Article
Computer Science, Artificial Intelligence
Manabu Okawa
Summary: This study proposes a novel single-template strategy to improve the speed and accuracy of online signature verification by using mean templates and local stability-weighted dynamic time warping. The experiment results confirm the effectiveness of the method in both random and skilled-forgery scenarios through research on DTW barycenter averaging and local stability.
PATTERN RECOGNITION
(2021)
Article
Chemistry, Analytical
Jing Li, Haowen Zhang, Yabo Dong, Tongbin Zuo, Duanqing Xu
Summary: This paper focuses on the application of self-training methods in the positive unlabeled time series classification problem, and proposes a new approach called ST-average, which utilizes an average sequence for data labeling that is more representative and reliable compared to traditional methods.
Article
Computer Science, Information Systems
Haowen Zhang, Yabo Dong, Jing Li, Duanqing Xu
Summary: The article proposes a method called product quantization (PQ)-based DTW (PQDTW) for fast time-series approximate similarity search under DTW. By utilizing dynamic time warping (DTW) and DTW barycenter averaging (DBA) techniques, along with the filter-and-refine framework, the method efficiently and accurately performs time-series similarity search. Comparisons with related popular algorithms using public time-series data sets show that the proposal achieves the best tradeoff between query efficiency and retrieval accuracy.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Automation & Control Systems
Yutao Liu, Yong-An Zhang, Ming Zeng, Jie Zhao
Summary: In this research, a novel shape-based time series averaging algorithm called Shape DTW Weighted Averaging (ShapeDWA) is proposed to address the limitations of DTW Barycenter Averaging (DBA). ShapeDWA combines the advantages of DBA and Cubic-spline DTW (CDTW) methods, allowing for averaging in both the amplitude and time domains. ShapeDWA uses a weighted average to attenuate the effects of noise, outliers, and local amplitude differences, resulting in superior performance compared to DBA and SSG in terms of average discrepancy distance and average time distortion.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Information Systems
Irati Rasines, Anthony Remazeilles, Miguel Prada, Itziar Cabanes
Summary: This paper proposes an innovative algorithm called MCA-CDTW for averaging multivariate time series with different lengths based on Constrained Dynamic Time Warping (CDTW). The algorithm utilizes CDTW for non-linear alignment and employs Minimum Cost Averaging (MCA) technique for obtaining equal-length time series. Compared to other averaging techniques, MCA-CDTW provides smooth mean curves even with large deviations and reduces algorithm complexity. Experimental results on different databases demonstrate the effectiveness of the proposed algorithm in achieving smooth average trajectories.
Article
Computer Science, Artificial Intelligence
Abdelmadjid Lahreche, Bachir Boucheham
Summary: The problem of similarity measures within the field of time series classification has led to the development of a new parameter-free measure called LE-DTW, which is designed to quickly and accurately assess similarity between long time series. Experimental results show that LE-DTW performs better than DTW for long time series, while also providing competitive results against popular distance based classifiers. In terms of efficiency, LE-DTW is significantly faster than DTW.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Automation & Control Systems
Hongyue Guo, Lidong Wang, Xiaodong Liu, Witold Pedrycz
Summary: This article introduces a two-stage time-series clustering approach, which involves dimensionality reduction based on information granules and fuzzy clustering using dynamic time warping and fuzzy C-means algorithm. Experiments on UCR time-series database and Chinese stocks datasets validate the effectiveness and advantages of the proposed fuzzy clustering approach.
IEEE TRANSACTIONS ON CYBERNETICS
(2021)
Article
Geochemistry & Geophysics
Yiming Liu, Huadong Guo, Lu Zhang, Dong Liang, Qi Zhu, Xuting Liu, Zhuoran Lv, Xinyu Dou, Yiting Gou
Summary: Rich datasets related to the Earth have been obtained due to the rapid development of Earth observation technologies. This research proposes a correlation analysis method of time series data based on the dynamic time warping (DTW) algorithm, and applies it to the correlation analysis between the time series features of the surface temperature and melting area of the Antarctic ice sheet. The results show that the proposed method can effectively distinguish the change details of nonlinear time series and outperforms traditional correlation coefficients like Pearson's correlation coefficient.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2023)
Article
Ecology
Jens C. Hegg, Brian P. Kennedy
Summary: Ecological patterns are often based on chronological time series, and DTW, a method capable of efficiently comparing series despite temporal offsets, is seldom used in ecology. DTW can detect subtle behavioral patterns within data sets that traditional techniques cannot.
