• Publications
  • Influence
A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics
TLDR
A database containing 'ground truth' segmentations produced by humans for images of a wide variety of natural scenes is presented and an error measure is defined which quantifies the consistency between segmentations of differing granularities.
Learning to detect natural image boundaries using local brightness, color, and texture cues
TLDR
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.
Spectral grouping using the Nystrom method
TLDR
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.
Globally-optimal greedy algorithms for tracking a variable number of objects
TLDR
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.
Photo Aesthetics Ranking Network with Attributes and Content Adaptation
TLDR
This work proposes to learn a deep convolutional neural network to rank photo aesthetics in which the relative ranking of photo aesthetics are directly modeled in the loss function.
From contours to regions: An empirical evaluation
TLDR
This work provides extensive experimental evaluation to demonstrate that, when coupled to a high-performance contour detector, the OWT-UCM algorithm produces state-of-the-art image segmentations.
Using contours to detect and localize junctions in natural images
TLDR
A new high-performance contour detector using a combination of local and global cues that provides the best performance to date on the Berkeley Segmentation Dataset (BSDS) benchmark and shows that improvements in the contour model lead to better junctions.
Discriminative models for multi-class object layout
Many state-of-the-art approaches for object recognition reduce the problem to a 0-1 classification task. Such reductions allow one to leverage sophisticated classifiers for learning. These models are
From contours to regions: An empirical evaluation
TLDR
This work provides extensive experimental evaluation to demonstrate that, when coupled to a high-performance contour detector, the OWT-UCM algorithm produces state-of-the-art image segmentations.
Discriminative Models for Multi-Class Object Layout
TLDR
A unified model for multi-class object recognition is introduced that casts the problem as a structured prediction task and how to formulate learning as a convex optimization problem is shown.
...
1
2
3
4
5
...