C
Charless C. Fowlkes
Researcher at University of California, Irvine
Publications - 185
Citations - 27274
Charless C. Fowlkes is an academic researcher from University of California, Irvine. The author has contributed to research in topics: Image segmentation & Segmentation. The author has an hindex of 53, co-authored 175 publications receiving 23475 citations. Previous affiliations of Charless C. Fowlkes include University of California, Berkeley & Amazon.com.
Papers
More filters
Proceedings ArticleDOI
A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics
TL;DR: In this paper, the authors present a database containing ground truth segmentations produced by humans for images of a wide variety of natural scenes, and define an error measure which quantifies the consistency between segmentations of differing granularities.
Journal ArticleDOI
Contour Detection and Hierarchical Image Segmentation
TL;DR: This paper investigates two fundamental problems in computer vision: contour detection and image segmentation and presents state-of-the-art algorithms for both of these tasks.
Journal ArticleDOI
Learning to detect natural image boundaries using local brightness, color, and texture cues
TL;DR: The two main results are that cue combination can be performed adequately with a simple linear model and that a proper, explicit treatment of texture is required to detect boundaries in natural images.
Journal ArticleDOI
Spectral grouping using the Nystrom method
TL;DR: The contribution of this paper is a method that substantially reduces the computational requirements of grouping algorithms based on spectral partitioning making it feasible to apply them to very large grouping problems.
Proceedings ArticleDOI
Globally-optimal greedy algorithms for tracking a variable number of objects
TL;DR: A near-optimal algorithm based on dynamic programming which runs in time linear in the number of objects andlinear in the sequence length is given which results in state-of-the-art performance.