Interactive control of avatars animated with human motion data

By Jehee Lee, Jinxiang Chai, Paul S. A. Reitsma, Jessica K. Hodgins, Nancy S. Pollard. International Conference on Computer Graphics and Interactive Techniques, 2002

1,111 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/212a6148b6d8a48e3e4d935df98f65e51bd534de

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

Gaussian Process Dynamical Models (2005, background): “Bayesian people tracking requires dynamical models in the form of transition densities in order to specify prediction distributions over new poses at each time instant (e.g., [11] [14]); similarly, data-driven computer animation requires prior distributions over poses and motion (e.g., [1] [4] [6]).”
Dynamic Kernel Distillation for Efficient Pose Estimation in Videos (2019, background): “It is important for many applications including surveillance [8], computer animation [18], and AR/VR [19].”
Modeling by example (2004, positive): “This approach has been demonstrated recently for a number of data types, including motion capture data (e.g., [Lee et al. 2002]).”
Synthesis and evaluation of linear motion transitions (2008, methodology): “Several researchers [Witkin and Popovi´c 1995; Gleicher et al. 2003; Lee et al. 2002] use displacement mapping techniques to blend motions.”
Action-Reaction: Forecasting the Dynamics of Human Interaction (2014, background): “The goal of interactive control is to create avatar animations in response to user input [12,15].”
Footstep Planning for the Honda ASIMO Humanoid (2005, methodology): “Large datasets of captured human motion are now available, and techniques have been developed to synthesize animations based on artist specified goals and automatically computed motion transitions [22].”
Segmenting Motion Capture Data into Distinct Behaviors (2004, background): “, [17]), but to our knowledge it has not been explored for the purpose of”
Mode-adaptive neural networks for quadruped motion control (2018, background): “Data structures such as motion graphs [Arikan and Forsyth 2002; Kovar et al. 2002; Lee et al. 2002] are introduced to synthesize continuous character movements from unstructured motion capture data.”
Hierarchical Aligned Cluster Analysis for Temporal Clustering of Human Motion (2013, background): “There are many possible distances between body configurations that can provide a good similarity to match human motion (see [59], [60] for an extensive discussion).”
Robust motion in-betweening (2020, background): “Motion graphs [Arikan and Forsyth 2002; Beaudoin et al. 2008; Kovar et al. 2008; Lee et al. 2002] allow one to produce motions by traversing nodes and edges that map to character states or motions segments from a dataset.”
On Human Motion Prediction Using Recurrent Neural Networks (2017, background): “Arikan and Forsyth [2] collapse full sequences into nodes in a directed graph, connected with possible transitions between them, and in [24] cluster trees improve the path availability.”
Style translation for human motion (2005, methodology): “Database approaches assemble short subsequences to synthesize motions that match user specifications, such as a desired path on the ground or a list of actions to perform [Kovar et al. 2002a; Lee et al. 2002; Arikan et al. 2003; Arikan and Forsyth 2002].”
Two Distributed-State Models For Generating High-Dimensional Time Series (2011, methodology): “Perhaps the simplest way to generate new motion sequences based on data isto sensibly concatenate short examples from a motion database to meet sparse user-specified constraints (Tanco and Hilton, 2000; Arikan and Forsyth, 2002; Kovar et al., 2002; Lee et al., 2002;Arikan et al., 2003).”