Guiding model search using segmentation

By Greg Mori. Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1, 2005

352 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/32510e7f88bc0767fbbc811397ba068dbc4cf549

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion (2010, background): “A variety of statistical [1, 2, 7, 17, 30, 74, 75, 76] as well as deterministic methods [46, 83, 69] have been developed for tracking people from single [1, 2, 21, 30, 36, 45, 46, 58, 59, 60, 63, 75] or multiple [7, 17, 26, 74] views.”
Event Detection in Crowded Videos (2007, background): “This is the spatio-temporal equivalent of the concept of superpixels [19].”
Unsupervised segmentation of natural images via lossy data compression (2008, methodology): “In this paper, we use a publicly available superpixel code [23].”
Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments (2008, methodology): “Therefore, we provide superpixel representations for all the images in the database based on Mori’s online implementation [19].”
SEEDS: Superpixels Extracted Via Energy-Driven Sampling (2012, background): “Normalized Cuts is computationally demanding, and there have been attempts to speed it up [9].”
Concealed Object Detection (2021, methodology): “, EGNet [12], PFANet [81]), pre-processing techniques [86], or post-processing strategies such as [87], [88].”
SLIC Superpixels Compared to State-of-the-Art Superpixel Methods (2012, background): “They have become key building blocks of many computer vision algorithms, such as top scoring multi-class object segmentation entries to the PASCAL VOC Challenge [9], [29], [11], depth estimation [30], segmentation [16], body model estimation [22], and object localization [9].”
Superpixels and Supervoxels in an Energy Optimization Framework (2010, background): “Many methods that need regular superpixels use normalized cuts [9, 1, 2, 4, 5].”
SLIC Superpixels ? (2010, methodology): “The superpixels from NC05 have been used in body model estimation [6] and skeletonization [5].”
Structured Learning and Prediction in Computer Vision (2011, background): “Superpixels introduced in [124, 107] are a common example of this reduction for image labeling tasks: by representing large sets of pixels as a single superpixel, a set of decisions — assigning one label to each pixel — is reduced to the single decision of assigning a label to the superpixel, as sho”
A Bayesian Model for Simultaneous Image Clustering, Annotation and Object Segmentation (2009, methodology): “The software used for over-segmentation is discussed in [17] and is available online (http://www.”
Beyond pixels: A comprehensive survey from bottom-up to semantic image segmentation and cosegmentation (2015, methodology): “s been applied to reduce the model complexity and improve speed and accuracy of some complex vision tasks, such as estimating dense correspondence eld [4], scene parsing [5] and body model estimation [6]. [7, 8, 9] have used segmented regions to facilitate object recognition, which provides better l”
Max Margin AND/OR Graph learning for parsing the human body (2008, methodology): “Finally, our inference algorithm outputs a single pose estimate only which, as we show in section (6), is better than any of the results in the list output by Srinivasan and Shi [18] (and their output list is better than that provided by other algorithms [9]).”
Shape-based pedestrian parsing (2011, methodology): “This approach is grounded in a long line of work starting with Ren and Malik [25] which scores multiple bottom-up segmentation hypotheses [21, 20, 26, 19, 5, 18].”
Superpixel lattices (2008, methodology): “However, it is surprising that normalized cuts ([13] + [14]) does not perform best.”
Segmentation of Multivariate Mixed Data via Lossy Data Coding and Compression (2007, methodology): “We compute the superpixel oversegmentation by using a publicly available code [34].”
Superpixels and Polygons Using Simple Non-iterative Clustering (2017, background): “After their introduction [27], several applications such as object localization [14], multi-class segmentation [15], optical flow [22], body model estimation [24], object tracking [35], and depth estimation [37] took advantage of superpixels .”
Camouflaged Object Detection (2020, methodology): “, EGNet [77], PFANet [78], PoolNet [38]), preprocessing techniques [46], or postprocessing strategies (e.”