MoRG research on human pose estimation accepted to ECCV

Monday, July 18, 2022

KAPAO, a human pose estimator developed by William McNally and John McPhee, as well as co-authors Kanav Vats and Alexander Wong, was accepted for publication at the 2022 European Conference on Computer Vision. Congratulations! 
  
KAPAO is an efficient single-stage multi-person human pose estimation method that models keypoints and poses aobjects within a dense anchor-based detection framework. KAPAO simultaneously detects pose objects and keypoint objects and fuses the detections to predict human poses. When not using test-time augmentation, KAPAO is much faster and more accurate than previous single-stage methods like DEKRHigherHRNetHigherHRNet + SWAHR, and CenterGroup. The paper can be found here, and the Github repository (550 stars) here.
   
Dr. McNally completed his PhD in April and is now a senior research engineer at Cleveland Golf.
   
kapao2

  1. 2022 (10)
    1. July (3)
    2. June (1)
    3. May (1)
    4. April (1)
    5. February (1)
    6. January (3)
  2. 2021 (13)
    1. November (4)
    2. August (5)
    3. April (2)
    4. March (2)
  3. 2020 (3)
    1. December (1)
    2. August (1)
    3. February (1)
  4. 2019 (8)
  5. 2018 (9)
  6. 2017 (1)
  7. 2016 (6)
  8. 2015 (5)