Article
Computer Science, Artificial Intelligence
Zaid Alyafeai, Maged S. Al-shaibani, Mustafa Ghaleb, Yousif Ahmed Al-Wajih
Summary: Calligraphy is a vital part of Arabic heritage and culture, with efforts being made to digitize this art form. While offline datasets with diverse Arabic styles for calligraphy exist, there is still a lack of available online datasets for Arabic calligraphy. Research in this area is ongoing, with proposed baseline models for character classification tasks and the recognition that further study is needed to address this open problem.
NEURAL COMPUTING & APPLICATIONS
(2022)
Letter
Engineering, Multidisciplinary
Mamta Bisht, Richa Gupta
Summary: In this study, two CNN-based models were proposed for offline handwritten modified character recognition. The double-CNN architecture outperformed the single CNN architecture and used fewer output classes. These models achieved good recognition accuracy on Hindi consonants and Matras dataset.
SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES
(2021)
Review
Computer Science, Information Systems
Trishita Ghosh, Shibaprasad Sen, Sk. Md. Obaidullah, K. C. Santosh, Kaushik Roy, Umapada Pal
Summary: The easy availability and rapid use of online devices have increased the demand for online handwriting recognition. This paper discusses various machine learning and deep learning approaches for recognizing online handwritten characters, words, and texts. The advantages and challenges of online handwriting recognition are also addressed.
COMPUTER SCIENCE REVIEW
(2022)
Article
Computer Science, Information Systems
Dmytro Zhelezniakov, Viktor Zaytsev, Olga Radyvonenko
Summary: The paper presents the latest methods for online recognition of handwritten mathematical expressions, including classification, evaluation, performance comparison, and more. It also discusses how to use these technologies to address the challenges posed by remote learning and remote work.
Article
Computer Science, Artificial Intelligence
Harjeet Singh, R. K. Sharma, V. P. Singh, Munish Kumar
Summary: This paper presents a method for recognizing Online handwritten basic characters of Gurmukhi, achieving high accuracy using a dataset written by 175 different individuals.
Article
Computer Science, Theory & Methods
Teruo M. Maruyama, Luiz S. Oliveira, Alceu S. Britto, Robert Sabourin
Summary: This study introduces a method to automatically model the most common writer variability traits in order to generate offline signatures and train ASVS. The results demonstrate that using specific techniques to generate duplicates significantly improves the performance of ASVS.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2021)
Article
Computer Science, Artificial Intelligence
Faisel Mushtaq, Muzafar Mehraj Misgar, Munish Kumar, Surinder Singh Khurana
Summary: The study proposed a handwritten Urdu character dataset and recognition system using a convolutional neural network architecture, achieving a recognition rate of 98.82% for 133 classes, outperforming all existing systems for the Urdu language.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Information Systems
B. R. Kavitha, C. Srimathi
Summary: This paper uses state-of-the-art CNN models to recognize handwritten Tamil characters in offline mode, achieving good recognition results on both training and testing datasets and setting a benchmark for deep learning techniques in offline HTCR field.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Xiang Ao, Xu-Yao Zhang, Cheng-Lin Liu
Summary: This study proposes a cross-modal prototype learning method (CMPL) for zero-shot recognition. By mapping printed characters into a deep neural network feature space, prototypes are generated and shared between online and offline data to achieve joint learning of different modalities. Experimental results demonstrate that CMPL outperforms existing methods in zero-shot handwritten Chinese character recognition and shows cross-domain generalization in terms of language and style.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Information Systems
Amar Jindal, Rajib Ghosh
Summary: This research proposes a novel hybrid deep learning based OCR method for recognizing characters in ancient handwritten document images written in Devanagari and Maithili scripts. The method extracts discriminating features from each character and classifies them using a hybrid deep learning model consisting of dense and recurrently connected hidden layers. The proposed method achieves a character recognition accuracy of 96.97% and 95.83% in Devanagari and Maithili scripts, respectively.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Sukhjinder Singh, Naresh Kumar Garg, Munish Kumar
Summary: The article discusses the importance and challenges of handwritten character recognition, with a focus on Devanagari script. It provides an overview of existing feature extraction and classification methods, as well as future research directions and the use of deep learning in this field.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Amar Jindal, Rajib Ghosh
Summary: This article proposes a novel method to segment any textline of ancient handwritten Devanagari and Maithili documents into different words and each word into different characters. The proposed method has achieved high accuracies for both word segmentation and character segmentation in the ancient documents, outperforming the state-of-the-art methods in this regard.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Wujiahemaiti Simayi, Mayire Ibrayim, Askar Hamdulla
Summary: This paper introduces a character type based approach for online handwritten Uyghur word recognition, which outperforms the character form based system in terms of speed and recognition results according to comparative experiments.
