2021 IEEE International Conference on Image Processing
19-22 September 2021 • Anchorage, Alaska, USA
Imaging Without Borders
All times are in Alaska local time (AKDT/UTC−08:00)
MLR-APPL-IVSMR-3: Machine learning for image and video sensing, modeling and representation 3 |
| Interactive Q&A Time: Wednesday, September 22, 14:30 - 16:00 |
| Session Chair: Junyeong Kim, KAIST |
| MLR-APPL-IVSMR-3.1: IMAGE ENHANCED ROTATION PREDICTION FOR SELF-SUPERVISED LEARNING |
| Shin'ya Yamaguchi; NTT |
| Sekitoshi Kanai; NTT |
| Tetsuya Shioda; NTT |
| Shoichiro Takeda; NTT |
| MLR-APPL-IVSMR-3.2: ENHANCING ADVERSARIAL ROBUSTNESS FOR IMAGE CLASSIFICATION BY REGULARIZING CLASS LEVEL FEATURE DISTRIBUTION |
| Cheng Yu; Tsinghua University |
| Youze Xue; Tsinghua University |
| Jiansheng Chen; Tsinghua University |
| Yu Wang; Tsinghua University |
| Huimin Ma; University of Science and Technology Beijing |
| MLR-APPL-IVSMR-3.3: SEMI-SUPERVISED LEARNING FOR MARS IMAGERY CLASSIFICATION |
| Wenjing Wang; Peking University |
| Lilang Lin; Peking University |
| Zejia Fan; Peking University |
| Jiaying Liu; Peking University |
| MLR-APPL-IVSMR-3.4: CLASS INCREMENTAL LEARNING FOR VIDEO ACTION CLASSIFICATION |
| Jiawei Ma; Xi'an Jiaotong University |
| Xiaoyu Tao; Xi'an Jiaotong University |
| Jianxing Ma; Xi'an Jiaotong University |
| Xiaopeng Hong; Xi'an Jiaotong University |
| Yihong Gong; Xi'an Jiaotong University |
| MLR-APPL-IVSMR-3.5: FINE-GRAINED MULTI-CLASS OBJECT COUNTING |
| Hyojun Go; Korea Advanced Institute of Science and Technology |
| Junyoung Byun; Korea Advanced Institute of Science and Technology |
| Byeongjun Park; Korea Advanced Institute of Science and Technology |
| Myung-Ae Choi; Korea Advanced Institute of Science and Technology |
| Seunghwa Yoo; National Institute of Ecology |
| Changick Kim; Korea Advanced Institute of Science and Technology |
| MLR-APPL-IVSMR-3.6: ITERATIVE SUBNETWORK WITH LINEAR HIERARCHICAL ORDERING FOR HUMAN POSE ESTIMATION |
| Shek Wai Chu; University of Sydney |
| Chaoyi Zhang; University of Sydney |
| Yang Song; University of New South Wales |
| Weidong Cai; University of Sydney |
| MLR-APPL-IVSMR-3.7: UNSUPERVISED FAST VISUAL LOCALIZATION AND MAPPING WITH SLOW FEATURES |
| Muhammad Haris; Frankfurt University of Applied Sciences |
| Mathias Franzius; Honda Research Institute Europe GmbH |
| Ute Bauer-Wersing; Frankfurt University of Applied Sciences |
| MLR-APPL-IVSMR-3.8: MULTI-TASK OCCLUSION LEARNING FOR REAL-TIME VISUAL OBJECT TRACKING |
| Gozde Sahin; University of Southern California |
| Laurent Itti; University of Southern California |
| MLR-APPL-IVSMR-3.9: CRACK DETECTION AND REFINEMENT VIA DEEP REINFORCEMENT LEARNING |
| Jinhyung Park; Carnegie Mellon University |
| Yi-Chun Chen; Carnegie Mellon University |
| Yu-Jhe Li; Carnegie Mellon University |
| Kris Kitani; Carnegie Mellon University |
| MLR-APPL-IVSMR-3.10: WEAKLY-SUPERVISED MOMENT RETRIEVAL NETWORK FOR VIDEO CORPUS MOMENT RETRIEVAL |
| Sunjae Yoon; Korea Advanced Institute of Science and Technology |
| Dahyun Kim; Korea Advanced Institute of Science and Technology |
| Ji Woo Hong; Korea Advanced Institute of Science and Technology |
| Junyeong Kim; Korea Advanced Institute of Science and Technology |
| Kookhoi Kim; Korea Advanced Institute of Science and Technology |
| Chang D. Yoo; Korea Advanced Institute of Science and Technology |
| MLR-APPL-IVSMR-3.11: PROGRESSIVE NEURAL IMAGE COMPRESSION WITH NESTED QUANTIZATION AND LATENT ORDERING |
| Yadong Lu; Department of Statistics, University of California Irvine |
| Yinhao Zhu; Qualcomm AI Research, Qualcomm Technologies, Inc. |
| Yang Yang; Qualcomm AI Research, Qualcomm Technologies, Inc. |
| Amir Said; Qualcomm AI Research, Qualcomm Technologies, Inc. |
| Taco Cohen; Qualcomm AI Research, Qualcomm Technologies Netherlands B.V. |
| MLR-APPL-IVSMR-3.12: EDGE-LABELING BASED DIRECTED GATED GRAPH NETWORK FOR FEW-SHOT LEARNING |
| Peixiao Zheng; Zhengzhou University |
| Xin Guo; Zhengzhou University |
| Lin Qi; Zhengzhou University |
| MLR-APPL-IVSMR-3.13: MICRO-EXPRESSION RECOGNITION BASED ON VIDEO MOTION MAGNIFICATION AND PRE-TRAINED NEURAL NETWORK |
| Mengjiong Bai; University of Canberra |
| Roland Goecke; University of Canberra |
| Damith Herath; University of Canberra |