We address the task of zero-shot fine-grained video classification, where no video examples or temporal annotations are available for unseen action classes. While contrastive vision-language models such as SigLIP demonstrate strong open-set recognition via mean-pooled image-text similarity, they fail to capture the temporal structure critical for distinguishing fine-grained activities. We introduce ActAlign, a zero-shot framework that formulates video classification as sequence alignment. For each class, a large language model generates an ordered sub-action sequence, which is aligned with video frames using Dynamic Time Warping (DTW) in a shared embedding space. Without any video-text supervision or fine-tuning, ActAlign achieves 30.5% accuracy on the extremely challenging ActionAtlas benchmark, where human accuracy is only 61.6%. ActAlign outperforms billion-parameter video-language models while using approximately 8x less parameters. These results demonstrate that structured language priors, combined with classical alignment techniques, offer a scalable and general approach to unlocking the open-set recognition potential of vision-language models for fine-grained video understanding.
We propose a novel two-stage framework to detect lead-lag relationships in the Chinese A-share market. First, long-term coupling between stocks is measured via daily data using correlation, dynamic time warping, and rank-based metrics. Then, high-frequency data (1-, 5-, and 15-minute) is used to detect statistically significant lead-lag patterns via cross-correlation, Granger causality, and regression models. Our low-coupling modular system supports scalable data processing and improves reproducibility. Results show that strongly coupled stock pairs often exhibit lead-lag effects, especially at finer time scales. These findings provide insights into market microstructure and quantitative trading opportunities.
Query-by-example spoken term detection (QbE-STD) searches for matching words or phrases in an audio dataset using a sample spoken query. When annotated data is limited or unavailable, QbE-STD is often done using template matching methods like dynamic time warping (DTW), which are computationally expensive and do not scale well. To address this, we propose H-QuEST (Hierarchical Query-by-Example Spoken Term Detection), a novel framework that accelerates spoken term retrieval by utilizing Term Frequency and Inverse Document Frequency (TF-IDF)-based sparse representations obtained through advanced audio representation learning techniques and Hierarchical Navigable Small World (HNSW) indexing with further refinement. Experimental results show that H-QuEST delivers substantial improvements in retrieval speed without sacrificing accuracy compared to existing methods.
Pretrained speech representations like wav2vec2 and HuBERT exhibit strong anisotropy, leading to high similarity between random embeddings. While widely observed, the impact of this property on downstream tasks remains unclear. This work evaluates anisotropy in keyword spotting for computational documentary linguistics. Using Dynamic Time Warping, we show that despite anisotropy, wav2vec2 similarity measures effectively identify words without transcription. Our results highlight the robustness of these representations, which capture phonetic structures and generalize across speakers. Our results underscore the importance of pretraining in learning rich and invariant speech representations.
A fundamental challenge in car-following modeling lies in accurately representing the multi-scale complexity of driving behaviors, particularly the intra-driver heterogeneity where a single driver's actions fluctuate dynamically under varying conditions. While existing models, both conventional and data-driven, address behavioral heterogeneity to some extent, they often emphasize inter-driver heterogeneity or rely on simplified assumptions, limiting their ability to capture the dynamic heterogeneity of a single driver under different driving conditions. To address this gap, we propose a novel data-driven car-following framework that systematically embeds discrete driving regimes (e.g., steady-state following, acceleration, cruising) into vehicular motion predictions. Leveraging high-resolution traffic trajectory datasets, the proposed hybrid deep learning architecture combines Gated Recurrent Units for discrete driving regime classification with Long Short-Term Memory networks for continuous kinematic prediction, unifying discrete decision-making processes and continuous vehicular dynamics to comprehensively represent inter- and intra-driver heterogeneity. Driving regimes are identified using a bottom-up segmentation algorithm and Dynamic Time Warping, ensuring robust characterization of behavioral states across diverse traffic scenarios. Comparative analyses demonstrate that the framework significantly reduces prediction errors for acceleration (maximum MSE improvement reached 58.47\%), speed, and spacing metrics while reproducing critical traffic phenomena, such as stop-and-go wave propagation and oscillatory dynamics.
