184260348236f9554fe9375772ff966e-Reviews.html

"NIPS 2013 Neural Information Processing Systems December 5 - 10, Lake Tahoe, Nevada, USA",,, "Paper ID:","1139" "Title:","Action is in the Eye of the Beholder: Eye-gaze Driven Model for Spatio-Temporal Action Localization" Reviews First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper proposes a method for action detection (localization and classification of actions) using weakly supervised information (action labels + eye gaze information, no explicit definition of bounding boxes). Overall, the spatio-temporal search (a huge spatio-temporal space) is done using dynamic programming and a max-path algorithm. Gaze information is introduced into framework through a loss which acounts for gaze density at a given location. QUALITY: The paper seems technically sound and makes for a nice study given gaze information.