Capturing natural hand articulation

By Ying Wu, John Y. Lin, Thomas S. Huang. Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001, 2001

294 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/febec389afdbcfd27f74d14e0ff245fba8ea785d

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

Survey on 3D Hand Gesture Recognition (2016, background): “They are also called model-based hand tracking approaches, which try to fit the explicit 3D DoF model to the observed hand data [103].”
Capturing Hands in Action Using Discriminative Salient Points and Physics Simulation (2015, background): “Kim et al (2012) and Wang and Popović (2009) use inverse-kinematics, while Heap and Hogg (1996) and Wu et al (2001) reduce the search space using linear subspaces.”
Fast pose estimation with parameter-sensitive hashing (2003, background): “Alternatively, it has been often observed or conjectured [12, 18] that images of many real-world phenomena do not fill the space uniformly, but rather belong to an intrinsically lowdimensional manifold, and densely covering that manifold is enough to ensure this property.”
Embodied hands (2017, methodology): “…[Kim et al. 2012; Wang and Popović 2009], probabilistic line matching [Athitsos and Sclaroff 2003], reduced linear search sub-spaces [Heap and Hogg 1996; Wu et al. 2001], Bayesian filtering with Chamfer matching [Thayananthan et al. 2003], and physics-based methods [Melax et al. 2013].”
Learning Joint Reconstruction of Hands and Manipulated Objects (2019, unknown): “Early work focused on hand estimation and tracking using articulated models [15, 44, 58, 71] or statistical shape models [26].”
Vision-based hand pose estimation: A review (2007, methodology): “Wu 01 [58] 20(Unclear) 1 Edges, silhouette L MH Particle filter”
Interactive Markerless Articulated Hand Motion Tracking Using RGB and Depth Data (2013, methodology): “The first study of size of the motion space of hand articulations when using kinematic skeletons was done by Lin et al. [11] [28] .”
Model-based 3D tracking of an articulated hand (2001, methodology): “In [ 26 ] a model-based method for capturing articulated hand motion is presented.”
3D Hand Shape and Pose From Images in the Wild (2019, background): “When it comes to a monocular color input, the problem becomes inherently ill posed due to the increased depth and scale ambiguities, but that did not prevent several researchers [4, 9, 51, 57, 63, 39] from attempting to solve it in the past albeit with limited results.”
Disentangling Latent Hands for Image Synthesis and Pose Estimation (2018, background): “Early methods could recognize only a restricted set of poses [1, 36] or used simplified hand representations instead of full 3D skeletons [26, 37].”
Vision-based human activity recognition: a survey (2020, methodology): “(b) Optimal estimation : These methods evaluate the state of moving systems from series of measures [9, 218].”
Accurate, Robust, and Flexible Real-time Hand Tracking (2015, unknown): “[24, 35]), again resulting in limited accuracy.”
Cascaded hand pose regression (2015, background): “Early work on hand Most early works [17, 38, 4, 2, 13, 24] use RGB images or videos.”
Model-based hand tracking using a hierarchical Bayesian filter (2006, methodology): “Articulated motion is naturally constrained, since each jo int can only move within certain limits and the motion of different joints is correlated [45] .”
3D hand tracking by rapid stochastic gradient descent using a skinning model (2004, background): “[2] decrease the state space dimensionality.”
Hands Deep in Deep Learning for Hand Pose Estimation (2015, methodology): “Similar to [28], we rely on a linear embedding.”
Realtime and Robust Hand Tracking from Depth (2014, background): “Hand tracking is important in many human computer interaction applications and has been intensely studied for decades [10, 28, 4, 2, 7, 14].”