Fast and scalable alignment of time series is a fundamental challenge in many domains. The standard solution, Dynamic Time Warping (DTW), struggles with poor scalability and sensitivity to noise. We introduce TimePoint, a self-supervised method that dramatically accelerates DTW-based alignment while typically improving alignment accuracy by learning keypoints and descriptors from synthetic data. Inspired by 2D keypoint detection but carefully adapted to the unique challenges of 1D signals, TimePoint leverages efficient 1D diffeomorphisms, which effectively model nonlinear time warping, to generate realistic training data. This approach, along with fully convolutional and wavelet convolutional architectures, enables the extraction of informative keypoints and descriptors. Applying DTW to these sparse representations yield major speedups and typically higher alignment accuracy than standard DTW applied to the full signals. TimePoint demonstrates strong generalization to real-world time series when trained solely on synthetic data, and further improves with fine-tuning on real data. Extensive experiments demonstrate that TimePoint consistently achieves faster and more accurate alignments than standard DTW, making it a scalable solution for time-series analysis. Our code is available at https://github.com/BGU-CS-VIL/TimePoint
This paper introduces $k$-Dynamic Time Warping ($k$-DTW), a novel dissimilarity measure for polygonal curves. $k$-DTW has stronger metric properties than Dynamic Time Warping (DTW) and is more robust to outliers than the Fr\'{e}chet distance, which are the two gold standards of dissimilarity measures for polygonal curves. We show interesting properties of $k$-DTW and give an exact algorithm as well as a $(1+\varepsilon)$-approximation algorithm for $k$-DTW by a parametric search for the $k$-th largest matched distance. We prove the first dimension-free learning bounds for curves and further learning theoretic results. $k$-DTW not only admits smaller sample size than DTW for the problem of learning the median of curves, where some factors depending on the curves' complexity $m$ are replaced by $k$, but we also show a surprising separation on the associated Rademacher and Gaussian complexities: $k$-DTW admits strictly smaller bounds than DTW, by a factor $\tilde\Omega(\sqrt{m})$ when $k\ll m$. We complement our theoretical findings with an experimental illustration of the benefits of using $k$-DTW for clustering and nearest neighbor classification.
Understanding how humans express and synchronize emotions across multiple communication channels particularly facial expressions and speech has significant implications for emotion recognition systems and human computer interaction. Motivated by the notion that non-overlapping speech promotes clearer emotional coordination, while overlapping speech disrupts synchrony, this study examines how these conversational dynamics shape the spatial and temporal alignment of arousal and valence across facial and vocal modalities. Using dyadic interactions from the IEMOCAP dataset, we extracted continuous emotion estimates via EmoNet (facial video) and a Wav2Vec2-based model (speech audio). Segments were categorized based on speech overlap, and emotional alignment was assessed using Pearson correlation, lag adjusted analysis, and Dynamic Time Warping (DTW). Across analyses, non overlapping speech was associated with more stable and predictable emotional synchrony than overlapping speech. While zero-lag correlations were low and not statistically different, non overlapping speech showed reduced variability, especially for arousal. Lag adjusted correlations and best-lag distributions revealed clearer, more consistent temporal alignment in these segments. In contrast, overlapping speech exhibited higher variability and flatter lag profiles, though DTW indicated unexpectedly tighter alignment suggesting distinct coordination strategies. Notably, directionality patterns showed that facial expressions more often preceded speech during turn-taking, while speech led during simultaneous vocalizations. These findings underscore the importance of conversational structure in regulating emotional communication and provide new insight into the spatial and temporal dynamics of multimodal affective alignment in real world interaction.
In today's digitally-driven world, the demand for personalized and context-aware recommendations has never been greater. Traditional recommender systems have made significant strides in this direction, but they often lack the ability to tap into the richness of conversational data. This paper represents a novel approach to recommendation systems by integrating conversational insights into the recommendation process. The Conversational Recommender System integrates cutting-edge technologies such as deep learning, leveraging machine learning algorithms like Apriori for Association Rule Mining, Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Long Short-Term Memory (LTSM). Furthermore, sophisticated voice recognition technologies, including Hidden Markov Models (HMMs) and Dynamic Time Warping (DTW) algorithms, play a crucial role in accurate speech-to-text conversion, ensuring robust performance in diverse environments. The methodology incorporates a fusion of content-based and collaborative recommendation approaches, enhancing them with NLP techniques. This innovative integration ensures a more personalized and context-aware recommendation experience, particularly in marketing applications.