Article
Computer Science, Information Systems
Yunxin Li, Qian Yang, Qingcai Chen, Baotian Hu, Xiaolong Wang, Yuxin Ding, Lin Ma
Summary: This paper proposes two models, vanilla compositional network (VCN) and deep spatial & contextual information fusion network (DSCIFN). VCN combines convolutional neural network with a sequence modeling architecture to leverage previous contextual information for single online handwritten Chinese character recognition (SOLHCCR). However, VCN is fragile when dealing with poorly written characters. To improve robustness, DSCIFN integrates spatial features and previous contextual information in a multi-layer fusion module. Experimental results show that DSCIFN outperforms VCN and previous models in terms of accuracy and robustness.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Artificial Intelligence
Yuan Wu, Hongliang Bi, Jing Fan, Guofei Xu, Huinan Chen
Summary: Efficient typing on a mobile device is challenging due to the small touch screen. Recent contactless solutions using acoustic sensors are low cost but not practical enough. In order to overcome these challenges, the DMHC system fuses ultrasonic and general audio signals to extract latent interactions between them. Experimental results show that DMHC achieves high recognition accuracies for letters and words, making it an effective and robust solution for real-life handwriting recognition.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Engineering, Civil
Kelathodi Kumaran Santhosh, Debi Prosad Dogra, Partha Pratim Roy, Adway Mitra
Summary: The study proposes a method for trajectory classification and anomaly detection using a hybrid CNN-VAE architecture. By introducing high-level features and semi-supervised class labeling, the accuracy of trajectory classification and anomaly detection is significantly improved.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Electrical & Electronic
Prateek Keserwani, Rajkumar Saini, Marcus Liwicki, Partha Pratim Roy
Summary: This article analyzes the impact of training data with partial annotations on scene text detection and proposes a text region refinement approach to address it. The proposed method refines text regions by generating pseudo-labels, resulting in significant improvement over existing approaches for partially annotated training data.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Debashis Das Chakladar, Partha Pratim Roy, Masakazu Iwamura
Summary: The article introduces a method to study the cognitive state of operators using EEG signals and proposes a deep ensemble model for classifying the cognitive state. Additionally, an algorithm is proposed to identify the brain dynamics for each cognitive state and analyze the connectivity between different brain regions.
IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS
(2022)
Article
Automation & Control Systems
Shreetam Behera, Debi Prosad Dogra, Malay Kumar Bandyopadhyay, Partha Pratim Roy
Summary: Crowd behavior is a natural phenomenon and modeling the visual appearance of a large crowd can provide valuable insights into its dynamics. In this article, a graph classification framework is proposed for crowd characterization using a deep graph convolutional neural network. Experimental results show significant improvements in accuracy and area under the curve (AUC) compared to existing frameworks.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Computer Science, Artificial Intelligence
Debashis Das Chakladar, Sumalyo Datta, Partha Pratim Roy, Vinod A. Prasad
Summary: An effective VAE-CBAM-based deep model is proposed in this article for estimating cognitive states. The model extracts noise-free robust features from the latent space using VAE and improves the spatial resolution of EEG signals using CBAM. Experimental results show that the proposed model achieves good classification accuracy under different cognitive task conditions.
IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Yixiao Zheng, Jiyang Xie, Aneeshan Sain, Yi-Zhe Song, Zhanyu Ma
Summary: This paper proposes the Sketch-Segformer framework for sketch semantic segmentation, which effectively utilizes multi-facet information of sketches to achieve state-of-the-art performance. By treating sketches as stroke sequences and incorporating order embedding and spatial embeddings, Sketch-Segformer demonstrates superior segmentation accuracy.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Subhadeep Koley, Ayan Kumar Bhunia, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song
Summary: This paper presents a method to transform abstract, deformed sketches into photorealistic images without the need for an edgemap-like sketch. The researchers propose a decoupled encoder-decoder training paradigm and use an autoregressive sketch mapper to bridge the abstraction gap between sketch and photo. The generated results outperform state-of-the-art methods in fine-grained sketch-based image retrieval tasks.
2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR
(2023)
Article
Engineering, Biomedical
Gourav Siddhad, Anmol Gupta, Debi Prosad Dogra, Partha Pratim Roy
Summary: This paper explores the effectiveness of using transformer networks to classify EEG data. The performance was evaluated on both local and public datasets, and the results show that the transformer networks achieved comparable accuracy to state-of-the-art methods without the need for feature extraction.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2024)
Proceedings Paper
Computer Science, Artificial Intelligence
Yixiao Zheng, Jiyang Xie, Aneeshan Sain, Zhanyu Ma, Yi-Zhe Song, Jun Guo
Summary: In this study, an encoder-decoder GNN framework called ENDE-GNN is proposed to improve the performance of sketch semantic segmentation. ENDE-GNN extracts both inter-stroke and intra-stroke features and pays attention to the drawing order of sketches. Experimental results demonstrate that ENDE-GNN achieves state-of-the-art performance on multiple sketch semantic segmentation datasets.
2022 IEEE INTERNATIONAL CONFERENCE ON VISUAL COMMUNICATIONS AND IMAGE PROCESSING (VCIP)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Ayan Kumar Bhunia, Aneeshan Sain, Parth Hiren Shah, Animesh Gupta, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song
Summary: This paper focuses on the generalization of fine-grained sketch-based image retrieval (FG-SBIR) and proposes a model-agnostic meta-learning framework that adapts quickly with few samples. The proposed framework includes key modifications to improve the stability and effectiveness of the model, and experiments show significant improvements over existing approaches.
COMPUTER VISION, ECCV 2022, PT XXXVII
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Pinaki Nath Chowdhury, Aneeshan Sain, Ayan Kumar Bhunia, Tao Xiang, Yulia Gryaditskaya, Yi-Zhe Song
Summary: In this paper, we advance sketch research using the first dataset of freehand scene sketches, FS-COCO. We collect 10,000 freehand scene vector sketches from 100 non-expert individuals, accompanied by text descriptions. This dataset allows us to study fine-grained image retrieval from freehand scene sketches and sketch captions, and explore insights on scene salience, performance comparison, and complementarity of information.
