We propose a new method for matching two 3D point sets of identical cardinality with global similarity but local non-rigid deformations and distribution errors. This problem arises...
Maximum a posteriori (MAP) inference in Markov Random Fields (MRFs) is an NP-hard problem, and thus research has focussed on either finding efficiently solvable subclasses (e.g. t...
Dhruv Batra, Andrew Gallagher, Devi Parikh, Tsuhan...
We present a novel approach to representing and recognizing composite video events. A composite event is specified by a scenario, which is based on primitive events and their tem...
The bounding box representation employed by many popular object detection models [3, 6] implicitly assumes all pixels inside the box belong to the object. This assumption makes th...
In this paper we reformulate the 3D reconstruction of deformable surfaces from monocular video sequences as a labeling problem. We solve simultaneously for the assignment of featu...