[Free GPT-4]
[DeepSeek]
J Pont-Tuset, P Arbelaez, JT Barron… - IEEE transactions on …, 2016 - ieeexplore.ieee.org
We propose a unified approach for bottom-up hierarchical image segmentation and object
proposal generation for recognition, called Multiscale Combinatorial Grou** (MCG). For …

Feedforward semantic segmentation with zoom-out features

M Mostajabi, P Yadollahpour… - Proceedings of the …, 2015 - openaccess.thecvf.com
We introduce a purely feed-forward architecture for semantic segmentation. We map small
image elements (superpixels) to rich feature representations extracted from a sequence of …

Perceptual organization and recognition of indoor scenes from RGB-D images

S Gupta, P Arbelaez, J Malik - Proceedings of the IEEE …, 2013 - openaccess.thecvf.com
We address the problems of contour detection, bottomup grou** and semantic
segmentation using RGB-D data. We focus on the challenging setting of cluttered indoor …

Beyond grids: Learning graph representations for visual recognition

Y Li, A Gupta - Advances in neural information processing …, 2018 - proceedings.neurips.cc
We propose learning graph representations from 2D feature maps for visual recognition. Our
method draws inspiration from region based recognition, and learns to transform a 2D image …

Video segmentation by tracking many figure-ground segments

F Li, T Kim, A Humayun, D Tsai… - Proceedings of the …, 2013 - openaccess.thecvf.com
We propose an unsupervised video segmentation approach by simultaneously tracking
multiple holistic figureground segments. Segment tracks are initialized from a pool of …

CPMC: Automatic object segmentation using constrained parametric min-cuts

J Carreira, C Sminchisescu - IEEE transactions on pattern …, 2011 - ieeexplore.ieee.org
We present a novel framework to generate and rank plausible hypotheses for the spatial
extent of objects in images using bottom-up computational processes and mid-level …

Geodesic object proposals

P Krähenbühl, V Koltun - Computer Vision–ECCV 2014: 13th European …, 2014 - Springer
We present an approach for identifying a set of candidate objects in a given image. This set
of candidates can be used for object recognition, segmentation, and other object-based …