Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Early research in still-image action recognition focused on engineered features and part-based models. A prominent direction involved human pose and body part detection, most notably through the use of “poselets” fragments of human pose trained as detectors to form activation vectors for classification (Bourdev & Malik, 2009; Maji, Bourdev & Malik, 2011; Thurau & Hlavác, 2008).
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
