Cascaded hand pose regression

By Xiao Sun, Yichen Wei, Shuang Liang, Xiaoou Tang. 2015

411 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, 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 Computer Vision and Pattern Recognition

In Control and Systems Engineering

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].”
SurfNet: Generating 3D Shape Surfaces Using Deep Residual Networks (2017, methodology): “Unlike standard methods which estimate the joint angle [7, 29] or joint position parameters [27, 32, 33], we reconstruct the full 3D surface.”
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map (2017, methodology): “In all cases, ∆ Z is set to 0 mm. Similar values to the real human hand size and camera projection parameters in the MSRA dataset were used for our visualization.”
Robust 3D Hand Pose Estimation in Single Depth Images: From Single-View CNN to Multi-View CNNs (2016, methodology): “Index Terms—3D hand pose estimation, Convolutional neural networks, Multi-view CNNs F”
3D Hand Shape and Pose From Images in the Wild (2019, background): “There is a rich literature on 3D hand pose and reconstruction from depth [62, 66, 10, 36, 61, 11, 43, 45, 19, 20, 24, 30, 37, 48, 52, 53, 59, 64], image and depth [26, 32, 49, 28], stereo [33, 65, 41] and multiple images [8, 31, 50].”
Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks (2017, background): “After cascading more than four or five weak regressors, the performance of cascaded regression is hard to improve further [52, 17].”
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”
Knowledge As Priors: Cross-Modal Knowledge Generalization for Datasets Without Superior Knowledge (2020, background): “Estimating 3D hand poses from depth maps has made great progress in the past few years [10, 11, 26, 32, 43].”
Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies (2018, background): “Hand motion captures are mostly lead by single depth sensor based methods [36, 46, 49, 30, 57, 45, 53, 43, 39, 42, 50, 58], with few exceptions based on multi-view systems [4, 43, 38].”
Depth-Based Hand Pose Estimation: Methods, Data, and Challenges (2015, neutral): “Example datasets include MSRA [25], A-Star [42], and Dexter [33].”
Real-Time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor (2017, background): “Random forests are a popular choice [12, 36, 34, 45, 43] due to their capacity but still result in kinematically inconsistent and jittery pose estimates.”
Spatial Attention Deep Net with Partial PSO for Hierarchical Hybrid Hand Pose Estimation (2016, methodology): “[17] refine the hand pose by ? indicates equal contribution ar X iv :1 60 4.”
InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image (2020, methodology): “nding and human-computer interaction. Recently, many methods [6,11, 15,38,46] utilize deep convolutional neural networks (CNNs) and have achieved noticeable performance improvement on public datasets [29,33,36,43,46]. Most of the previous 3D hand pose estimation methods [6, 11, 15, 38, 46] are desig”
Deep Kinematic Pose Regression (2016, background): “Some approaches represent the object pose in a non-parametric way (as a number of points) and directly learn the pose from data [28,27,5].”
A hand pose tracking benchmark from stereo matching (2017, background): “At present, existing hand tracking datasets [2–7] are captured with active depth sensors.”
Two-hand Global 3D Pose Estimation using Monocular RGB (2020, background): “For depth-based hand pose estimation, [28, 26, 25, 34, 7] presented large-scale datasets consisting of real depth images with estimated ground-truth joint locations.”
Learning Joint Reconstruction of Hands and Manipulated Objects (2019, neutral): “In contrast to other methods [4, 20, 37, 65, 80] that only predicts sparse skeleton keypoints, our model produces a dense hand mesh.”
Cross-Modal Deep Variational Hand Pose Estimation (2018, methodology): “For NYU, we train and test on viewpoint 1 and all 36 available joints, and evaluate on 14 joints as done in [15, 17, 34] while for MSRA, we perform a leave-one-out cross-validation and evaluate the errors for the 9 models trained as done in [15, 25, 34].”
Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals (2017, methodology): “Semi-automatic annotation methods, which combine manual annotation with tracking, help scaling the dataset size [43, 46, 52], but in the case of [46] the annotation errors are close to the lowest estimation errors.”