Composite Templates for Cloth Modeling and Sketching

By Hong Chen, Zijian Xu, Ziqiang Liu, Song-Chun Zhu. 2006

162 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Neuroaesthetics in fashion: Modeling the perception of fashionability (2015, background): “Early work focused on manually building composite clothing models to match to images [4].”
Parsing clothing in fashion photographs (2012, background): “Later work focused on grammatical representations of clothing using artists’ sketches [6].”
Unsupervised Learning of a Probabilistic Grammar for Object Detection and Parsing - eScholarship (2007, background): “The grammars are based on AND-OR graphs [1, 5, 6], which relate to mixtures of trees [7].”
Clothing Co-parsing by Joint Image Segmentation and Labeling (2014, background): “One classic work [6] proposed a composite And-Or graph template for modeling and parsing clothing configurations.”
Who Blocks Who: Simultaneous clothing segmentation for grouping images (2011, background): “It has been proven that clothing segmentation will benefit human detection [18] and recognition [9], pose estimation [16] and human sketches [5].”
Semantic event representation and recognition using syntactic attribute graph grammar (2009, background): “In addition, the attribute graph grammar was first presented by Han and Zhu (2005), Chen et al. (2006), and Zhu and Mumford (2007) further discussed it as a large scale knowledge representation.”
Street-to-shop: Cross-scenario clothing retrieval via parts alignment and auxiliary set (2012, methodology): “One representative work for clothing modeling is from Chen et al. [7], which used an And-Or graph representation to produce a large set of composite graphical templates accounting for the wide vari-abilities of cloth conﬁgurations.”
Introduction to a Large-Scale General Purpose Ground Truth Database: Methodology, Annotation Tool and Benchmarks (2007, methodology): “Moreover, the tool is associated with an And-Or Graph knowledgebase[4], which organizes and summarizes labeled visual knowledge in a universal way.”
Unsupervised Learning of a Probabilistic Grammar for Object Detection and Parsing (2006, background): “The grammars are based on AND-OR graphs [1, 5, 6], which relate to mixtures of trees [7].”
Compositional Boosting for Computing Hierarchical Image Structures (2007, background): “More specifically, as compositionality and part-sharing [5, 3, 11] are common principles in object modeling and recognition, an effective inference algorithm must explore the compositional structures.”
Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos (2009, methodology): “In computer vision, AND-OR graphs have been used to represent compositional patterns [26, 4].”
Parsing video events with goal inference and intent prediction (2011, background): “Leaf nodes for atomic actions are defined by a set of fluents (time varying properties) of the agents and their interactions with objects in the scene.”
A stochastic graph grammar for compositional object representation and recognition (2009, methodology): “5(c), different frames are matched to the sketch-graph of the input image using thin-plate-spline warping with an affine transformation described in [15].”
Apparel Classification with Style (2012, unknown): “[4] manually built a tree of composite clothing templates and match those to the”
Deep Human Parsing with Active Template Regression (2015, methodology): “Previous methods are generally based on two types of pipelines: the hand-designed pipeline and the deep learning pipeline.”