Latent Regression Forest: Structured Estimation of 3D Articulated Hand Posture

By Danhang Tang, Hyung Jin Chang, Alykhan Tejani, Tae-Kyun Kim. 2014

421 citations recorded by the source corpus.

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

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

In Human-Computer Interaction

Citations in the corpus

Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “Among a large number of human representation approaches [24], [25], [26], [27], [28], [29], most of the existing 3D based methods can be broadly grouped into two categories: representations based on local features [30], [31] and skeletonbased representations [32] [33] [34].”
Multi-scale Deep Learning for Gesture Detection and Localization (2014, background): “els, exploring spatial relationships between body and hand parts, have recently attracted close attention from the vision community [25, 26].”
Cross-Modal Deep Variational Hand Pose Estimation (2018, methodology): “Much work exists that tracks articulated hands in streams of depth images, or that estimates hand pose [15, 16, 27, 35] from individual depth frames.”
Latent-Class Hough Forests for 3D Object Detection and Pose Estimation (2014, background): “Hough-based methods have worked extremely well in the case where there is no background clutter present [23, 67, 72, 73] and even in the case of previously unseen backgrounds [14, 21, 43].”
TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 1 ModDrop (2018, positive): “On the other hand, in [27] the authors proposed the Latent Regression Forest for coarse-to-fine search of joint positions.”
Hand Keypoint Detection in Single Images Using Multiview Bootstrapping (2017, background): “These are broadly classifiable into generative methods [14], discriminative methods [24, 25, 9, 30, 22, 27], or hybrid methods [20, 16, 18, 26, 31].”
Accurate, Robust, and Flexible Real-time Hand Tracking (2015, background): “[27, 26] extend this work demonstrating more complex poses at 25Hz.”
Training a Feedback Loop for Hand Pose Estimation (2015, methodology): “Accurate hand pose estimation is an important requirement for many Human Computer Interaction or Augmented Reality tasks [10], and has been steadily regaining ground as a focus of research interest in the past few years [13, 14, 19, 23, 26, 30, 31, 37], probably because of the emergence of 3D sensor”
First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations (2017, background): “An important limitation is the difficulty of obtaining accurate 3D hand pose annotations leading researchers to resort to synthetic [3, 10, 35, 48, 53], manually or semi-automatically annotated [38, 58, 59, 61] datasets, resulting in non-realistic images, a low number of samples, and often inconsist”
Random tree walk toward instantaneous 3D human pose estimation (2015, methodology): “As with the methods of [19, 13, 20, 5, 21], the proposed method is also based on randomized trees.”
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map (2017, methodology): “The ICVL dataset [40] consists of 330K training and 1.”
Spatial Attention Deep Net with Partial PSO for Hierarchical Hybrid Hand Pose Estimation (2016, methodology): “ICVL [34] dataset is a real sequence captured by Intel RealSense with the range of view about 120 degrees consisting 1596 test frames and 16008 training frames.”
Robust 3D Hand Pose Estimation in Single Depth Images: From Single-View CNN to Multi-View CNNs (2016, methodology): “Data-driven approaches [3, 4, 5, 6]: • Find the optimal hand pose parameters via fitting a deformable 3D hand model to input image observations • Need to pre-define hand size and motion constraints; sensitive to initialization”
GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB (2017, background): “Numerous follow-up works have been proposed to improve the generative component [44, 46, 51, 52], and the learning-based discriminator [58, 16, 45, 49, 55, 7, 37, 22, 61, 5, 4, 29].”
Monocular Real-Time Hand Shape and Motion Capture Using Multi-Modal Data (2020, background): “, leveraging stereo cameras [50] or a depth camera [36, 42, 38, 49], which prevents collecting diverse data at large scale.”
Cascaded hand pose regression (2015, methodology): “Regressing all parts together is less effective and it slows down the convergence of boosted regression framework [12], because each weak regressor has relatively large errors.”