We propose a novel framework for reconstructing homogenous, transparent, refractive height-fields from a single viewpoint. The height-field is imaged against a known planar back...
We introduce the problem of scene viewpoint recognition, the goal of which is to classify the type of place shown in a photo, and also recognize the observer’s viewpoint within ...
Jianxiong Xiao, Krista A. Ehinger, Aude Oliva, Ant...
In this paper we propose a novel Conditional Random Field (CRF) formulation for the semantic scene labeling problem which is able to enforce temporal consistency between consecuti...
In this paper we present the first large-scale scene attribute database. First, we perform crowd-sourced human studies to find a taxonomy of 102 discriminative attributes. Next,...
We propose a framework that performs action recognition and identity maintenance of multiple targets simultaneously. Instead of first establishing tracks using an appearance mode...