Class-specific Hough forests for object detection

By Juergen Gall, Victor S. Lempitsky. 2009

664 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation (2019, methodology): “Additionally, our method bears a similarity to Hough-Voting-based methods [4, 39, 21, 5] and recent works by Kendall et al.”
Learning Complexity-Aware Cascades for Deep Pedestrian Detection (2015, methodology): “The cascade used 2048 decision trees of depth 2, and was bootstrapped 6 times during training, after stages {32, 128, 256, 512, 1024, 1536}, using the procedure of [10, 30].”
Deep Hough Voting for 3D Object Detection in Point Clouds (2019, background): “More recently, [15] demonstrated improved voting-based 6D pose estimation by using deep features extracted to build a code-book.”
Efficient Human Pose Estimation from Single Depth Images (2013, methodology): “We show that these make our method both faster and more accurate than Hough Forests [20].”
Hough Regions for Joining Instance Localization and Segmentation (2012, methodology): “We assume that we are given any generalized Hough voting method like [17, 5, 18, 19], which provides our N voting elements Xi within the test image and”
Robust Nucleus/Cell Detection and Segmentation in Digital Pathology and Microscopy Images: A Comprehensive Review (2016, methodology): “Inspired by [143] and [144], the CNN model in [162]”
Recent advances and trends in visual tracking: A review (2011, methodology): “In Gall et al. [29], extended the Hough-transform based class-speciﬁc ISM to construct a novel Hough forest detection method.”
Efficient regression of general-activity human poses from depth images (2011, methodology): “Gall and Lempitsky [7] replace the visual word codebook of ISM by learning a random forest in which each tree assigns every image pixel to a decision-tree leaf node at which is stored a potentially large collection of votes.”
Vehicle detection in aerial imagery : A small target detection benchmark (2016, methodology): “For completeness, we have also implemented a template matching approach [80], as template matching was considered in the past as the standard approach for small target detection, and we tested a non window protocol based on the Hough forest [81].”
Fast PRISM: Branch and Bound Hough Transform for Object Class Detection (2011, background): “Indeed, object class detectors based on ISM’s idea have become increasingly popular (Liebelt et al. 2008; Opelt et al. 2006; Maji and Malik 2009; Gall and Lempitsky 2009; Chum and Zisserman 2007).”
Real-time facial feature detection using conditional regression forests (2012, methodology): “While modeling the distribution in a non-parametric manner using a Parzen estimate over the offsets of all patches reaching the leaf at training time as in [15] does not impose any assumption on the type of distribution, it prevents real-time performance for larger training sets.”
Neural Decision Forests for Semantic Image Labelling (2014, methodology): “They have been applied to various tasks including semantic segmentation [30, 20], object detection [15, 20], and edge detection [12].”