arXiv research

CNN-DTW system improves keyword spotting in under-resourced languages.

End-to-end neural network improves QbE-STD in multilingual speech search.

Paper introduces k-DTW for robust curve comparison.

Graph clustering method uses templates to match vertices and outperforms classical methods.

Method finds multiple noisy graph templates in large graphs.

Designs a Cellular Automata rule for forming touching loop patterns.

A new framework for averaging spatio-temporal signals using optimal transport and soft alignments.

Cellular Electron CryoTomography (CECT) is a 3D imaging technique that captures information about the structure and spatial organization of macromolecular complexes within single cells, in near-native state and at sub-molecular resolution. Although template matching is often used to locate macromolecules in a CECT imag…

The surfaces of many cultural heritage objects were embellished with various patterns, especially curve patterns. In practice, most of the unearthed cultural heritage objects are highly fragmented, e.g., sherds of potteries or vessels, and each of them only shows a very small portion of the underlying full design, with…

Hopfield networks improve reaction template prediction for few/zero-shot scenarios.

Improved binning technique boosts nUV measure performance.

We propose in this paper a differentiable learning loss between time series, building upon the celebrated dynamic time warping (DTW) discrepancy. Unlike the Euclidean distance, DTW can compare time series of variable size and is robust to shifts or dilatations across the time dimension. To compute DTW, one typically so…

New tighter lower bounds for DTW improve NN-DTW classification efficiency.

Diffeomorphic Time Warping (DiffTW) is a novel method for time series classification that learns a diffeomorphic mapping between time series.

This paper converts dtw-distance to a semi-metric for data mining.

A new warping-invariant distance improves nearest-neighbor classification efficiency.

A new method for tracking objects using diverse templates.

Two supervised methods classify single-molecule patterns from X-ray imaging.

G2Gs transforms target molecules into reactants without templates, improving accuracy.

New method discovers time series motifs under DTW, significantly reducing computations.

Efficiently identifies users from walking activity data using kernel-based DTW.

Valid inference method for DTW distance for abnormal time-series detection.

A new differentiable divergence for time series comparison.

A new method aligns spatial and temporal data, improving on Dynamic Time Warping.

Paper proposes DTW-SOM for visual exploration of time-series motifs.

A new kernel reduces time-series analysis complexity from quadratic to linear.

The concept of sample mean in dynamic time warping (DTW) spaces has been successfully applied to improve pattern recognition systems and generalize centroid-based clustering algorithms. Its existence has neither been proved nor challenged. This article presents sufficient conditions for existence of a sample mean in DT…

FastDTW is often slower than exact DTW in practical applications.

Study clusters bank customers using LSTM and DTW.

Dynamic Time Warping improves regression accuracy on spectroscopy data.

New algorithm tackles adversarial contextual bandits using stochastic smoothing.

Guided warping augments time series data by aligning features with a teacher.

We investigate metric learning in the context of dynamic time warping (DTW), the by far most popular dissimilarity measure used for the comparison and analysis of motion capture data. While metric learning enables a problem-adapted representation of data, the majority of methods has been proposed for vectorial data onl…

Templates are branched 2-manifolds with semi-flows used to model `chaotic' hyperbolic invariant sets of flows on 3-manifolds. Knotted orbits on a template correspond to those in the original flow. Birman and Williams conjectured that for any given template the number of prime factors of the knots realized would be boun…

New chatter detection method using DTW and kNN outperforms existing techniques.

METRO predicts reactions using minimal templates, reducing computational overhead and achieving state-of-the-art results.

Bayesian method learns optimal momentum for landmark matching.

Improved gesture recognition using compressed domain signals.

Unified framework for imitation learning via moment matching.

A new KD layer lets student models learn and apply teacher knowledge explicitly.

Paper proposes a new efficient transport-based dissimilarity measure for time series classification.

We consider the use of the Joint Clustering and Matching (JCM) procedure for the supervised classification of a flow cytometric sample with respect to a number of predefined classes of such samples. The JCM procedure has been proposed as a method for the unsupervised classification of cells within a sample into a numbe…

New method to classify simple Smale flows on $S^3$.

The nearest neighbor method together with the dynamic time warping (DTW) distance is one of the most popular approaches in time series classification. This method suffers from high storage and computation requirements for large training sets. As a solution to both drawbacks, this article extends learning vector quantiz…

Dasgupta and Shulman showed that a two-round variant of the EM algorithm can learn mixture of Gaussian distributions with near optimal precision with high probability if the Gaussian distributions are well separated and if the dimension is sufficiently high. In this paper, we generalize their theory to learning mixture…

We describe the Williams zeta functions and the twist zeta functions of sub-Lorenz templates generated by renormalizable Lorenz maps, in terms of the corresponding zeta-functions of the sub-Lorenz templates generated by the renormalized map and by the map that determines the renormalization type.

New algorithms minimize regret in SSP with optimal sparse updates.

Neural production systems learn visual dynamics by applying rule templates to entities.