Information retrieval for music and motion

By Meinard Müller. 2007

2,010 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

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 Signal Processing

Citations in the corpus

Deep Learning on Lie Groups for Skeleton-Based Action Recognition (2016, methodology): “Note that, for the LieNet, we do not employ the dynamic time warping (DTW) technique [29], which has been used in the SO and SE methods to solve the problem of speed variations.”
Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning (2017, methodology): “We make use of Dynamic Time Warping (DTW) as described in M¨uller (2007), a well known method for learning correspondences across sequences which may vary in speed.”
Fast Global Alignment Kernels (2011, background): “Indeed, the DTW distance is not rigorously a distance and is known not to be negative definite since it does not satisfy the triangle inequality (Bahlmann et al., 2002; Müller, 2007, p.72), and as a result cannot be used to define a p.d. kernel.”
End-To-End Speech Synthesis Applied to Brazilian Portuguese (2020, methodology): “For the preliminary evaluation, we used the measures L1 loss [Goodfellow et al., 2016], Root Mean Square Error (RMSE) [Tamamori et al., 2017a] and the Dynamic Time Warping (DTW) distance [Müller, 2007].”
Gesture recognition for human-robot collaboration: A review (2017, background): “Dynamic time warping (DTW) is an optimal alignment algo-rithm for two sequences (Müller, 2007; Keogh and Pazzani, 2001).”
Action2Motion: Conditioned Generation of 3D Human Motions (2020, background): “[7] represents a human skeleton with 3D joint angles, whereas the temporal information is modeled using dynamic time warping [21].”
Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group (2014, methodology): “We use the squared Euclidean distance in the Lie algebra for DTW. Note that to compute a nominal curve all the curves should have equal number of samples.”
Unobtrusive User-Authentication on Mobile Phones Using Biometric Gait Recognition (2010, methodology): “This is done by using Dynamic Time Warping (DTW) [25] to calculate the distances between all cycles and deleting the ones which have an unusual large distance to the other cycles.”
Gyrophone: Recognizing Speech from Gyroscope Signals (2014, background): “Dynamic Time Warping (DTW) is a time-series matching and alignment technique [37].”