TEC-03: Machine Learning for Image and Video Processing I |
| Interactive Q&A Time: Monday, 26 October, 17:30 - 18:25 |
| Virtual Session: View on Virtual Platform |
| Session Chairs: Ivan Bajic, Simon Fraser University and Mylene Farias, University of Brasilia (UnB) |
| TEC-03.1: PRIMARY QUALITY FACTOR ESTIMATION OF RESIZED DOUBLE COMPRESSED JPEG IMAGES |
| Yakun Niu; Beijing Jiaotong University |
| Xiaolong Li; Beijing Jiaotong University |
| Yao Zhao; Beijing Jiaotong University |
| Rongrong Ni; Beijing Jiaotong University |
| TEC-03.2: ENSEMBLE LEARNING USING BAGGING AND INCEPTION-V3 FOR ANOMALY DETECTION IN SURVEILLANCE VIDEOS |
| Yumna Zahid; National University of Computer and Emerging Sciences |
| Muhammad Atif Tahir; National University of Computer and Emerging Sciences |
| Muhammad Nouman Durrani; National University of Computer and Emerging Sciences |
| TEC-03.3: TYPE I ATTACK FOR GENERATIVE MODELS |
| Chengjin Sun; Shanghai Jiao Tong University |
| Sizhe Chen; Shanghai Jiao Tong University |
| Jia Cai; Huawei |
| Xiaolin Huang; Shanghai Jiao Tong University |
| TEC-03.4: MDT: UNSUPERVISED MULTI-DOMAIN IMAGE-TO-IMAGE TRANSLATOR BASED ON GENERATIVE ADVERSARIAL NETWORKS |
| Ye Lin; Sichuan University, China |
| Keren Fu; Sichuan University, China |
| Shenggui Ling; Sichuan University, China |
| Peng Cheng; Sichuan University, China |
| TEC-03.5: DYNAMIC OBJECT-AWARE MONOCULAR VISUAL ODOMETRY WITH LOCAL AND GLOBAL INFORMATION AGGREGATION |
| Yiming Wan; NLPR, Institute of Automation, Chinese Academy of Sciences |
| Wei Gao; NLPR, Institute of Automation, Chinese Academy of Sciences |
| Sheng Han; NLPR, Institute of Automation, Chinese Academy of Sciences |
| Yihong Wu; NLPR, Institute of Automation, Chinese Academy of Sciences |
| TEC-03.6: ST-LSTM: SPATIO-TEMPORAL GRAPH BASED LONG SHORT-TERM MEMORY NETWORK FOR VEHICLE TRAJECTORY PREDICTION |
| Guangxi Chen; Guilin University of Electronic Technology |
| Ling Hu; Guilin University of Electronic Technology |
| Qieshi Zhang; Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences |
| Ziliang Ren; Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences |
| Xiangyang Gao; Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences |
| Jun Cheng; Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences |
| TEC-03.7: CHANNEL-GROUPING BASED PATCH SWAP FOR ARBITRARY STYLE TRANSFER |
| Yan Zhu; Xidian University |
| Yi Niu; Xidian University |
| Fu Li; Xidian University |
| Chunbo Zou; Xi'an institute of optics and precision mechanics of CAS |
| Guangming Shi; Xidian University |
| TEC-03.8: HUMAN DETECTION IN DENSE SCENE OF CLASSROOMS |
| Jisheng Ding; University of Electronic Science and Technology of China |
| Linfeng Xu; University of Electronic Science and Technology of China |
| Jiangtao Guo; University of Electronic Science and Technology of China |
| Shengxuan Dai; University of Electronic Science and Technology of China |
| TEC-03.9: SELECTIVE COMPLEMENTARY FEATURES FOR MULTI-PERSON POSE ESTIMATION |
| Buwei Li; Soochow University |
| Kai Liu; Soochow University |
| Yi Ji; Soochow University |
| Jianyu Yang; Soochow University |
| Chunping Liu; Soochow University |
| TEC-03.10: EFFICIENT HEVC-TO-VVC TRANSCODER BASED ON A BAYESIAN CLASSIFIER FOR THE FIRST QUADTREE DEPTH LEVEL |
| David García Lucas; University of Castilla-La Mancha |
| Gabriel Cebrián Márquez; University of Oviedo |
| Antonio Jesús Díaz Honrubia; Universidad Politécnica de Madrid |
| Thanuja Mallikarachchi; Cardiff Metropolitan University |
| Pedro Cuenca; University of Castilla-La Mancha |
| TEC-03.11: LEARNING LIGHT FIELD SYNTHESIS WITH MULTI-PLANE IMAGES: SCENE ENCODING AS A RECURRENT SEGMENTATION TASK |
| Tomás Völker; InterDigital |
| Guillaume Boisson; InterDigital |
| Bertrand Chupeau; InterDigital |
| TEC-03.12: INFOPRINT: INFORMATION THEORETIC DIGITAL IMAGE FORENSICS |
| Aurobrata Ghosh; Verisk Analytics |
| Zheng Zhong; Verisk Analytics |
| Steve Cruz; University of Colorado |
| Subbu Veeravasarapu; Verisk Analytics |
| Maneesh Singh; Verisk Analytics |
| Terrance E Boult; University of Colorado |
| TEC-03.13: DEEP LEARNING AND INTERACTIVITY FOR VIDEO ROTOSCOPING |
| Shivam Saboo; Indian Institute of Information Technology |
| Frederic Lefebvre; InterDigital |
| Vincent Demoulin; InterDigital |
| TEC-03.14: SUBSTITUTE MODEL GENERATION FOR BLACK-BOX ADVERSARIAL ATTACK BASED ON KNOWLEDGE DISTILLATION |
| Ｗeiyu Cui; University of Electronic Science and Technology of China |
| Xiaorui Li; University of Electronic Science and Technology of China |
| Jiawei Huang; University of Electronic Science and Technology of China |
| Wenyi Wang; University of Electronic Science and Technology of China |
| Shuai Wang; University of Electronic Science and Technology of China |
| Jianwen Chen; University of Electronic Science and Technology of China |
| TEC-03.15: EQ-LPR: EFFICIENT QUALITY-AWARE LICENSE PLATE RECOGNITION |
| Cong Zhang; Northwestern Polytechnical University |
| Qi Wang; Northwestern Polytechnical University |
| Xuelong Li; Northwestern Polytechnical University |
| TEC-03.16: PERCEPTION ENHANCED FRAME FOR VISUAL OBJECT TRACKING |
| Binpeng Song; Institute of Computing Technology, Chinese Academy of Sciences |
| Jianfeng Liu; Institute of Computing Technology, Chinese Academy of Sciences |
| Jian Ye; Institute of Computing Technology, Chinese Academy of Sciences |
| TEC-03.17: LOWNET: PRIVACY PRESERVED ULTRA-LOW RESOLUTION POSTURE IMAGE CLASSIFICATION |
| Munkhjargal Gochoo; United Arab Emirates University |
| Tan-Hsu Tan; National Taipei University of Technology |
| Fady Alnajjar; United Arab Emirates University |
| Jun-Wei Hsieh; National Chiao Tung University |
| Ping-Yang Chen; National Chiao Tung University |
| TEC-03.18: CAM-NET: COMPRESSED ATTENTIVE MULTI-GRANULARITY NETWORK FOR DYNAMIC SCENE CLASSIFICATION |
| Yue Li; Beihang University |
| Wenrui Ding; Beihang University |
| Yanjun Zhu; University at Buffalo |
| Yuanjun Huang; Beihang University |
| Yalong Jiang; Hong Kong Polytechnic University |
| Baochang Zhang; Beihang University |