Technical Program

Click on the icon to view the manuscript on IEEE XPlore in the IEEE ICIP 2020 Open Preview.

ARS-13: Machine Learning for Image and Video Classification III

Interactive Q&A Time: Tuesday, 27 October, 16:30 - 16:55
Virtual Session: View on Virtual Platform
Session Chair: Yicong Zhou, University of Macau
 
 ARS-13.1: MULTI-MODAL FUSION WITH OBSERVATION POINTS FOR SKELETON ACTION RECOGNITION
         Iqbal Singh; Queen's University
         Xiaodan Zhu; Queen's University
         Michael Greenspan; Queen's University
 
 ARS-13.2: MOTION REPRESENTATION USING RESIDUAL FRAMES WITH 3D CNN
         Li Tao; University of Tokyo
         Xueting Wang; University of Tokyo
         Toshihiko Yamasaki; University of Tokyo
 
 ARS-13.3: LEARNING STYLE CORRELATION FOR ELABORATE FEW-SHOT CLASSIFICATION
         Junho Kim; Korea Advanced Institute of Science and Technology (KAIST)
         Minsu Kim; Korea Advanced Institute of Science and Technology (KAIST)
         Jung Uk Kim; Korea Advanced Institute of Science and Technology (KAIST)
         Hong Joo Lee; Korea Advanced Institute of Science and Technology (KAIST)
         Sangmin Lee; Korea Advanced Institute of Science and Technology (KAIST)
         Joanna Hong; Korea Advanced Institute of Science and Technology (KAIST)
         Yong Man Ro; Korea Advanced Institute of Science and Technology (KAIST)
 
 ARS-13.4: DIMENSIONALITY REDUCTION VIA DIFFUSION MAP IMPROVED WITH SUPERVISED LINEAR PROJECTION
         Bowen Jiang; University of Illinois Urbana-Champaign
         Maohao Shen; University of Illinois Urbana-Champaign
 
 ARS-13.5: GROUPED TEMPORAL ENHANCEMENT MODULE FOR HUMAN ACTION RECOGNITION
         Hong Liu; Peking University
         Bin Ren; Peking University
         Mengyuan Liu; Tencent Research
         Runwei Ding; Peking University
 
 ARS-13.6: STYLE EXTRACTOR FOR FACIAL EXPRESSION RECOGNITION IN THE PRESENCE OF SPEECH
         Ali N. Salman; University of Texas at Dallas
         Carlos Busso; University of Texas at Dallas
 
 ARS-13.7: TRANSFER LEARNING FOR VIDEOS: FROM ACTION RECOGNITION TO SIGN LANGUAGE RECOGNITION
         Noha Sarhan; Universität Hamburg
         Simone Frintrop; Universität Hamburg
 
 ARS-13.8: A STUDY OF ALIGNMENT MECHANISMS IN ADVERSARIAL DOMAIN ADAPTATION
         Rodrigue Siry; Université de Caen Normandie, Safran Electronics and Defense
         Loic Simon; Université de Caen Normandie
         Frederic Jurie; Université de Caen Normandie
 
 ARS-13.9: EXTRACTING DEEP LOCAL FEATURES TO DETECT MANIPULATED IMAGES OF HUMAN FACES
         Michail Tarasiou; Imperial College London
         Stefanos Zafeiriou; Imperial College London
 
 ARS-13.10: ADAPTIVE CONVOLUTIONALLY ENCHANCED BI-DIRECTIONAL LSTM NETWORKS FOR CHOREOGRAPHIC MODELING
         Nikolaos Bakalos; National Technical University of Athens
         Ioannis Rallis; National Technical University of Athens
         Nikolaos Doulamis; National Technical University of Athens
         Anastasios Doulamis; National Technical University of Athens
         Athanasios Voulodimos; Univertsity of West Attica
         Eftychios Protopapadakis; National Technical University of Athens
 
 ARS-13.11: SKELETON ACTION RECOGNITION BASED ON SINGULAR VALUE DECOMPOSITION
         Radek Simkanič; VŠB - Technical University of Ostrava
 
 ARS-13.12: GENDER RECOGNITION ON RGB-D IMAGE
         Xiaoxiong Zhang; Khalifa University
         Sajid Javed; Khalifa University
         Ahmad Obeid; Khalifa University
         Jorge Dias; Khalifa University
         Naoufel Werghi; Khalifa University
 
 ARS-13.13: MODEL UNCERTAINTY FOR UNSUPERVISED DOMAIN ADAPTATION
         JoonHo Lee; Seoul National University of Science and Technology
         Gyemin Lee; Seoul National University of Science and Technology
 
 ARS-13.14: CLASS INCREMENTAL LEARNING WITH TASK-SELECTION
         Eun Sung Kim; Korea Advanced Institute of Science and Technology (KAIST)
         Jung Uk Kim; Korea Advanced Institute of Science and Technology (KAIST)
         Sangmin Lee; Korea Advanced Institute of Science and Technology (KAIST)
         Sang-Keun Moon; Korea Electric Power Corporation (KEPCO) Research Institute
         Yong Man Ro; Korea Advanced Institute of Science and Technology (KAIST)
 
 ARS-13.15: ASSOCIATING MULTI-SCALE RECEPTIVE FIELDS FOR FINE-GRAINED RECOGNITION
         Zihan Ye; Suzhou University of Science and Technology
         Fuyuan Hu; Suzhou University of Science and Technology
         Yin Liu; Shanghai Institute of Technology
         Zhenping Xia; Suzhou University of Science and Technology
         Fan Lyu; Tianjin University
         Pengqing Liu; Suzhou University of Science and Technology