Dalian University of Technology, China


17:30 DEEP PYRAMID VARIATION LEARNING FOR IMAGE INTERPOLATION


Fu Qiang, Wenhan Yang, Ying Li, and Jiaying Liu


Peking University, China


O-23: Pose and Action Recognition II


Time: 16:45 - 17:45 PM


Room: 5BC


Chair: Sheng Tang Institute of Computing Technology, Chinese Academy of Sciences, China


16:45 CLOTHES KEYPOINTS LOCALIZATION AND ATTRIBUTE RECOGNITION VIA PRIOR KNOWL- EDGE


Zhangxuan Gu, Jianfu Zhang, Ziqi Pan, Haohua Zhao, Liqing Zhang


Shanghai Jiao Tong University, China


17:00 SPATIO-TEMPORAL MULTI-FACTOR DISCRIMINANT ANALYSIS FOR INDIVIDUAL IDENTIFICA- TION


Yong Su, Zhiyong Feng


Tianjin University, China


17:15 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


17:30 LOCALIZATION GUIDED FIGHT ACTION DETECTION IN SURVEILLANCE VIDEOS


Qichao Xu1, John See2, Weiyao Lin1


1Shanghai Jiao Tong University, China, 2Multimedia University, Malaysia


O-24: Image and Video Enhancements I


Time: 16:45 - 17:45 PM


Room: 5DE


Chair: Miaohui Wang Shenzhen University, China


16:45 RECURSIVE MULTI-STAGE UPSCALING NETWORK WITH DISCRIMINATIVE FUSION FOR SU- PER-RESOLUTION

Yue Lu1, Zhuqing Jiang1, Guodong Ju2, Liangheng Shen2, Aidong Men1


1Beijing University of Posts and Telecommunications, China, 2GuangDong TUS-TuWei Technology Co., Ltd, China


17:00 IMPROVING IMAGE SUPER-RESOLUTION VIA FEATURE RE-BALANCING FUSION


Yuanfei Huang, Jie Li, Xinbo Gao, Wen Lu, Yanting Hu


Xidian University, China


17:15 DIFFICULTY-AWARE IMAGE SUPER RESOLUTION VIA DEEP ADAPTIVE DUAL-NETWORK


Jinghui Qin, Ziwei Xie, Yukai Shi, Wushao Wen


Sun Yat-sen University, China


17:30 DENSE-CONNECTED RESIDUAL NETWORK FOR VIDEO SUPER-RESOLUTION


Xiaoting Du, Yuan Zhou, Yanfang Chen, Yeda Zhang, Jianxing Yang and Dou Jin


Tianjin University, China


O-25: Face and Person Analysis


Time: 14:00 - 15:00 PM


Room: 3CD


Chair: Hailin Shi JD AI Research, China


14:00 DYNAMIC CASCADED REGRESSION NETWORK WITH REINFORCEMENT LEARNING FOR RO- BUST FACE ALIGNMENT


Zhihao Zhang, Liansheng Zhuang, Wengang Zhou, Houqiang Li


University of Science and Technology of China, China


14:15 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


14:30 EMOTION RECOGNITION FROM PHYSIOLOGICAL SIGNALS USING MULTI-HYPERGRAPH NEU- RAL NETWORKS


Junjie Zhu1, Xibin Zhao1, Han Hu2, Yue Gao1


1Tsinghua University, China, 2Beijing Institute of Technology, China


14:45 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


O-26: Media Classification and Segmentation III


Time: 14:00 - 15:00 PM


Room: 3HI


Chair: Chenggang Yan Hangzhou Dianzi University, China


14:00 MULTI-LABEL IMAGE RECOGNITION WITH JOINT CLASS-AWARE MAP DISENTANGLING AND LABEL CORRELATION EMBEDDING

Zhao-Min Chen1,2, Xiu-Shen Wei2, Xin Jin2, Yanwen Guo1,3


1Nanjing University, China, 2Megvii Technology, China, 3Science and Technology on Information Systems Engineer- ing Laboraty, China


