HP-V1.V4.3
Pyramid Knowledge Distillation for Efficient Human Pose Estimation
Yang Li, Peng Jiao, Haoqian Wang, Tsinghua Shenzhen International Graduate School, China
Session:
Imaging and Media Applications
Track:
Imaging and Media Applications
Location:
Gather.Town 4
Presentation Time:
Thu, 6 Oct, 21:00 - 22:00 China Standard Time (UTC +8)
Thu, 6 Oct, 15:00 - 16:00 Central European Time (UTC +1)
Thu, 6 Oct, 13:00 - 14:00 UTC
Thu, 6 Oct, 09:00 - 10:00 Eastern Time (UTC -5)
Thu, 6 Oct, 15:00 - 16:00 Central European Time (UTC +1)
Thu, 6 Oct, 13:00 - 14:00 UTC
Thu, 6 Oct, 09:00 - 10:00 Eastern Time (UTC -5)
Session Co-Chairs:
Jean-Christophe Pesquet, CentraleSupélec and Andrea Cavallaro, Queen Mary University of London and Rebecca Willett, University of Chicago
Presentation
Discussion
Resources
No resources available.
Session HP-V1.V4
HP-V1.V4.1: A UNIFIED FRAMEWORK FOR MASKED AND MASK-FREE FACE RECOGNITION VIA FEATURE RECTIFICATION
Shaozhe Hao, Kwan-Yee K. Wong, The University of Hong Kong, Hong Kong; Chaofeng Chen, Nanyang Technological University, Singapore; Zhenfang Chen, MIT-IBM Watson AI Lab, United States of America
HP-V1.V4.2: PROTOTYPE QUEUE LEARNING FOR MULTI-CLASS FEW-SHOT SEMANTIC SEGMENTATION
Zichao Wang, Zhiyu Jiang, Yuan Yuan, Northwestern Polytechnical University, China
HP-V1.V4.3: Pyramid Knowledge Distillation for Efficient Human Pose Estimation
Yang Li, Peng Jiao, Haoqian Wang, Tsinghua Shenzhen International Graduate School, China
HP-V1.V4.4: VEFNET: AN EVENT-RGB CROSS MODALITY FUSION NETWORK FOR VISUAL PLACE RECOGNITION
Ze Huang, Rui Huang, Songzhi Su, Xiamen University, China; Li Sun, University of Sheffield, United Kingdom of Great Britain and Northern Ireland; Cheng Zhao, Bosch Research North America, United States of America; Min Huang, Jimei University, China
HP-V1.V4.5: Learned Video Compression with Residual Prediction and Feature-aided Loop Filter
Chao Liu, Xiaoyang Zeng, Yibo Fan, Fudan University, China; Heming Sun, Waseda University, China
HP-V1.V4.6: HIERARCHICAL TRAINING FOR DISTRIBUTED DEEP LEARNING BASED ON MULTIMEDIA DATA OVER BAND-LIMITED NETWORKS
Siyu Qi, Lahiru D. Chamain, Zhi Ding, University of California Davis, United States of America
HP-V1.V4.7: LOW-COMPLEXITY SCALER BASED ON CONVOLUTIONAL NEURAL NETWORKS FOR ADAPTIVE VIDEO STREAMING
Jaehwan Kim, Dongkyu Kim, Min Woo Park, Chaeeun Lee, Youngo Park, Kwang Pyo Choi, Samsung Research, Korea, Republic of
HP-V1.V4.8: DOCUMENT LAYOUT ANALYSIS VIA POSITIONAL ENCODING
EJian Zhou, Xingjiao Wu, Luwei Xiao, Xiangcheng Du, TianLong Ma, Liang He, East China Normal University, China
HP-V1.V4.9: Multi-frame Video Prediction with Learnable Motion Encodings
Rakesh Jasti, UC Merced, United States of America; Varun Jampani, Deqing Sun, Google Research, United States of America; Ming-Hsuan Yang, UC Merced, Google Research, United States of America
HP-V1.V4.10: SCANPATH PREDICTION VIA SEMANTIC REPRESENTATION OF THE SCENE
Kepei Zhang, Meiqi Lu, Xuetao Zhang, Xi’an Jiaotong University, China; Zheng Lu, China Academy of Space Technology, China
HP-V1.V4.11: SAT: SELF-ADAPTIVE TRAINING FOR FASHION COMPATIBILITY PREDICTION
Ling Xiao, Toshihiko Yamasaki, The University of Tokyo, Japan