COMPUTER VISION, ECCV 2022, PT VIII
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Aneeshan Sain, Ayan Kumar Bhunia, Vaishnav Potlapalli, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song
Summary: This paper extends the zero-shot sketch-based image retrieval method to adapt to both categories and sketch distributions. A test-time training paradigm is proposed, along with the use of a self-supervised auxiliary task for sketches without paired photos. Extensive experiments demonstrate that the proposed method not only transfers to new categories but also accommodates to new sketching styles.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Ayan Kumar Bhunia, Subhadeep Koley, Abdullah Faiz Ur Rahman Khilji, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song
Summary: This paper proposes an auxiliary module that allows users to sketch without worries in image retrieval. Through detecting noisy strokes and selecting the ones that contribute positively to retrieval, the module achieves significant performance improvement when combined with pre-trained retrieval models. Furthermore, the trained selector can be used in various sketch applications in a plug-and-play manner.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Ayan Kumar Bhunia, Viswanatha Reddy Gajjala, Subhadeep Koley, Rohit Kundu, Aneeshan Sain, Tao Xiang, Yi-Zhe Song
Summary: This paper introduces a novel FSCIL framework that utilizes sketches as a modality for class support, addressing the challenges of learning from diverse modalities and limited accessibility to photos.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Pinaki Nath Chowdhury, Ayan Kumar Bhunia, Viswanatha Reddy Gajjala, Aneeshan Sain, Tao Xiang, Yi-Zhe Song
Summary: This article presents a method to address the issue of partial scene sketches by using an optimal transport model to model cross-modal region associativity in a partially-aware manner, and further improving upon it to consider holistic partialness. The proposed method is robust to partial scene sketches and achieves state-of-the-art performance on existing datasets.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Article
Computer Science, Artificial Intelligence
C. Lopez-Molina, S. Iglesias-Rey, B. De Baets
Summary: Quantitative image comparison is a critical topic in image processing literature, with diverse applications. Existing measures of comparison often overlook the context in which the comparison takes place. This paper presents a context-aware comparison method for binary images, tested on the BSDS500 benchmark.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Lorenz Linhardt, Klaus-Robert Mueller, Gregoire Montavon
Summary: This paper investigates the issue of mismatches between the decision strategy of the explainable model and the user's domain knowledge, and proposes a new method EGEM to mitigate hidden flaws in the model. Experimental results demonstrate that the approach can significantly reduce reliance on Clever Hans strategies and improve the accuracy of the model on new data.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Zhimin Shao, Weibei Dou, Yu Pan
Summary: This paper proposes a novel algorithm, Dual-level Deep Evidential Fusion (DDEF), to integrate multimodal information at both the BBA level and multimodal level, aiming to enhance accuracy, robustness, and reliability. The DDEF approach utilizes the Dirichlet framework and BBA methods for effective uncertainty estimation and employs the Dempster-Shafer Theory for dual-level fusion. The experimental results show that the proposed DDEF outperforms existing methods in synthetic digit classification and real-world medical prognosis after BCI treatment.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Abhishek K. Ghosh, Danilo S. Catelli, Samuel Wilson, Niamh C. Nowlan, Ravi Vaidyanathan
Summary: The inability of current FM monitoring methods to be used outside clinical environments has made it challenging to understand the nature and evolution of FM. This investigation introduces a novel wearable FM monitor with a heterogeneous sensor suite and a data fusion architecture to efficiently capture and separate FM from interfering artifacts. The performance of the device and architecture were validated through at-home use, demonstrating high accuracy in detecting and recognizing FM events. This research is a major milestone in the development of low-cost wearable FM monitors for pervasive monitoring of FM in unsupervised environments.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Jianlei Kong, Xiaomeng Fan, Min Zuo, Muhammet Deveci, Xuebo Jin, Kaiyang Zhong
Summary: In this study, we propose an intelligent traffic flow prediction framework based on the adaptive dual-graphic transformer with a cross-fusion strategy, aiming to uncover latent graphic feature representations that transcend temporal and spatial limitations. By establishing a traffic spatiotemporal prediction model using a cross-fusion attention mechanism, our proposed model achieves superior prediction performance on practical urban traffic flow datasets, particularly for long-term predictions.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Huilai Zhi, Jinhai Li
Summary: This article addresses the issue that conflict analysis based on single-valued information systems is no longer valid. It proposes a conflict analysis method based on component similarity, which uses three-way n-valued concept lattices to handle set-valued formal contexts and realizes fast conflict analysis from an information fusion viewpoint. Experimental results verify the effectiveness of this method in reducing time consumption.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Huchang Liao, Jiaxin Qi, Jiawei Zhang, Chonghui Zhang, Fan Liu, Weiping Ding
