TY - GEN
T1 - A-HRNet
T2 - 2nd International Conference on Transdisciplinary AI, TransAI 2020
AU - Li, Ying
AU - Wang, Chenxi
AU - Cao, Yu
AU - Liu, Benyuan
AU - Luo, Yan
AU - Zhang, Honggang
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/9
Y1 - 2020/9
N2 - Recently, human pose estimation has received much attention in the research community due to its broad range of application scenarios. Most architectures for human pose estimation use multiple resolution networks, such as Hourglass, CPN, HRNet, etc. High Resolution Network (HRNet) is the latest SOTA architecture improved from Hourglass. In this paper, we propose a novel attention block that leverages a special Channel-Attention branch. We use this attention block as the building block and adopt the architecture of HRNet to build our Attention Based HRNet (A-HRNet). Experiments show that our model can consistently outperform HRNet on different datasets. Moreover, our model achieves the state-of-the-art performance on the COCO keypoint detection val2017 dataset (77.7 AP)1.
AB - Recently, human pose estimation has received much attention in the research community due to its broad range of application scenarios. Most architectures for human pose estimation use multiple resolution networks, such as Hourglass, CPN, HRNet, etc. High Resolution Network (HRNet) is the latest SOTA architecture improved from Hourglass. In this paper, we propose a novel attention block that leverages a special Channel-Attention branch. We use this attention block as the building block and adopt the architecture of HRNet to build our Attention Based HRNet (A-HRNet). Experiments show that our model can consistently outperform HRNet on different datasets. Moreover, our model achieves the state-of-the-art performance on the COCO keypoint detection val2017 dataset (77.7 AP)1.
KW - attention block
KW - human pose estimation
UR - https://www.scopus.com/pages/publications/85097610965
UR - https://www.scopus.com/pages/publications/85097610965#tab=citedBy
U2 - 10.1109/TransAI49837.2020.00016
DO - 10.1109/TransAI49837.2020.00016
M3 - Conference contribution
AN - SCOPUS:85097610965
T3 - Proceedings - 2020 2nd International Conference on Transdisciplinary AI, TransAI 2020
SP - 75
EP - 79
BT - Proceedings - 2020 2nd International Conference on Transdisciplinary AI, TransAI 2020
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 21 September 2020 through 23 September 2020
ER -