À¶Ý®ÊÓƵ

KAPAO, a human pose estimator developed by William McNally ²¹²Ô»åÌýJohn McPhee, as well as co-authors Kanav Vats and Alexander Wong,Ìýwas accepted for publication at the . Congratulations! 
ÌýÌý
KAPAO is an efficient single-stage multi-person human pose estimation method that model²õÌýk±ð²â±è´Ç¾±²Ô³Ù²õÌýa²Ô»åÌýp´Ç²õ±ð²õÌýa²õÌýobjects within a dense anchor-based detection framework. KAPAO simultaneously detect²õÌýpose objects ²¹²Ô»åÌýkeypoint 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 ,Ìý,Ìý, ²¹²Ô»åÌý. The paper can be found , and the Github repository (550 stars) .
ÌýÌý 
Dr. McNally completed his PhD in April and is now a senior research engineer at Cleveland Golf.
ÌýÌý