dynamic time warping
PulseAugur coverage of dynamic time warping — every cluster mentioning dynamic time warping across labs, papers, and developer communities, ranked by signal.
-
AI framework identifies autism biomarkers through dance imitation analysis
Researchers have developed a computational framework to analyze motor signatures in autism, utilizing dance imitation data. By employing Dynamic Time Warping and introducing the Social Context Sensitivity Index (SCSI), …
-
New DTW-GBC method improves noisy-label time-series classification
Researchers have developed a new method called DTW-based Granular Ball Computing (DTW-GBC) for classifying time-series data, particularly when the training data contains noisy labels. This approach organizes similar tra…
-
New Diffeomorphic Time Warping method challenges traditional DTW
Researchers have introduced Diffeomorphic Time Warping (DiffTW), a novel theoretical framework for time series classification that moves beyond traditional dynamic time warping (DTW) by learning mappings between real-va…
-
New research uses path signatures for advanced online goal recognition
A new research paper proposes an innovative approach to online goal recognition in continuous domains. The method utilizes path signatures, a technique from rough path theory, to create compact and expressive representa…
-
New framework uses EEG and AR to assess ocular response times for mTBI
Researchers have developed a novel framework that integrates electroencephalogram (EEG) data with augmented reality (AR)-based Vestibular/Ocular Motor Screening (VOMS) tasks to assess ocular response times. This system …
-
New framework improves trajectory similarity learning with lower-bound representations
Researchers have developed a new framework called LB-TrajRep for learning trajectory similarity. This method uses lower-bound representations, which are independent of deep neural embeddings, to provide admissible and i…
-
New AI models enhance handwriting trajectory reconstruction from sensor data · 3 sources tracked
Researchers have developed new methods for reconstructing handwriting trajectories using digital pens equipped with IMU sensors. One approach utilizes a Mixture-of-Experts (MOE) model, with separate experts for pen-touc…
-
AI model achieves stable 10-day PM2.5 forecasts using DTW-CNN-GRU
A research paper proposes a novel deep learning framework for long-term PM2.5 concentration forecasting, specifically designed for cities with limited monitoring networks like Isfahan, Iran. The model integrates Dynamic…
-
Self-supervised speech comparison method for L2 pronunciation scoring
Researchers have developed a novel self-supervised speech comparison method using WavLM representations and dynamic time warping (DTW) to assess L2 pronunciation. This text-free framework aims to score phonetic accuracy…
-
New neural network method extracts rail tracks from 3D point clouds
Researchers have developed a new method for extracting rail tracks from 3D point clouds using a fully convolutional recurrent neural network. This approach, trained on synthetic data, preserves full spatial resolution a…
-
Quantum Dynamic Time Warping enhances multivariate time series classification
Researchers have developed a hybrid Quantum Dynamic Time Warping (qDTW) architecture to improve multivariate time series classification. This new approach replaces traditional Euclidean distances with the geometry of a …
-
New Diffeomorphic Time Warping method outperforms DTW on 60 datasets
Researchers have introduced Diffeomorphic Time Warping (DiffTW), a novel theoretical framework for time series classification that moves beyond traditional dynamic time warping (DTW). DiffTW learns mappings between real…
-
New Transformer Model Automates Mechanical Mechanism Design
Researchers have developed a Discrete Autoregressive Transformer (DAT) to address the complex problem of planar path synthesis for mechanical mechanisms. This novel approach models the synthesis process as a conditional…
-
New Benchmark Evaluates VLMs on Extracting Data from Epidemic Curves
Researchers have introduced EpiCurveBench, a new benchmark designed to evaluate vision-language models (VLMs) on the task of extracting data from epidemic curve charts. This benchmark includes 1,000 real-world epidemic …
-
New probabilistic framework enhances data alignment with uncertainty modeling
Researchers have developed a new probabilistic framework called uncertainty-DTW (uDTW) for aligning structured data, enhancing traditional methods like Dynamic Time Warping. This approach models pairwise correspondences…
-
Deep neural framework estimates ocular response times for mTBI assessment
Researchers have developed a novel framework integrating electroencephalogram (EEG) with augmented reality (AR) Vestibular/Ocular Motor Screening (VOMS) tasks to estimate ocular response times. The system utilizes a Red…
-
New method uses path signatures for efficient online goal recognition
Researchers have developed a new method for online goal recognition that utilizes path signatures from rough path theory. This approach efficiently encodes and compares large trajectory datasets, outperforming existing …
-
New defense offers certified robustness for time-series anomaly detection
Researchers have developed the first defense mechanism that provides certified robustness for time-series anomaly detection under the Dynamic Time Warping (DTW) metric. This new approach adapts the randomized smoothing …
-
Researchers improve medical VQA with trajectory-aware process supervision
Researchers have developed a novel method to improve medical visual question answering (VQA) systems by incorporating trajectory-aware process supervision. This approach utilizes a two-stage training framework, starting…
-
TokenTiming: A Dynamic Alignment Method for Universal Speculative Decoding Model Pairs
Researchers have developed a new method called TokenTiming, inspired by Dynamic Time Warping, to improve the efficiency of speculative decoding in large language models. This technique allows for the use of draft and ta…