14:15 REAL TIME COMPRESSED VIDEO OBJECT SEGMENTATION


Zhentao Tan, Bin Liu, Weihai Li, Nenghai Yu


University of Science and Technology of China, China


14:30 ACCURATE AND FAST FINE-GRAINED IMAGE CLASSIFICATION VIA DISCRIMINATIVE LEARN- ING


Zhihui Wang1, Shijie Wang1, Pengbo Zhang1, Haojie Li1, Bo Liu2


1Dalian University of Technology, China, 2Shanghai Jiao Tong University, China


14:45 POSE2BODY: POSE-GUIDED HUMAN PARTS SEGMENTATION


Zhong Li1, Xin Chen2, Wangyiteng Zhou2, Yingliang Zhang2, Jingyi Yu2


1University of Delaware, USA, 2ShanghaiTech University, China


O-27: Image and Video Enhancements II


Time: 14:00-15:00 PM


Room: 5BC


Chair: Ce Zhu University of Electronic Science & Technology of China, China


14:00 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


14:15 EVERYONE IS A CARTOONIST: SELFIE CARTOONIZATION WITH ATTENTIVE ADVERSARIAL NETWORKS


Xinyu Li, Wei Zhang, Tong Shen, Tao Mei


JD AI Research, China


14:30 SCALE-AWARE DEEP NETWORK WITH HOLE CONVOLUTION FOR BLIND MOTION DEBLURRING


Jichun Li, Ke Li, Bo Yan


Fudan University, China


14:45 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


O-28: Multimedia Learning and Adaptation

Time: 14:00 - 15:00 PM


Room: 5DE


Chair: Song Li Shanghai Jiao Tong University, China


14:00 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


14:15 HIGH SPEED RECURRENT REGRESSION NETWORK FOR VISUAL TRACKING


Ding Ma, Xiangqian Wu


Harbin Institute of Technology, China


14:30 PAAE: A UNIFIED FRAMEWORK FOR PREDICTING ANCHOR LINKS WITH ADVERSARIAL EM- BEDDING


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 Response technical Team,China, 3State Information Center, China


14:45 MANIFOLD ALIGNMENT AND DISTRIBUTION ADAPTATION FOR UNSUPERVISED DOMAIN ADAP- TATION


Ying Li, Lin Cheng, Yaxin Peng, Zhijie Wen, Shihui Ying


Shanghai University, China


O-29: Person (Re-)Identification and People Detection

Time: 15:30 - 16:30 PM


Room: 3CD


Chair: Bingpeng Ma University of Science and Technology of China, China


15:30 PEDESTRIAN RE-IDENTIFICATION BASED ON TREE BRANCH NETWORK WITH LOCAL AND GLOBAL LEARNING


Hui Li1, Meng Yang24, Zhihui Lai1, Weishi Zheng2, Zitong Yu3


1Shenzhen University, China, 2Sun Yat-sen University, China, 3University of Oulu, Finland, 4Key Laboratory of Ma- chine Intelligence and Advanced Computing(SYSU), Ministry of Education, China


15:45 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, UAE, 3Computer Vision Laboratory, ETH Zurich, Switzerland


16:00 PERSON RE-IDENTIFICATION WITH GRADUAL BACKGROUND SUPPRESSION


Yingzhi Tang, Xi Yang, Nannan Wang, Xinrui Jiang, Bin Song, Xinbo Gao


Xidian University, China


16:15 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, Beijing, China


O-30: Multimedia and Language II

Time: 15:30 - 16:30 PM


Room: 3HI


Chair: Annan Li Beijing University of Aeronautics and Astronautics, China


15:30 POST-PROCESSING OF WORD REPRESENTATIONS VIA VARIANCE NORMALIZATION AND DY- NAMIC EMBEDDING


Bin Wang1, Fenxiao Chen1, Angela Wang2 and C.-C. Jay Kuo1


1University of Southern California, USA, 2University of California, Berkeley, USA