Time Series Classification (TSC) is an important problem with numerous applications in science and technology. Dissimilarity-based approaches, such as Dynamic Time Warping (DTW), are classical methods for distinguishing time series when time deformations are confounding information. In this paper, starting from a deformation-based model for signal classes we define a problem statement for time series classification problem. We show that, under theoretically ideal conditions, a continuous version of classic 1NN-DTW method can solve the stated problem, even when only one training sample is available. In addition, we propose an alternative dissimilarity measure based on Optimal Transport and show that it can also solve the aforementioned problem statement at a significantly reduced computational cost. Finally, we demonstrate the application of the newly proposed approach in simulated and real time series classification data, showing the efficacy of the method.
In recent years, non-intrusive load monitoring (NILM) technology has attracted much attention in the related research field by virtue of its unique advantage of utilizing single meter data to achieve accurate decomposition of device-level energy consumption. Cutting-edge methods based on machine learning and deep learning have achieved remarkable results in load decomposition accuracy by fusing time-frequency domain features. However, these methods generally suffer from high computational costs and huge memory requirements, which become the main obstacles for their deployment on resource-constrained microcontroller units (MCUs). To address these challenges, this study proposes an innovative Dynamic Time Warping (DTW) algorithm in the time-frequency domain and systematically compares and analyzes the performance of six machine learning techniques in home electricity scenarios. Through complete experimental validation on edge MCUs, this scheme successfully achieves a recognition accuracy of 95%. Meanwhile, this study deeply optimizes the frequency domain feature extraction process, which effectively reduces the running time by 55.55% and the storage overhead by about 34.6%. The algorithm performance will be further optimized in future research work. Considering that the elimination of voltage transformer design can significantly reduce the cost, the subsequent research will focus on this direction, and is committed to providing more cost-effective solutions for the practical application of NILM, and providing a solid theoretical foundation and feasible technical paths for the design of efficient NILM systems in edge computing environments.
Fault classification in industrial machinery is vital for enhancing reliability and reducing downtime, yet it remains challenging due to the variability of vibration patterns across diverse operating conditions. This study introduces a novel graph-based framework for fault classification, converting time-series vibration data from machinery operating at varying horsepower levels into a graph representation. We utilize Shannon's entropy to determine the optimal window size for data segmentation, ensuring each segment captures significant temporal patterns, and employ Dynamic Time Warping (DTW) to define graph edges based on segment similarity. A Graph Auto Encoder (GAE) with a deep graph transformer encoder, decoder, and ensemble classifier is developed to learn latent graph representations and classify faults across various categories. The GAE's performance is evaluated on the Case Western Reserve University (CWRU) dataset, with cross-dataset generalization assessed on the HUST dataset. Results show that GAE achieves a mean F1-score of 0.99 on the CWRU dataset, significantly outperforming baseline models-CNN, LSTM, RNN, GRU, and Bi-LSTM (F1-scores: 0.94-0.97, p < 0.05, Wilcoxon signed-rank test for Bi-LSTM: p < 0.05) -- particularly in challenging classes (e.g., Class 8: 0.99 vs. 0.71 for Bi-LSTM). Visualization of dataset characteristics reveals that datasets with amplified vibration patterns and diverse fault dynamics enhance generalization. This framework provides a robust solution for fault diagnosis under varying conditions, offering insights into dataset impacts on model performance.
Robots with wheeled, quadrupedal, or humanoid forms are increasingly integrated into built environments. However, unlike human social learning, they lack a critical pathway for intrinsic cognitive development, namely, learning from human feedback during interaction. To understand human ubiquitous observation, supervision, and shared control in dynamic and uncertain environments, this study presents a brain-computer interface (BCI) framework that enables classification of Electroencephalogram (EEG) signals to detect cognitively demanding and safety-critical events. As a timely and motivating co-robotic engineering application, we simulate a human-in-the-loop scenario to flag risky events in semi-autonomous robotic driving-representative of long-tail cases that pose persistent bottlenecks to the safety performance of smart mobility systems and robotic vehicles. Drawing on recent advances in few-shot learning, we propose a dual-attention Siamese convolutional network paired with Dynamic Time Warping Barycenter Averaging approach to generate robust EEG-encoded signal representations. Inverse source localization reveals activation in Broadman areas 4 and 9, indicating perception-action coupling during task-relevant mental imagery. The model achieves 80% classification accuracy under data-scarce conditions and exhibits a nearly 100% increase in the utility of salient features compared to state-of-the-art methods, as measured through integrated gradient attribution. Beyond performance, this study contributes to our understanding of the cognitive architecture required for BCI agents-particularly the role of attention and memory mechanisms-in categorizing diverse mental states and supporting both inter- and intra-subject adaptation. Overall, this research advances the development of cognitive robotics and socially guided learning for service robots in complex built environments.
