Spatial priors for part-based recognition using statistical models

By David J. Crandall, Pedro F. Felzenszwalb, Dan Huttenlocher. Computer Vision and Pattern Recognition, 2005

339 citations recorded by the source corpus.

Subfields: Environmental Engineering, Geometry and Topology, Ocean Engineering

View Paper: https://www.semanticscholar.org/paper/626a742de034cba3a8706510aca63bd287691995

How researchers see this paper

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

In Environmental Engineering

In Geometry and Topology

In Ocean Engineering

Citations in the corpus

Recognition using visual phrases (2011, background): “Conventional wisdom suggests detecting components like “person” and “horse” independently, and then describing the relation.”
Sparse and Locally Constant Gaussian Graphical Models (2009, methodology): “In this paper, we propose local constancy as a prior for learning Gaussian graphical models, which is natural for spatial datasets such as those encountered in computer vision [1, 2, 3].”
A Review of Computer Vision Techniques for the Analysis of Urban Traffic (2011, background): “The idea of local interest-point features as used in [28], [85], [88], and [106] and is extended to boundary elements.”
Nonparametric Scene Parsing via Label Transfer (2011, background): “Moreover, the authors in [47] showed that with a database of 80 million images, even simple SSD match can give semantically meaningful parsing for 32 32 images.”
Birdlets: Subordinate categorization using volumetric primitives and pose-normalized appearance (2011, background): “Constellation models [11] [48] and their computationally attractive variants [14] [27] are composed of a set of local part detectors together with one or more probability density functions describing the parts' relative locations.”
Weakly Supervised Learning of Part-Based Spatial Models for Visual Object Recognition (2006, methodology): “Two recent papers have demonstrated improved object detection results by not using feature detectors [ 2 ,7].”
The Cross-Depiction Problem: Computer Vision Algorithms for Recognising Objects in Artwork and in Photographs (2015, methodology): “Deformable models of various types are widely used to model object classes for detection tasks, including several kinds of deformable template models [8, 9] and a variety of part-based models [1, 10, 22, 20, 23, 27, 42].”
A Boundary-Fragment-Model for Object Detection (2006, neutral): “[9], Bar-Hillel et al.”
Automatic feature localisation with constrained local models (2008, background): “Recently a denser graph matching approach using k-fans has been suggested to provide a stronger shape constraint [20].”
A discriminatively trained, multiscale, deformable part model (2008, background): “The spatial model for the part locations is equivalent to a star graph or 1-fan [3] where the coarse template serves as a reference position.”
Each Part Matters: Local Patterns Facilitate Cross-View Geo-Localization (2020, background): “The local feature has been widely studied in the design of hand-crafted algorithms [27], [28], [29], [30], [31].”
This Hand Is My Hand: A Probabilistic Approach to Hand Disambiguation in Egocentric Video (2014, methodology): “As is common in part-based models [4], we assume the relative spatial distribution between each pair of parts is Gaussian.”
From simple innate biases to complex visual concepts (2012, methodology): “The existing appearance-based classifier (28) and a context-based classifier (32) are trained on the extracted patches.”
Guiding model search using segmentation (2005, background): “, mixture of trees [11], triangulated graph [21], k-fan [1], common-factor model [9].”
The Layout Consistent Random Field for Recognizing and Segmenting Partially Occluded Objects (2006, background): “It is possible to pre-select which parts are used as in [4], though this requires considerable human effort for each new object class.”
Object Detection with Discriminatively Trained Part Based Models (2010, background): “, [2], [6], [9], [15], [18], [20], [28], [42]).”