Tracking loose-limbed people

By Leonid Sigal, Sidharth Bhatia, Stefan Roth, Michael J. Black, Michael Isard. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004., 2004

463 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/dc39b61661bc57c8239cd2678a09248c8d98e88f

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

HumanEva: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion (2006, methodology): “As a convention from previous methods [3, 15, 37, 36] that have already used this error metric we compute the 3D error in millimeters ( mm ) and 2D error directly in the image in pixels ( pix ).”
Vision-based human motion analysis: An overview (2007, background): “In [95,32], temporal constraints are also taken into account, resulting in a tracking framework.”
Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part Detectors (2007, unknown): “Parttrackinghasbeenusedtotrackthe pose of humans (Sigal et al., 2004; Ramanan et al., 2005; Lee and Nevatia, 2006).”
Measure Locally, Reason Globally: Occlusion-sensitive Articulated Pose Estimation (2006, methodology): “The messages are approximated using a kernel density formed by propagating particles through a conditional density [19].”
Clustered Pose and Nonlinear Appearance Models for Human Pose Estimation (2010, background): “Allowing the parts to drift apart in a controlled ‘loose-limbed’ manner [21] improves robustness.”
Detailed Human Shape and Pose from Images (2007, methodology): “There exist a number of techniques that can be used to initialize the stochastic search; for example, pose prediction from silhouettes [19], voxel carving skeletonization [5], or loose-limbed body models [18].”
HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion (2010, methodology): “A variety of statistical (Agarwal and Triggs 2004a, 2004b; Balan et al. 2005; Deutscher and Reid 2005; Hua et al. 2005; Sigal et al. 2004; Sigal and Black 2006; Sminchisescu et al. 2005) as well as deterministic methods (Mori et al. 2004; Taylor 2000; Shakhnarovich et al. 2003) have been developed…”
Robust Fragments-based Tracking using the Integral Histogram (2006, unknown): “We present extensive experimental results on challenging sequences, which demonstrate the robust tracking achieved by our algorithm (even with the use of only gray-scale (noncolor) information).”
Panoptic Studio: A Massively Multiview System for Social Motion Capture (2015, background): “One direction of approaches pursue high-quality motion capture in well-controlled studio setups [37, 17, 14, 38, 24].”
Real time motion capture using a single time-of-flight camera (2010, methodology): “In the multiview vision setting, Sigal et al. [15] apply a similar strategy, but use nonparametric belief propagation for their inference method.”
Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments (2014, background): “matic discriminative prediction [10], [11], [12], [13], [14], whereas others aim at model-image alignment [15], [16], [17], [18], [19], [20], [21], [22], [23] or accurate modeling of 3D shape[24], [25] or clothing[26].”
Progressive search space reduction for human pose estimation (2008, background): “This dense representation avoids the sampling needed by particle representations (e.g. [23, 24]).”
Efficient Human Pose Estimation from Single Depth Images (2013, background): “Traditional human body tracking algorithms [8], [9], [1], [10], [6], [11] infer a complete skeleton by exploiting kinematic constraints and can achieve high frame-rates by using temporal coherence from frame-to-frame.”
Real-time human pose recognition in parts from single depth images (2011, methodology): “[39] use eigen-appearance template detectors for head, upper arms and lower legs proposals.”
Particle Belief Propagation (2009, methodology): “Our experiments are not designed to showcase an application requiring particle BP, since there are already many such applications described in the literature (e.g., Coughlan and Ferreira, 2002; Sigal et al., 2004; Sudderth et al., 2004; Ihler et al., 2005a).”
Guiding model search using segmentation (2005, background): “Note that the ideas of shouters [14] or proposal maps [5] could be used in conjunction with the superpixel representation for improved performance.”
Beyond trees: common-factor models for 2D human pose recovery (2005, methodology): “For testing we used 50 frames from the Brown sequence in [13], for which there is ground truth from motion capture.”
Neural Body Fitting: Unifying Deep Learning and Model Based Human Pose and Shape Estimation (2018, methodology): “Early models were based on geometric primitives [34, 11, 39, 50, 54], while more recent ones are estimated from 1000s of scans of real people, and are typically parameterized by separate body pose and shape components [5, 13, 28, 71, 41], with few exceptions, e.”
Hierarchical Gaussian process latent variable models (2007, background): “Do not distribute. for object recognition (Felzenszwalb & Huttenlocher, 2000; Io.e & Forsyth, 2001) and human pose estimation (Ramanan & Forsyth, 2003; Sigal et al., 2004; Lan & Huttenlocher, 2005).”