Overview:
icon

Consider the image patches at right. Though they lack global context, it is often clear which contain object boundaries and which do not. We are developing algorithms that integrate local image measurements in order to provide global explanations of scenes in terms of objects, surfaces and their spatial relations. This includes algorithms for bottom-up boundary detection and segmentation from local features as well integrating top-down knowledge such as the detection of familiar objects.

Publications:
icon
Low-rank Bilinear Pooling for Fine-grained Classification
Shu Kong, Charless Fowlkes
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
[pdf]
icon
icon
icon
icon
Hierarchical Planar Correlation Clustering for Cell Segmentation
Julian Yarkony, Chong Zhang, Charless Fowlkes
Energy Minimization Methods in Computer Vision and Pattern Recognition, 2015, 492--504.
[pdf]
icon
Planar Ultrametrics for Image Segmentation
Julian Yarkony, Charless Fowlkes
Neural Information Processing Systems (NIPS), 2015.
[pdf]
icon
icon
icon
icon
icon
icon
icon
icon
icon
Contour Detection and Hierarchical Image Segmentation
Pablo Arbelaez, Michael Maire, Charless Fowlkes, Jitendra Malik
IEEE PAMI, 2011, 33(5).
[pdf]
icon
icon
icon
From Contours to Regions: An Empirical Evaluation
Pablo Arbelaez, Michael Maire, Charless Fowlkes, Jitendra Malik
CVPR, 2009.
[pdf]
icon
icon
Using Contours to Detect and Localize Junctions in Natural Images
Michael Maire, Pablo Arbelaez, Charless Fowlkes, Jitendra Malik
CVPR, 2008.
[pdf]
icon
Learning Probabilistic Models for Contour Completion.
Xiaofeng Ren, Charless Fowlkes, Jitendra Malik
IJCV, 2008, 77, 47-63.
[pdf]
icon
Figure/Ground Assignment in Natural Images
Xiaofeng Ren, Charless Fowlkes, Jitendra Malik
ECCV, 2006, II: 614-627.
[pdf]
icon
Cue Integration for Figure/Ground Labeling
Xiaofeng Ren, Charless Fowlkes, Jitendra Malik
Advances in Neural Information Processing Systems 18, 2006, 1121--1128.
[pdf]
icon
icon
Mid-level cues improve boundary detection
Xiaofeng Ren, Charless Fowlkes, Jitendra Malik
UC Berkeley, 2005, UCB//CSD-05-1382.
[pdf]
icon
How Much Does Globalization Help Segmentation?
Charless Fowlkes, Jitendra Malik
UC Berkeley, 2004, UCB//CSD-04-1340.
[pdf]
icon
icon
Spectral Grouping Using the Nyström Method
Charless Fowlkes, Serge Belongie, Fan Chung, Jitendra Malik
IEEE PAMI, 2004, 26, 2, 214-225.
[pdf]
icon
icon
Spectral Partitioning with Indefinite Kernels Using the Nyström Extension
Serge Belongie, Charless Fowlkes, Fan Chung, Jitendra Malik
ECCV, 2002, III: 531 ff..
[pdf]
icon
Learning to Detect Natural Image Boundaries Using Brightness and Texture
David, Martin, Charless, Fowlkes, Jitendra Malik
Advances in Neural Information Processing Systems, 2002.
[pdf]
icon
icon
Efficient Spatiotemporal Grouping Using the Nyström Method
Charless Fowlkes, Serge Belongie, Jitendra Malik
CVPR, 2001, I:231-238.
[pdf]