Proceedings Paper
Computer Science, Artificial Intelligence
Manabu Okawa
Summary: This study proposes a novel online signature verification method using locally and globally weighted dynamic time warping (LG-DTW) to improve verification performance. The method utilizes Euclidean barycenter-based DTW barycenter averaging in the enrollment phase to obtain a mean template set and employs local and global weighting estimates to handle intra-user and inter-user variability. Experimental results confirm the effectiveness of the proposed method.
2021 IEEE 3RD GLOBAL CONFERENCE ON LIFE SCIENCES AND TECHNOLOGIES (IEEE LIFETECH 2021)
(2021)
Article
Computer Science, Information Systems
Eiji Mizutani, Stuart Dreyfus
Summary: Dynamic programming is a mathematical optimization algorithm used in time warping procedures. While simple use is correct and efficient, sophisticated applications require considerable skill. This article discusses published sophisticated time warping procedures that are incorrect or inefficient, aiming to educate readers on the artful use of dynamic programming.
INFORMATION SCIENCES
(2021)
Article
Environmental Sciences
Fa Zhao, Guijun Yang, Hao Yang, Yaohui Zhu, Yang Meng, Shaoyu Han, Xinlei Bu
Summary: The study introduces a novel method combining DTW and LSTM models for winter wheat NDVI prediction, which improves prediction accuracy by reducing errors caused by overfitting. The combined method performs well in a case study in Hebei Province, demonstrating promising results for short and medium-term NDVI prediction.
Article
Computer Science, Artificial Intelligence
Shilei Hao, Zhihai Wang, Jidong Yuan
Summary: The key problem in time series classification is the measurement of similarity between time series. In recent years, researchers have paid extensive attention to efficient and accurate methods for measuring the similarity of time series. Existing methods for time series classification can be broadly categorized into shape-based (original value) methods and structure-based (symbol transformation) methods, depending on the similarity measurement strategies they employ. Shape-based methods typically use Euclidean distance (ED), dynamic time warping (DTW), or other methods to measure the overall similarity between sequences. These methods often fail to capture local sensible matchings of time series, resulting in decreased accuracy and interpretability. To address this issue, structure-based methods discretize or symbolize the local values of time sequences, leading to a loss of original information. This paper proposes a novel similarity measurement method called dynamic time warping based on the local morphological pattern (MPDTW), which decomposes local subsequences using discrete wavelet transforms to extract local structure information, encodes the decomposed subsequence using morphological pattern, and applies the weighted ED between points and their local structure difference based on morphological pattern to the DTW algorithm for similarity measurement. Experimental results on the UCR datasets demonstrate that our method outperforms existing baselines.
INTELLIGENT DATA ANALYSIS
(2023)
Article
Environmental Sciences
Zheng Zhang, Ping Tang, Changmiao Hu, Zhiqiang Liu, Weixiong Zhang, Liang Tang
Summary: This paper proposes a seeded SITS classification method based on lower-bounded Dynamic Time Warping, which only requires a few labeled samples and uses a combination of cascading lower bounds and early abandoning of DTW as an accurate yet efficient similarity measure. Experimental results demonstrate the utility of this method for SITS classification in large-scale tasks.
Article
Engineering, Electrical & Electronic
Zhengyu Chen, Jie Gu
Summary: This research introduces a mixed-signal DTW accelerator utilizing mixed-signal time-domain computing to improve the throughput of time-series classification. A specially designed time flip-flop circuit enables pipelined operation, leading to significant improvements in performance and scalability.
IEEE JOURNAL OF SOLID-STATE CIRCUITS
(2021)
Article
Computer Science, Information Systems
Sheng Fang, Catherine Achard, Severine Dubuisson
MULTIMEDIA TOOLS AND APPLICATIONS
(2018)
Article
Computer Science, Artificial Intelligence
Geoffrey Vaquette, Catherine Achard, Laurent Lucat
JOURNAL OF REAL-TIME IMAGE PROCESSING
(2019)
Article
Psychiatry
C. Leclere, M. Avril, S. Viaux-Savelon, N. Bodeau, C. Achard, S. Missonnier, M. Keren, R. Feldman, M. Chetouani, D. Cohen
TRANSLATIONAL PSYCHIATRY
(2016)
Article
Computer Science, Artificial Intelligence
Marion Morel, Catherine Achard, Richard Kulpa, Severine Dubuisson
IMAGE AND VISION COMPUTING
(2017)
Article
Computer Science, Artificial Intelligence
Abdallah Benzine, Bertrand Luvison, Quoc Cuong Pham, Catherine Achard
Summary: This paper proposes a new single-shot method for multi-person 3D human pose estimation in complex images. The method is able to handle variable numbers of people without needing bounding boxes for estimating 3D poses. By leveraging and extending the Stacked Hourglass Network and associative embedding method, the approach achieves significant improvements over the state of the art on challenging datasets.
