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,...
The problem of simultaneous feature extraction and selection, for classifier design, is considered. A new framework is proposed, based on boosting algorithms that can either 1) s...
This paper presents a novel approach to utilizing high level knowledge for the problem of scene recognition in an active vision framework, which we call active scene recognition. ...
Weakly supervised discovery of common visual structure in highly variable, cluttered images is a key problem in recognition. We address this problem using deformable part-based mo...
—CENTRIST (CENsus TRansform hISTogram), a new visual descriptor for recognizing topological places or scene categories, is introduced in this paper. We show that place and scene ...
Abstract— Scene recognition is a highly valuable perceptual ability for an indoor mobile robot, however, current approaches for scene recognition present a significant drop in p...
Pablo Espinace, Thomas Kollar, Alvaro Soto, Nichol...
We describe a framework for robot navigation that exploits the continuity of image sequences. Tracked visual features both guide the robot and provide predictive information about...
We propose a robust scene recognition framework using scene context information for multimedia contents. Multimedia contents consist of scene sequences that are more likely to hap...
We propose a robust scene recognition system for baseball broadcast videos. This system is based on the data-driven approach which has been successful in continuous speech recogni...
The concept of probabilistic Latent Semantic Analysis (pLSA) has gained much interest as a tool for feature transformation in image categorization and scene recognition scenarios. ...