Remote photoplethysmography (rPPG) offers a novel approach to noninvasive monitoring of vital signs, such as respiratory rate, utilizing a camera. Although several supervised and self-supervised methods have been proposed, they often fail to accurately reconstruct the PPG signal, particularly in distinguishing between systolic and diastolic components. Their primary focus tends to be solely on extracting heart rate, which may not accurately represent the complete PPG signal. To address this limitation, this paper proposes a novel deep learning architecture using Generative Adversarial Networks by introducing multi-discriminators to extract rPPG signals from facial videos. These discriminators focus on the time domain, the frequency domain, and the second derivative of the original time domain signal. The discriminator integrates four loss functions: variance loss to mitigate local minima caused by noise; dynamic time warping loss to address local minima induced by alignment and sequences of variable lengths; Sparsity Loss for heart rate adjustment, and Variance Loss to ensure a uniform distribution across the desired frequency domain and time interval between systolic and diastolic phases of the PPG signal.
Alzheimer's disease (AD) affects 50 million people worldwide and is projected to overwhelm 152 million by 2050. AD is characterized by cognitive decline due partly to disruptions in metabolic brain connectivity. Thus, early and accurate detection of metabolic brain network impairments is crucial for AD management. Chief to identifying such impairments is FDG-PET data. Despite advancements, most graph-based studies using FDG-PET data rely on group-level analysis or thresholding. Yet, group-level analysis can veil individual differences and thresholding may overlook weaker but biologically critical brain connections. Additionally, machine learning-based AD prediction largely focuses on univariate outcomes, such as disease status. Here, we introduce explainable graph-theoretical machine learning (XGML), a framework employing kernel density estimation and dynamic time warping to construct individual metabolic brain graphs that capture the distance between pair-wise brain regions and identify subgraphs most predictive of multivariate AD-related outcomes. Using FDG-PET data from the Alzheimer's Disease Neuroimaging Initiative, XGML builds metabolic brain graphs and uncovers subgraphs predictive of eight AD-related cognitive scores in new subjects. XGML shows robust performance, particularly for predicting scores measuring learning, memory, language, praxis, and orientation, such as CDRSB ($r = 0.74$), ADAS11 ($r = 0.73$), and ADAS13 ($r = 0.71$). Moreover, XGML unveils key edges jointly but differentially predictive of several AD-related outcomes; they may serve as potential network biomarkers for assessing overall cognitive decline. Together, we show the promise of graph-theoretical machine learning in biomarker discovery and disease prediction and its potential to improve our understanding of network neural mechanisms underlying AD.
Clustering high-dimensional data is a critical challenge in machine learning due to the curse of dimensionality and the presence of noise. Traditional clustering algorithms often fail to capture the intrinsic structures in such data. This paper explores a combination of clustering methods, which we called Line Space Clustering (LSC), a representation that transforms data points into lines in a newly defined feature space, enabling clustering based on the similarity of feature value patterns, essentially treating features as sequences. LSC employs a combined distance metric that uses Euclidean and Dynamic Time Warping (DTW) distances, weighted by a parameter {\alpha}, allowing flexibility in emphasizing shape or magnitude similarities. We delve deeply into the mechanics of DTW and the Savitzky Golay filter, explaining their roles in the algorithm. Extensive experiments demonstrate the efficacy of LSC on synthetic and real-world datasets, showing that randomly experimenting with time-series optimized methods sometimes might surprisingly work on a complex dataset, particularly in noisy environments. Source code and experiments are available at: https://github.com/JoanikijChulev/LSC.