15:45 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


16:00 MODELING THE CLAUSE-LEVEL STRUCTURE TO MULTIMODAL SENTIMENT ANALYSIS VIA REINFORCEMENT LEARNING


Dong Zhang, Shoushan Li, Qiaoming Zhu, Guodong Zhou


Soochow University, China


16:15 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


O-31: Multimedia Communications and Localization

Time: 15:30 - 16:30 PM


Room: 5BC


Chair: Sanjeev Mehrotra Microsoft, USA


15:30 GEOCAPSNET: GROUND TO AERIAL VIEW IMAGE GEO-LOCALIZATION USING CAPSULE NET- WORK


Bin Sun1, Chen Chen2, Yingying Zhu1, Jianmin Jiang1


1Shenzhen University, China, 2University of North Carolina at Charlotte, USA


15:45 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


16:00 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


16:15 TAXI ORIGIN-DESTINATION DEMAND PREDICTION WITH CONTEXTUALIZED SPATIAL-TEMPO- RAL NETWORK


Zhilin Qiu, Lingbo Liu, Guanbin Li, Qing Wang, Nong Xiao, Liang Lin


Sun Yat-sen University, China


O-32: Multimedia Security, Privacy and Forensics II

Time: 15:30 - 16:30 PM


Room: 5DE


Chair: Wen Ji Institute of Computing Technology, Chinese Academy of Sciences, China


15:30 FAST IMAGE CLUSTERING BASED ON CAMERA FINGERPRINT ORDERING


Sahib Khan, Tiziano Bianchi


Politecnico di Torino, Italy


15:45 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 Sci- ences, China


16:00 ATTRIBUTE-BASED ACCOUNTABLE ACCESS CONTROL FOR MULTIMEDIA CONTENT WITH IN-NETWORK 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


16:15 PRACTICAL IMAGE OBFUSCATION WITH PROVABLE PRIVACY


Liyue Fan


University at Albany, State University of New York, USA


O-33: Multimedia Sensing and Signal Processing


Time: 16:45 - 17:45 PM


Room: 3HI


Chair: Zhi Jin Sun Yat-sen University, China


16:45 JOINTLY SOLVING DEBLURRING AND SUPER-RESOLUTION PROBLEMS WITH DUAL SUPER- VISED NETWORK


Zhenwen Liang, Dongyang Zhang, Jie Shao


University of Electronic Science and Technology of China, China


17:00 TWO-STAGED ACOUSTIC MODELING ADAPTION FOR ROBUST SPEECH RECOGNITION BY THE EXAMPLE OF GERMAN ORAL HISTORY INTERVIEWS


Michael Gref1,2, Christoph Schmidt1, Sven Behnke1,3, Joachim Köhler1


1Fraunhofer Institute for Intelligent Analysis and Information Systems, Germany, 2Niederrhein University of Applied Sciences, Germany, 3University of Bonn, Germany


17:15 AN ADAPTIVE AFFINITY GRAPH WITH SUBSPACE PURSUIT FOR NATURAL IMAGE SEGMENTA- TION


Yang Zhang1, Huiming Zhang1, Yanwen Guo1, Kai Lin2, Jingwu He1


1Nanjing University, China, 2Hubei University of Technology, China


17:30 PHASE TIME-FREQUENCY MASKING BASED SPEECH ENHANCEMENT ALGORITHM USING CIR- CULAR MICROPHONE ARRAY


Li He, Yi Zhou, Hongqing Liu


Chongqing University of Posts and Telecommunications, China


O-34: Detection and Recognition


Time: 16:45 - 17:45 PM


Room: 5BC


Chair: Lifang Wu Beijing University of Technology, China


16:45 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


17:00 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


17:15 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


17:30 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


O-35: Multi-modal Media Computing and Human-machine Interaction


Time: 16:45 - 17:45 PM


Room: 5DE


Chair: Sanghoon Lee Yonsei University, Korea


16:45 MANY COULD BE BETTER THAN ALL: A NOVEL INSTANCE-ORIENTED ALGORITHMFOR MULTI-MODAL MULTI-LABEL PROBLEM


Yi Zhang, Cheng Zeng, Hao Cheng, Chongjun Wang, Lei Zhang


Nanjing University, China


17:00 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, America, 4Key Laboratory of Machine Intelli- gence and Advanced Computing, Ministry of Education, China


17:15 LEARNING A 3D GAZE ESTIMATOR WITH IMPROVED ITRACKER COMBINED WITH BIDIREC- TIONAL LSTM


Xiaolong Zhou, Jianing Lin, Jiaqi Jiang, Shengyong Chen


Zhejiang University of Technology, China


17:30 DETECTION OF OCCLUDED ROAD SIGNS ON AUTONOMOUS DRIVING VEHICLES


Jingda Guo, Xianwei Cheng, Qi Chen, Qing Yang


University of North Texas, USA