IVMSP-36.6
LIGHTPOSE: A LIGHTWEIGHT AND EFFICIENT MODEL WITH TRANSFORMER FOR HUMAN POSE ESTIMATION
Xiyang Liu, Peng Li, Ding Ni, Yan Wang, Hui Xue, Alibaba Group, China
Session:
Camera Calibration and Human Pose
Track:
Image, Video, and Multidimensional Signal Processing
Location:
Gather Area J
Presentation Time:
Thu, 12 May, 21:00 - 21:45 China Time (UTC +8)
Thu, 12 May, 13:00 - 13:45 UTC
Thu, 12 May, 13:00 - 13:45 UTC
Session Chair:
Ville Hautamaki, National University of Singapore
Session IVMSP-36
IVMSP-36.1: Camera Calibration through Camera Projection Loss
Talha Butt, Murtaza Taj, Lahore University of Management Sciences, Pakistan
IVMSP-36.2: Inferring Camera Intrinsics Based on Surfaces of Revolution: A Single Image Geometric Network Approach for Camera Calibration
Christopher Walker, Yuxing Wang, Yawen Lu, Guoyu Lu, Rochester Institute of Technology, United States of America
IVMSP-36.3: Text2Video: Text-driven Talking-head Video Synthesis with Personalized Phoneme - Pose Dictionary
Sibo Zhang, Jiahong Yuan, Miao Liao, Liangjun Zhang, Baidu Research, United States of America
IVMSP-36.4: TOWARDS ACCURATE CROSS-DOMAIN IN-BED HUMAN POSE ESTIMATION
Mohamed Afham, Udith Haputhanthri, Jathurshan Pradeepkumar, Mithunjha Anandakumar, Chamira Edussooriya, University of Moratuwa, Sri Lanka; Ashwin De Silva, Johns Hopkins University, United States of America
IVMSP-36.5: LEARNING MONOCULAR MESH RECOVERY OF MULTIPLE BODY PARTS VIA SYNTHETICS
Yu Sun, Wenpeng Gao, Yili Fu, Harbin Institute of Technology, China; Tianyu Huang, University of Maryland, China; Qian Bao, Wu Liu, AI Research of JD.com, China
IVMSP-36.6: LIGHTPOSE: A LIGHTWEIGHT AND EFFICIENT MODEL WITH TRANSFORMER FOR HUMAN POSE ESTIMATION
Xiyang Liu, Peng Li, Ding Ni, Yan Wang, Hui Xue, Alibaba Group, China