Image Segmentation by Probabilistic Bottom-Up Aggregation and Cue Integration

By Sharon Alpert, Meirav Galun, Achi Brandt, Ronen Basri. 2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007

621 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/4547c1e75fe24322b4e8777a3c6690bc98188118

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

Citations in the corpus

Salient object detection via bootstrap learning (2015, methodology): “The SED2 dataset [3] contains 100 images which are labeled with pixel-wise ground truth annotations.”
Saliency Detection via Absorbing Markov Chain (2013, neutral): “The third one is the SED dataset [28], which contains: the single object sub-dataset SED1 and two objects sub-dataset SED2.”
What Makes a Patch Distinct? (2013, methodology): “The reported run-times were computed on the SED1 dataset [3], on a Pentium 2.”
Learning Must-Link Constraints for Video Segmentation Based on Spectral Clustering (2014, background): “Other related work in segmentation have looked at merging superpixels with equivalence [1], but using hand-designed affinities, or learned pair-wise relations between superpixels [23], disregarding equivalence in the agglomerative merging process.”
Recurrent Attentional Networks for Saliency Detection (2016, background): “To further evaluate the proposed method “CNN-DecNN + RACDNN”, we compare it with two recent deep learningbased saliency detection methods (MCDL [49] and MDF [29]) on HKUIS, ECSSD, and SED2 datasets.”
Salient Object Detection in the Deep Learning Era: An In-Depth Survey (2019, background): “• SED [117] 1 comprises of a single-object subset SED1 and a two-object subset SED2, each of which contains 100 images and has pixel-wise annotations.”
Contextual Hypergraph Modeling for Salient Object Detection (2013, background): “SED-100 is a subset of the SED dataset [29, 30], and consists of 100 images.”
Constrained parametric min-cuts for automatic object segmentation (2010, methodology): “We use three publicly available datasets: Weizmann’s Segmentation Evaluation Database [28], MSRC [32] and the VOC2009 train and validation sets for the object-class segmentation problem [11].”
CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts (2012, methodology): “The last three rows show results from the Weizmann Segmentation Database.”
How to Evaluate Foreground Maps (2014, background): “The common measures for evaluating a binary map are PASCAL's VOC (Visual Object Classes) segmentation measure (referred to henceforth as PASCAL) [3] [11] [14] and F β -measure [2] [4] [10] [17] [23].”
Deep Level Sets for Salient Object Detection (2017, background): “The SED2 [2] is composed of 100 images with two salient objects.”
DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection (2015, methodology): “More specifically, ASD is a commonly used dataset Dataset ASD THUS THUR DUT-OMRON ECSSD PASCAL-S SOD SED2 Size 1000 10000 6232 5168 1000 850 300 100 TABLE I: Illustration of the image numbers associated with the eight datasets. in salient object detection.”
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”
Salient Object Detection: A Discriminative Regional Feature Integration Approach (2013, neutral): “This data set [3] contains two subsets: SED1 that has 100 images containing only one salient object and SED2 that has 100 images containing two salient objects.”
Contour Detection and Hierarchical Image Segmentation (2011, methodology): “To provide a basis of comparison for the OWT-UCM algorithm, we make use of the region merging (Felz-Hutt) [32], Mean Shift [34], Multiscale NCuts [33], and SWA [31], [52] segmentation methods reviewed in Section 2.”
Saliency Optimization from Robust Background Detection (2014, neutral): “[19], MSRA [25], SED1 [1] and SED2 [1].”