Motion texture: a two-level statistical model for character motion synthesis

By Yan Li, Tianshu Wang, Harry Shum. ACM Transactions on Graphics, 2002

515 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/0a1e825f62d08f3137ab16a3c0966bc1e34fce7e

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

Citations in the corpus

Modeling Human Motion Using Binary Latent Variables (2006, methodology): “Another method is to transform motion in the training data to new sequences by l earning to adjusting its style or other characteristics[4, 5, 6].”
Learning physics-based motion style with nonlinear inverse optimization (2005, background): “Because of the difficulties in directly modeling physics and style, learning simple models of style from examples has recently been an extremely active and productive area of research [Arikan and Forsyth 2002; Arikan et al. 2003; Brand and Hertzmann 2000; Grochow et al. 2004; Kovar et al. 2002; Kova”
Segmenting Motion Capture Data into Distinct Behaviors (2004, background): “Li, Wang, and Shum [19] explore a more sophisticated technique where low-level segments ( textons) are represented as the output of linear dynamic systems.”
Style translation for human motion (2005, methodology): “, [Brand and Hertzmann 2000; Giese and Poggio 2000; Kovar et al. 2002a; Li et al. 2002]), the LTI model describes the translation without an explicit content model.”
Beyond pixels: exploring new representations and applications for motion analysis (2009, background): “1 Related Work Motion magnification analyzes and redisplays a motion signal, and thus relates to research on manipulating and redisplaying motion capture data, such as modifications to create new actions from others [5, 58, 84, 60], and methods to alter style [17, 42, 119].”
Temporal segmentation and activity classification from first-person sensing (2009, background): “Research that addresses the problem of detection, recognition and synthesis of human human motion have gained substantial interests from both academia and industry over the last few years due to the large number of applications[1], [20], [13], [15], [22].”
Spacetime faces: high resolution capture for modeling and animation (2004, background): “Other researchers have explored data-driven animation techniques in the domains of human (cid:2)gure motion [Li et al. 2002; Arikan and Forsyth 2002; Kovar et al. 2002; Lee et al. 2002] and video sprites [Sch¤odl and Essa 2002].”
Two Distributed-State Models For Generating High-Dimensional Time Series (2011, methodology): “Furthermore, the resulting motions often grossly violate dynamics, resulting in artifacts such as “footskate” and thereby requiring extensive clean-up using inverse kinematics.”
Analysis and synthesis of textured motion: particles and waves (2004, background): “The dynamicmodel also includes probabilistic representations for the birth/death (source/sink) of the motons.”
Performance animation from low-dimensional control signals (2005, methodology): “Three distinct approaches have been used: constructing models of human motion [Li et al. 2002; Brand and Hertzmann 2000], reordering motion clips employing a motion graph [Arikan and Forsyth 2002; Kovar et al. 2002; Lee et al. 2002; Pullen and Bregler 2002; Arikan et al. 2003] and interpolating…”
Video-based face recognition using probabilistic appearance manifolds (2003, background): “Recently, Li et al. [ 17 ] applied piecewise linear models to capture local motion and a transition matrix among these models to describe nonlinear global dynamics.”
Style-based inverse kinematics (2004, methodology): “2002; Pullen and Bregler 2002] or by learning a likelihood function over sequences [Brand and Hertzmann 2000; Li et al. 2002].”
Construction and optimal search of interpolated motion graphs (2007, methodology): “A number of algorithms have been developed to search a motion graph in an off-line fashion [Arikan and Forsyth 2002; Kovar et al. 2002; Pullen and Bregler 2002; Arikan et al. 2003; Choi et al. 2003; Sung et al. 2005; Li et al. 2002; Srinivasan et al. 2005].”