Hough Forests for Object Detection, Tracking, and Action Recognition

By Juergen Gall, Angela Yao, Nima Razavi, Luc Van Gool, Victor S. Lempitsky. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011

651 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/e8e82ae774e08eeebefc0cda1a64b66bf6884130

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

In Human-Computer Interaction

Citations in the corpus

Random Forests for Real Time 3D Face Analysis (2012, methodology): “in Gall et al. (2011) in order to be less sensitive to noise;”
Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images (2013, background): “3 will then describe how the camera pose is optimized by evaluating the forest at a sparse set of pixels.”
Body Parts Dependent Joint Regressors for Human Pose Estimation in Still Images (2014, methodology): “The used split functions are pixel comparisons as in [60]:”
Capturing Hands in Action Using Discriminative Salient Points and Physics Simulation (2015, methodology): “We use a Hough forest (Gall et al, 2011b) with 10 trees, each trained with 100000 positive and 100000 negative patches.”
Vision-as-Inverse-Graphics: Obtaining a Rich 3D Explanation of a Scene from a Single Image (2017, methodology): “In addition, [6] used random forests to predict (in our notation) p(z|xi), and were able to obtain good results for problems of object detection, tracking and action detection.”
Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network (2015, methodology): “Various learning algorithms have been incorporated including online boosting (Grabner et al., 2006; Saffari et al., 2010), multiple instance learning (Babenko et al., 2011), structured support vector machine (Hare et al., 2011), and online random forest (Gall et al., 2011; Schul-ter et al., 2011).”
Prime Object Proposals with Randomized Prim's Algorithm (2013, methodology): “The proposals can indeed be used as a replacement for the computationally expensive sliding window approach for object detection [6] [12] [15].”
A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation (2017, background): “Various learning approaches such as Support Vector Machines, boosting [96] and random forest [34] have been used with varying degree of success.”
Latent-Class Hough Forests for 3D Object Detection and Pose Estimation (2014, methodology): “This is done by individual parts voting, in a Hough space, for the object anchor point(s) [16, 26, 43, 55, 67, 71–73] or the object 3D rotation [21, 23, 26] and local maxima are chosen as hypotheses.”
Informed Haar-Like Features Improve Pedestrian Detection (2014, background): “Yet, we note that corresponding features are either determined by means of exhaustive searches over all possible variations [24] or by means of less exhaustive random sampling [13].”
Fast action proposals for human action detection and search (2015, methodology): “A united framework based Hough forest is presented for human detection, tracking, and action recognition in [15].”
A visual analytics approach to understanding cycling behaviour (2012, neutral): “An introduction to C-IL 2 P is also presented, followed by a review of propositionalization and feature selection.”
Sequential Max-Margin Event Detectors (2014, methodology): “[6] used Hough Forests to segment the spatial-temporal cuboids of person from videos.”
Motion Capture of Hands in Action Using Discriminative Salient Points (2012, methodology): “A Hough forest classifier [30] was trained on 400 manually labeled images of nails/non-nails seen from different viewing angles.”
Dense Non-rigid Shape Correspondence Using Random Forests (2014, background): “Applications range from object detection, tracking and action recognition [7] to semantic image segmentation and categorization [20], and 3D pose estimation [22] to name just a few.”
Global Hypothesis Generation for 6D Object Pose Estimation (2016, methodology): “[7, 26] used a Hough-voting-scheme for 2D object detection and coarse pose estimation.”