TEC-05: Machine Learning for Image and Video Processing III |
| Interactive Q&A Time: Monday, 26 October, 19:30 - 20:25 |
| Virtual Session: View on Virtual Platform |
| Session Chair: YU LIU, Tianjin University |
| TEC-05.1: A SIAMESE NETWORK UTILIZING IMAGE STRUCTURAL DIFFERENCES FOR CROSS-CATEGORY DEFECT DETECTION |
| Chenhui Luan; Beijing Institute of Technology |
| Ruyao Cui; Beijing Institute of Technology |
| Lei Sun; Beijing Institute of Technology |
| Zhiping Lin; Nanyang Technological University |
| TEC-05.2: CHROMA INTRA PREDICTION WITH ATTENTION-BASED CNN ARCHITECTURES |
| Marc Gorriz Blanch; British Broadcasting Corporation |
| Saverio Blasi; British Broadcasting Corporation |
| Alan Smeaton; Dublin City University |
| Noel E. O'Connor; Dublin City University |
| Marta Mrak; British Broadcasting Corporation |
| TEC-05.3: ART2CONTOUR: SALIENT CONTOUR DETECTION IN ARTWORKS USING GENERATIVE ADVERSARIAL NETWORKS |
| Aline Sindel; Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) |
| Andreas Maier; Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) |
| Vincent Christlein; Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) |
| TEC-05.4: PREDICTIVE CODING NETWORKS MEET ACTION RECOGNITION |
| Xia Huang; SUTD university |
| Hossein Mousavi; SUTD university |
| Gemma Roig; Goethe University of Frankfurt am Main, Frankfurt am Main, Germany |
| TEC-05.5: INTERPRETING CNN FOR LOW COMPLEXITY LEARNED SUB-PIXEL MOTION COMPENSATION IN VIDEO CODING |
| Luka Murn; British Broadcasting Company |
| Saverio Blasi; British Broadcasting Company |
| Alan F. Smeaton; Dublin City University |
| Noel E. O'Connor; Dublin City University |
| Marta Mrak; British Broadcasting Company |
| TEC-05.6: BOUNDARY OF DISTRIBUTION SUPPORT GENERATOR (BDSG): SAMPLE GENERATION ON THE BOUNDARY |
| Nikolaos Dionelis; University of Edinburgh, Edinburgh, UK |
| Mehrdad Yaghoobi; University of Edinburgh, Edinburgh, UK |
| Sotirios Tsaftaris; University of Edinburgh, Edinburgh, UK |
| TEC-05.7: TRIPLET DISTILLATION FOR DEEP FACE RECOGNITION |
| Yushu Feng; Zhejiang University |
| Huan Wang; Zhejiang University |
| Haoji Hu; Zhejiang University |
| Lu Yu; Zhejiang University |
| Wei Wang; Chongqing University of Posts and Telecommunications |
| Shiyan Wang; Chongqing University of Posts and Telecommunications |
| TEC-05.8: SINGLE ARCHITECTURE AND MULTIPLE TASK DEEP NEURAL NETWORK FOR ALTERED FINGERPRINT ANALYSIS |
| Oliver Giudice; University of Catania |
| Mattia Litrico; University of Catania |
| Sebastiano Battiato; University of Catania |
| TEC-05.9: CORNET: COMPOSITE-REGULARIZED NEURAL NETWORK FOR CONVOLUTIONAL SPARSE CODING |
| Dhruv Jawali; Indian Institute of Science |
| Praveen Kumar Pokala; Indian Institute of Science |
| Chandra Sekhar Seelamantula; Indian Institute of Science |
| TEC-05.10: FAKE VIDEO DETECTION WITH CERTAINTY-BASED ATTENTION NETWORK |
| Dae Hwi Choi; 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) |
| Jung Uk Kim; Korea Advanced Institute of Science and Technology (KAIST) |
| Yong Man Ro; Korea Advanced Institute of Science and Technology (KAIST) |
| TEC-05.11: SEGMENTING UNSEEN INDUSTRIAL COMPONENTS IN A HEAVY CLUTTER USING RGB-D FUSION AND SYNTHETIC DATA |
| Seunghyeok Back; Gwangju Institute of Science and Techonology (GIST) |
| Jongwon Kim; Gwangju Institute of Science and Techonology (GIST) |
| Raeyoung Kang; Gwangju Institute of Science and Techonology (GIST) |
| Seungjun Choi; Gwangju Institute of Science and Techonology (GIST) |
| Kyoobin Lee; Gwangju Institute of Science and Techonology (GIST) |
| TEC-05.12: DATA AUGMENTATION USING ARTIFICIAL IMMUNE SYSTEMS FOR NOISE-ROBUST CNN MODELS |
| Mark Ofori-Oduro; Concordia University |
| Maria Amer; Concordia University |
| TEC-05.13: CONVOLUTIONAL ATTENTION MODEL FOR RESTAURANT RECOMMENDATION WITH MULTI-VIEW VISUAL FEATURES |
| Haihua Luo; Shenzhen University |
| Xiaoyan Zhang; Shenzhen University |
| Guibing Guo; Northeastern University of China |
| TEC-05.14: ROBUST STRUCTURED DICTIONARY LEARNING FOR BLOCK SPARSE REPRESENTATIONS USING ALPHA-DIVERGENCE |
| Abd-Krim Seghouane; University of Melbourne |
| TEC-05.15: BIOLOGICALLY INSPIRED HEXAGONAL DEEP LEARNING FOR HEXAGONAL IMAGE GENERATION |
| Tobias Schlosser; Chemnitz University of Technology |
| Frederik Beuth; Chemnitz University of Technology |
| Danny Kowerko; Chemnitz University of Technology |
| TEC-05.16: MASKPAN: MASK PRIOR GUIDED NETWORK FOR PANSHARPENING |
| Xue Rui; University of Science and Technology of China |
| Yang Cao; University of Science and Technology of China |
| Yu Kang; University of Science and Technology of China |
| Weiguo Song; University of Science and Technology of China |
| Rui Ba; University of Science and Technology of China |
| TEC-05.17: JITTER-ROBUST VIDEO RETARGETING WITH KALMAN FILTER AND ATTENTION SALIENCY FUSION NETWORK |
| Hyunwoo Nam; Samsung Electronics |
| Dubok Park; Samsung Electronics |
| Kangwon Jeon; Samsung Electronics |
| TEC-05.18: LEGENDRE BASED ADAPTIVE IMAGE SEGMENTATION COMBINING THE GRADIENT INFORMATION |
| Jiajie Zhu; ChongQing University |
| Bin Fang; ChongQing University |
| Mingliang Zhou; ChongQing University |
| Hengjun Zhao; Chongqing University of Arts and Sciences |
| Futing Luo; ChongQing University |
| TEC-05.19: JOINT IMAGE SUPER-RESOLUTION VIA RECURRENT CONVOLUTIONAL NEURAL NETWORKS WITH COUPLED SPARSE PRIORS |
| Iman Marivani; Vrije Universiteit Brussel-imec |
| Evaggelia Tsiligianni; Vrije Universiteit Brussel-imec |
| Bruno Cornelis; Vrije Universiteit Brussel-imec |
| Nikos Deligiannis; Vrije Universiteit Brussel-imec |