This study proposes a novel metric to quantitatively evaluate body synergistic coordination, explicitly addressing dynamic interactions between pairs of body segments in baseball pitching motions. Conventional methods typically compare motion trajectories using individual joint coordinates or velocities independently, employing techniques like Dynamic Time Warping (DTW) that inherently apply temporal alignment even when such correction may distort meaningful rhythm-based differences. In contrast, our approach models the coordination dynamics as Linear Time-Invariant (LTI) systems, leveraging convolution operations between pairs of time series data to capture the gain and phase-lag inherent in genuine coordination dynamics. Empirical validation demonstrates the robustness of the proposed metric to variations in camera angles and scaling, providing superior discriminative capability compared to DTW and deep learning-based methods.
This study examines insurance companies' financial performance and reporting trends within the medical sector using advanced clustering techniques to identify distinct patterns. Four clusters were identified by analyzing financial ratios and time series data, each representing unique financial performance and reporting consistency combinations. Dynamic Time Warping (DTW) and KMeans clustering were employed to capture temporal variations and uncover key insights into company behaviors. The findings reveal that resilient performers consistently report and have financial stability, making them reliable options for policyholders. In contrast, clusters of underperforming companies and those with reporting gaps highlight operational challenges and issues related to data consistency. These insights emphasize the importance of transparency and timely reporting to ensure the sector's resilience. This study contributes to the literature by integrating time series analysis into financial clustering, offering practical recommendations for improving data governance and financial stability in the insurance sector. Future research could further investigate non-financial indicators and explore alternative clustering methods to provide a deeper understanding of performance dynamics.
Effective resource management and environmental planning in regions with high climatic variability, such as Chile, demand advanced predictive tools. This study addresses this challenge by employing an innovative and computationally efficient hybrid methodology that integrates machine learning (ML) methods for time series forecasting with established statistical techniques. The spatiotemporal data undergo decomposition using time-dependent Empirical Orthogonal Functions (EOFs), denoted as \(\phi_{k}(t)\), and their corresponding spatial coefficients, \(\alpha_{k}(s)\), to reduce dimensionality. Wavelet analysis provides high-resolution time and frequency information from the \(\phi_{k}(t)\) functions, while neural networks forecast these functions within a medium-range horizon \(h\). By utilizing various ML models, particularly a Wavelet - ANN hybrid model, we forecast \(\phi_{k}(t+h)\) up to a time horizon \(h\), and subsequently reconstruct the spatiotemporal data using these extended EOFs. This methodology is applied to a grid of climate data covering the territory of Chile. It transitions from a high-dimensional multivariate spatiotemporal data forecasting problem to a low-dimensional univariate forecasting problem. Additionally, cluster analysis with Dynamic Time Warping for defining similarities between rainfall time series, along with spatial coherence and predictability assessments, has been instrumental in identifying geographic areas where model performance is enhanced. This approach also elucidates the reasons behind poor forecast performance in regions or clusters with low spatial coherence and predictability. By utilizing cluster medoids, the forecasting process becomes more practical and efficient. This compound approach significantly reduces computational complexity while generating forecasts of reasonable accuracy and utility.
Time Series Alignment is a critical task in signal processing with numerous real-world applications. In practice, signals often exhibit temporal shifts and scaling, making classification on raw data prone to errors. This paper introduces a novel approach for Multiple Time Series Alignment (MTSA) leveraging Deep Learning techniques. While most existing methods primarily address Multiple Sequence Alignment (MSA) for protein and DNA sequences, there remains a significant gap in alignment methodologies for numerical time series. Additionally, conventional approaches typically focus on pairwise alignment, whereas our proposed method aligns all signals in a multiple manner (all the signals are aligned together at once). This innovation not only enhances alignment efficiency but also significantly improves computational speed. By decomposing into piece-wise linear sections, we introduce varying levels of complexity into the warping function. Additionally, our method ensures the satisfaction of three warping constraints: boundary, monotonicity, and continuity conditions. The utilization of a deep convolutional network allows us to employ a new loss function, addressing some limitations of Dynamic Time Warping (DTW). Experimental results on the UCR Archive 2018, comprising 129 time series datasets, demonstrate that employing our approach to align signals significantly enhances classification accuracy and warping average and also reduces the run time across the majority of these datasets.