no code implementations • CVPR 2014 • David F. Fouhey, C. L. Zitnick
Given a static scene, a human can trivially enumerate the myriad of things that can happen next and characterize the relative likelihood of each.
no code implementations • CVPR 2014 • Bharath Hariharan, C. L. Zitnick, Piotr Dollar
Several popular and effective object detectors separately model intra-class variations arising from deformations and appearance changes.
no code implementations • CVPR 2013 • Dennis Park, C. L. Zitnick, Deva Ramanan, Piotr Dollar
We describe novel but simple motion features for the problem of detecting objects in video sequences.
no code implementations • CVPR 2013 • C. L. Zitnick, Devi Parikh
Importantly, abstract images also allow the ability to generate sets of semantically similar scenes.
no code implementations • CVPR 2013 • Joseph J. Lim, C. L. Zitnick, Piotr Dollar
Our features, called sketch tokens, are learned using supervised mid-level information in the form of hand drawn contours in images.