PATTERN RECOGNITION
(2021)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Liu Yang, Catherine Achard, Catherine Pelachaud
Summary: The paper proposes a new annotation schema to classify different types of interruptions based on timeliness, accomplishment, and speech content level, integrating existing interruption and turn switch classification methods. The French section of the NoXi corpus is annotated using this schema, and the annotations are used to study the probability distribution and duration of each turn switch type.
LREC 2022: THIRTEEN INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION
(2022)
Proceedings Paper
Automation & Control Systems
Megane Millan, Catherine Achard
Summary: This study aims to address the issue of quality assessment by providing automatic feedback based on neural network explanation, focusing on explaining network decisions for quality score prediction. By using gradient-based approaches and adjusting them for better robustness, the method aims to provide a more accurate assessment.
2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Liu Yang, Catherine Achard, Catherine Pelachaud
Summary: Turn management is a necessary social interaction skill, with interruptions being inherent in conversation and potentially enriching interactions. To achieve natural human-agent interaction, Embodied Conversational Agents (ECAs) must be able to communicate autonomously through both verbal and nonverbal means. One challenge is handling interruptions during interactions, which requires analyzing human-human interaction data.
PROCEEDINGS OF THE 21ST ACM INTERNATIONAL CONFERENCE ON INTELLIGENT VIRTUAL AGENTS (IVA)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Guillaume Vaudaux-Ruth, Adrien Chan-Hon-Tong, Catherine Achard
Summary: Research shows that learning self-assessment scores in action detection can improve overall performance, with experimental results demonstrating that the approach outperforms the state-of-the-art on two action detection benchmarks.
2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Abdallah Benzine, Florian Chabot, Bertrand Luvison, Quoc Cuong Pham, Catherine Achard
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Proceedings Paper
Computer Science, Software Engineering
Megane Millan, Catherine Achard
PROCEEDINGS OF THE 15TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VOL 5: VISAPP
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Shuai Liang, Mokrane Boudaoud, Catherine Achard, Weibin Rong, Stephane Regnier
2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)
(2019)
Proceedings Paper
Imaging Science & Photographic Technology
Abdallah Benzine, Bertrand Luvison, Quoc Cuong Pham, Catherine Achard
2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Gilles Bailly, Emmanouil Giannisakis, Marion Morel, Catherine Achard
ACTES DE LA 30 CONFERENCE FRANCOPHONE SUR L'INTERACTION HOMME-MACHINE - (IHM 2018)
(2018)
Article
Computer Science, Artificial Intelligence
Guang-Hai Liu, Zuo-Yong Li, Jing-Yu Yang, David Zhang
Summary: This article introduces a novel image retrieval method that improves retrieval performance by using sublimated deep features. The method incorporates orientation-selective features and color perceptual features, effectively mimicking these mechanisms to provide a more discriminating representation.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Fengguang Peng, Zihan Ding, Ziming Chen, Gang Wang, Tianrui Hui, Si Liu, Hang Shi
Summary: RGB-Thermal (RGB-T) semantic segmentation is an emerging task that aims to improve the robustness of segmentation methods under extreme imaging conditions by using thermal infrared modality. The challenges of foreground-background distinguishment and complementary information mining are addressed by proposing a cross modulation process with two collaborative components. Experimental results show that the proposed method achieves state-of-the-art performances on current RGB-T segmentation benchmarks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Baihong Han, Xiaoyan Jiang, Zhijun Fang, Hamido Fujita, Yongbin Gao
Summary: This paper proposes a novel automatic prompt generation method called F-SCP, which focuses on generating accurate prompts for low-accuracy classes and similar classes. Experimental results show that our approach outperforms state-of-the-art methods on six multi-domain datasets.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Huikai Liu, Ao Zhang, Wenqian Zhu, Bin Fu, Bingjian Ding, Shengwu Xiong
Summary: Adverse weather conditions present challenges for computer vision tasks, and image de-weathering is an important component of image restoration. This paper proposes a multi-patch skip-forward structure and a Residual Deformable Convolutional module to improve feature extraction and pixel-wise reconstruction.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Oliver M. Crook, Mihai Cucuringu, Tim Hurst, Carola-Bibiane Schonlieb, Matthew Thorpe, Konstantinos C. Zygalakis
Summary: The transportation LP distance (TLP) is a generalization of the Wasserstein WP distance that can be applied directly to color or multi-channelled images, as well as multivariate time-series. TLP interprets signals as functions, while WP interprets signals as measures. Although both distances are powerful tools in modeling data with spatial or temporal perturbations, their computational cost can be prohibitively high for moderate pattern recognition tasks. The linear Wasserstein distance offers a method for projecting signals into a Euclidean space, and in this study, we propose linear versions of the TLP distance (LTLP) that show significant improvement over the linear WP distance in signal processing tasks while being several orders of magnitude faster to compute than the TLP distance.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Haitao Tian, Shiru Qu, Pierre Payeur