Summary: In this paper, a hospital selection approach based on a fuzzy multi-criterion decision-making method is proposed. This approach considers sentiment evaluation values of unstructured data from online reviews and structured data of public indexes simultaneously. The methodology involves collecting and processing online reviews, classifying topics and sentiments, quantifying sentiment analysis results using fuzzy numbers, and obtaining final preference scores of hospitals based on patients' preferences. A case study and robustness analysis are conducted to validate the effectiveness of the method.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Faramarz Farhangian, Rafael M. O. Cruz, George D. C. Cavalcanti
Summary: The proliferation of social networks has posed challenges in combating fake news, but automatic fake news detection using artificial intelligence has become more feasible. This paper revisits the definitions and perspectives of fake news and proposes an updated taxonomy, based on multiple criteria, for the field. The study finds that optimal feature extraction techniques vary depending on the dataset, and context-dependent models based on transformer models consistently exhibit superior performance.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Mariana A. Souza, Robert Sabourin, George D. C. Cavalcanti, Rafael M. O. Cruz
Summary: In this study, a dynamic selection technique is proposed to handle sparse and overlapped data. The technique leverages the relationships between instances and classifiers to learn a dynamic classifier combination rule. Experimental results show that the proposed method outperforms static selection and other dynamic selection techniques.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Bin Yu, Ruihui Xu, Mingjie Cai, Weiping Ding
Summary: This paper introduces a clustering method based on non-Euclidean metric and multi-granularity staged clustering to address the challenges posed by complex spatial structure data to traditional clustering methods. The method improves the similarity measure and employs an attenuation-diffusion pattern for local to global clustering, achieving good clustering results.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Jian Zhu, Pengbo Hu, Bingqian Li, Yi Zhou
Summary: The acquisition of multi-view hash representation for heterogeneous data is highly important for multimedia retrieval. Current approaches suffer from limited retrieval precision due to insufficient integration of multi-view features and failure to effectively utilize metric information from diverse samples. In this paper, we propose an innovative method called Fast Metric Multi-View Hashing (FMMVH), which demonstrates the superiority of gate-based fusion over traditional methods. We also introduce a novel deep metric loss function to leverage metric information from dissimilar samples. By optimizing and employing model compression techniques, our FMMVH method significantly outperforms existing state-of-the-art methods on benchmark datasets, with up to 7.47% improvement in mean Average Precision (mAP).
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Fayaz Ali Dharejo, Iyyakutti Iyappan Ganapathi, Muhammad Zawish, Basit Alawode, Moath Alathbah, Naoufel Werghi, Sajid Javed
Summary: The resource-limited nature of underwater vision equipment affects underwater robotics and ocean engineering tasks. Super-resolution methods, particularly using Vision Transformers (ViTs), have emerged to enhance low-resolution underwater images. However, ViTs face challenges in handling severe degradation in underwater imaging. In contrast, Multi-scale ViTs (MViTs) overcome these challenges by preserving long-range dependencies through evolving channel capacity. This study proposes a novel algorithm, SwinWave-SR, for efficient and accurate multi-scale super-resolution for underwater images.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Weiwei Jiang, Haoyu Han, Yang Zhang, Jianbin Mu
Summary: This study incorporates federated learning and split learning paradigms with satellite-terrestrial integrated networks and introduces a split-then-federated learning framework and federated split learning with long short-term memory to handle sequential data in STINs. The proposed solution is demonstrated to be effective through a case study of electricity theft detection based on a real-world dataset.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Najah Abuali, Mohammad Bilal Khan, Farman Ullah, Mohammad Hayajneh, Hikmat Ullah, Shahid Mumtaz
Summary: The demand for innovative solutions in biomedical systems for precise diagnosis and management of critical diseases is increasing. A promising technology, non-invasive and intelligent Internet of Medical Things (IoMT) system, emerges to assess patients with reduced health risks. This research introduces a comprehensive framework for early diagnosis of respiratory abnormalities through RF sensing and SDR technology. The results highlight the superior performance of deep learning frameworks in classifying respiratory anomalies.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Shichen Huang, Weina Fu, Zhaoyue Zhang, Shuai Liu
Summary: In the era of adversarial machine learning (AML), developing robust and generalized algorithms has become a key research topic. This study proposes a global similarity matching module and a global-local cognition fusion training mechanism based on relationship adversarial sample generation to improve image-text matching algorithm. Experimental results show significant improvements in accuracy and robustness, performing well in facing security challenges and promoting the fusion of visual and linguistic modalities.
INFORMATION FUSION
(2024)