Class-Specific, Top-Down Segmentation

By Eran Borenstein, Shimon Ullman. 2002

494 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Industrial and Manufacturing Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Industrial and Manufacturing Engineering

Citations in the corpus

Hypercolumns for object segmentation and fine-grained localization (2014, background): “Borenstein and Ullman [4] first suggested the idea of using class-specific knowledge for segmentation.”
Barrier Frank-Wolfe for Marginal Inference (2015, background): “(3) Restricted Boltzmann Machines (RBMs): From the Probabilistic Inference Challenge 2011.3 (4) Horses: Large (N ≈ 12000) MRFs representing images from the Weizmann Horse Data (Borenstein and Ullman, 2002) with potentials learned by Domke (2013).”
Iterative Instance Segmentation (2015, background): “Borenstein and Ullman [3] first suggested using category-specific information to improve the accuracy of segmentation.”
Object Skeleton Extraction in Natural Images by Fusing Scale-Associated Deep Side Outputs (2016, methodology): “The other one is the WH-SYMMAX dataset [25], which is converted from the Weizmann Horse dataset [7].”
Contextual Models for Object Detection Using Boosted Random Fields (2004, methodology): “The weak learners we use for the local evidence potentials are based on the segmentation fragments proposed in [2].”
Combined Object Categorization and Segmentation With an Implicit Shape Model (2004, background): “Borenstein & Ullman [3] generate class-specific segmentations by combining object fragments in a jigsaw-puzzle fashion.”
Crowdsourcing in Computer Vision (2016, unknown): “In addition, datasets such as Weizmann Horses [Borenstein and Ullman, 2002], CMU-Cornell iCoseg [Batra et al.”
Learning AND-OR Templates for Object Recognition and Detection (2013, methodology): “We apply our learning algorithm for the Weizmann horse dataset [1] and perform detection of articulated horses.”
A mobile vision system for robust multi-person tracking (2008, background): “Several instantiations of this concept have been successfully demonstrated in recent years, among them the feedback from recognition to segmentation [4] [17], from geometry estimation to object detection [13] [15], and the often-used feedback from tracking to detection (e.g. [16]).”
Finding Things: Image Parsing with Regions and Per-Exemplar Detectors (2013, background): “The idea of transferring object segmentation masks from training to test images – either whole or in " fragments " – has been explored before in the literature – see, e.g., [2] [17] [20].”
Modeling object appearance using Context-Conditioned Component Analysis (2015, methodology): “Horses We use the Weizmann Horse Dataset [3] that consists of images of horses and corresponding segmentation masks.”
Domain Adaptation for Semantic Segmentation of Urban Scenes (2017, background): “, assigning a category label to every pixel of an image or video frame [6].”
Beyond Bounding Boxes: Precise Localization of Objects in Images (2015, background): “Borenstein and Ullman [6] first suggested the idea of using class-specific knowledge for segmentation.”
Object cosegmentation (2011, result): “reports results for a subset of the Weizmann horse database [6].”
Loosecut: Interactive image segmentation with loosely bounded boxes (2015, methodology): “To justify the proposed LooseCut algorithm, we conduct experiments on three widely used image datasets – the GrabCut dataset [15], the Weizmann dataset [3, 5], and the iCoseg dataset [4], and compare its performance”
Visual Parsing After Recovery From Blindness (2009, background): “In circumscribed domains, these heuristics can account rather well for human performance (Elder & Zucker, 1998; Kanizsa, 1979; Koffka, 1935), but using them for analyzing realworld imagery remains an open challenge ( Borenstein & Ullman, 2002; Shi & Malik, 1997).”
Class-specific Hough forests for object detection (2009, unknown): “We have also considered the Weizmann Horses dataset [5] containing the near-side views of horses in natural environments under varying scale and strongly varying poses.”
Learning Active Basis Model for Object Detection and Recognition (2010, methodology): “Some of the images are taken from the Weizmann data set (Borenstein and Ullman 2002) and the INRIA data set (Ferrari et al.”
Learning Stochastic Feedforward Neural Networks (2013, methodology): “We also tested on the Weizmann segmentation database [21] of horses, learning a conditional distribution of horse appearances conditioned on the segmentation mask.”
Boundary Detection Benchmarking: Beyond F-Measures (2013, background): “In the development of boundary detection, datasets [16, 8, 5, 1] - along with their evaluation criteria1 - have played critical roles.”