Summary: This paper proposes a method of target-dependent classifier, which optimizes the joint hypothesis of domain adaptation into a target-dependent hypothesis that better fits with the target domain clusters through an unsupervised fine-tuning strategy and the concept of meta-learning. Experimental results demonstrate that this method outperforms existing techniques in synthetic-to-real adaptation and cross-city adaptation benchmarks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Qingsen Yan, Axi Niu, Chaoqun Wang, Wei Dong, Marcin Wozniak, Yanning Zhang
Summary: Deep learning-based methods have achieved remarkable results in the field of super-resolution. However, the limitation of paired training image sets has led researchers to explore self-supervised learning. However, the assumption of inaccurate downscaling kernel functions often leads to degraded results. To address this issue, this paper introduces KGSR, a kernel-guided network that trains both upscaling and downscaling networks to generate high-quality high-resolution images even without knowing the actual downscaling process.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Yifan Chen, Xuelong Li
Summary: Gait recognition is a popular technology for identification due to its ability to capture gait features over long distances without cooperation. However, current methods face challenges as they use a single network to extract both temporal and spatial features. To solve this problem, we propose a two-branch network that focuses on spatial and temporal feature extraction separately. By combining these features, we can effectively learn the spatio-temporal information of gait sequences.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Wei Shi, Wentao Zhang, Wei-shi Zheng, Ruixuan Wang
Summary: This article proposes a simple yet effective visualization framework called PAMI, which does not require detailed model structure and parameters to obtain visualization results. It can be applied to various prediction tasks with different model backbones and input formats.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Xiaobo Hu, Jianbo Su, Jun Zhang
Summary: This paper reviews the latest technologies in pattern recognition, highlighting their instabilities and failures in practical applications. From a control perspective, the significance of disturbance rejection in pattern recognition is discussed, and the existing problems are summarized. Finally, potential solutions related to the application of compensation on features are discussed to emphasize future research directions.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Andres Felipe Posada-Moreno, Nikita Surya, Sebastian Trimpe
Summary: Convolutional neural networks are widely used in critical systems, and explainable artificial intelligence has proposed methods for generating high-level explanations. However, these methods lack the ability to determine the location of concepts. To address this, we propose a novel method for automatic concept extraction and localization based on pixel-wise aggregations, and validate it using synthetic datasets.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Peng Bao, Jianian Li, Rong Yan, Zhongyi Liu
Summary: In this paper, a novel Dynamic Graph Contrastive Learning framework, DyGCL, is proposed to capture the temporal consistency in dynamic graphs and achieve good performance in node representation learning.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Kristian Schultz, Saptarshi Bej, Waldemar Hahn, Markus Wolfien, Prashant Srivastava, Olaf Wolkenhauer
Summary: Research indicates that deep generative models perform poorly compared to linear interpolation-based methods for synthetic data generation on small, imbalanced tabular datasets. To address this, a new approach called ConvGeN, combining convex space learning with deep generative models, has been proposed. ConvGeN improves imbalanced classification on small datasets while remaining competitive with existing linear interpolation methods.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Khondaker Tasrif Noor, Antonio Robles-Kelly
Summary: In this paper, the authors propose H-CapsNet, a capsule network designed for hierarchical image classification. The network effectively captures hierarchical relationships using dedicated capsules for each class hierarchy. A modified hinge loss is utilized to enforce consistency among the involved hierarchies. Additionally, a strategy for dynamically adjusting training parameters is presented to achieve better balance between the class hierarchies. Experimental results demonstrate that H-CapsNet outperforms competing hierarchical classification networks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Lei Liu, Guorun Li, Yuefeng Du, Xiaoyu Li, Xiuheng Wu, Zhi Qiao, Tianyi Wang
Summary: This study proposes a new agricultural image segmentation model called CS-Net, which uses Simple-Attention Block and Simpleformer to improve accuracy and inference speed, and addresses the issue of performance collapse of Transformers in agricultural image processing.
PATTERN RECOGNITION
(2024)
