Subjects -> COMPUTER SCIENCE (Total: 2313 journals)
    - ANIMATION AND SIMULATION (33 journals)
    - ARTIFICIAL INTELLIGENCE (133 journals)
    - AUTOMATION AND ROBOTICS (116 journals)
    - CLOUD COMPUTING AND NETWORKS (75 journals)
    - COMPUTER ARCHITECTURE (11 journals)
    - COMPUTER ENGINEERING (12 journals)
    - COMPUTER GAMES (23 journals)
    - COMPUTER PROGRAMMING (25 journals)
    - COMPUTER SCIENCE (1305 journals)
    - COMPUTER SECURITY (59 journals)
    - DATA BASE MANAGEMENT (21 journals)
    - DATA MINING (50 journals)
    - E-BUSINESS (21 journals)
    - E-LEARNING (30 journals)
    - ELECTRONIC DATA PROCESSING (23 journals)
    - IMAGE AND VIDEO PROCESSING (42 journals)
    - INFORMATION SYSTEMS (109 journals)
    - INTERNET (111 journals)
    - SOCIAL WEB (61 journals)
    - SOFTWARE (43 journals)
    - THEORY OF COMPUTING (10 journals)

COMPUTER SCIENCE (1305 journals)            First | 1 2 3 4 5 6 7 | Last

Showing 601 - 800 of 872 Journals sorted alphabetically
International Journal of Digital Enterprise Technology     Hybrid Journal   (Followers: 1)
International Journal of Digital Literacy and Digital Competence     Full-text available via subscription   (Followers: 6)
International Journal of Digital Signals and Smart Systems     Hybrid Journal   (Followers: 4)
International Journal of Education and Development using Information and Communication Technology     Open Access   (Followers: 9)
International Journal of Electrical and Computer Engineering     Open Access   (Followers: 8)
International Journal of Electronic Banking     Hybrid Journal   (Followers: 3)
International Journal of Electronic Business     Hybrid Journal   (Followers: 2)
International Journal of Electronic Commerce     Full-text available via subscription   (Followers: 10)
International Journal of Electronic Government Research     Full-text available via subscription   (Followers: 3)
International Journal of Embedded and Real-Time Communication Systems     Full-text available via subscription   (Followers: 9)
International Journal of Engineering and Manufacturing     Open Access   (Followers: 3)
International Journal of Engineering Science     Hybrid Journal   (Followers: 5)
International Journal of Entertainment Technology and Management     Hybrid Journal   (Followers: 1)
International Journal of Experimental Design and Process Optimisation     Hybrid Journal   (Followers: 5)
International Journal of Foundations of Computer Science     Hybrid Journal   (Followers: 3)
International Journal of Fuzzy Computation and Modelling     Hybrid Journal   (Followers: 2)
International Journal of Fuzzy System Applications     Full-text available via subscription   (Followers: 3)
International Journal of General Systems     Hybrid Journal   (Followers: 1)
International Journal of Granular Computing, Rough Sets and Intelligent Systems     Hybrid Journal   (Followers: 1)
International Journal of Green Computing     Full-text available via subscription  
International Journal of Grid and High Performance Computing     Full-text available via subscription   (Followers: 2)
International Journal of Grid and Utility Computing     Hybrid Journal  
International Journal of Handheld Computing Research     Full-text available via subscription  
International Journal of Heritage in the Digital Era     Full-text available via subscription   (Followers: 7)
International Journal of High Performance Computing and Networking     Hybrid Journal   (Followers: 4)
International Journal of High Performance Computing Applications     Hybrid Journal   (Followers: 4)
International Journal of High Performance Systems Architecture     Hybrid Journal   (Followers: 6)
International Journal of Human Capital and Information Technology Professionals     Full-text available via subscription   (Followers: 3)
International Journal of Human-Computer Interaction     Hybrid Journal   (Followers: 22)
International Journal of Human-Computer Studies     Hybrid Journal   (Followers: 20)
International Journal of Humanitarian Technology     Hybrid Journal   (Followers: 1)
International Journal of Humanities and Arts Computing     Hybrid Journal   (Followers: 11)
International Journal of Hybrid Intelligence     Hybrid Journal   (Followers: 1)
International Journal of ICT Research and Development in Africa     Full-text available via subscription   (Followers: 4)
International Journal of Imaging Systems and Technology     Hybrid Journal   (Followers: 1)
International Journal of Impact Engineering     Hybrid Journal   (Followers: 9)
International Journal of Industrial and Systems Engineering     Hybrid Journal   (Followers: 7)
International Journal of Industrial Electronics and Drives     Hybrid Journal   (Followers: 3)
International Journal of Information and Coding Theory     Hybrid Journal   (Followers: 6)
International Journal of Information and Communication Technology Education     Full-text available via subscription   (Followers: 13)
International Journal of Information Communication Technologies and Human Development     Full-text available via subscription   (Followers: 4)
International Journal of Information Quality     Hybrid Journal   (Followers: 3)
International Journal of Information Retrieval Research     Full-text available via subscription   (Followers: 28)
International Journal of Information Science and Management     Open Access   (Followers: 5)
International Journal of Information Science and Technology     Open Access  
International Journal of Information Systems and Management     Hybrid Journal   (Followers: 2)
International Journal of Information Systems and Project Management     Free   (Followers: 12)
International Journal of Information Systems and Software Engineering for Big Companies     Open Access   (Followers: 2)
International Journal of Information Technology and Computer Science     Open Access   (Followers: 3)
International Journal of Information Technology and Web Engineering     Hybrid Journal   (Followers: 2)
International Journal of Information Technology Project Management     Full-text available via subscription   (Followers: 9)
International Journal of Information Technology, Communications and Convergence     Hybrid Journal   (Followers: 14)
International Journal of Innovation in the Digital Economy     Full-text available via subscription   (Followers: 5)
International Journal of Innovative Computing and Applications     Hybrid Journal   (Followers: 3)
International Journal of Innovative Technology and Research     Open Access   (Followers: 1)
International Journal of Intelligence and Sustainable Computing     Hybrid Journal  
International Journal of Intelligence Science     Open Access   (Followers: 3)
International Journal of Intelligent Engineering Informatics     Hybrid Journal  
International Journal of Intelligent Enterprise     Hybrid Journal   (Followers: 1)
International Journal of Intelligent Information and Database Systems     Hybrid Journal   (Followers: 3)
International Journal of Intelligent Internet of Things Computing     Hybrid Journal   (Followers: 2)
International Journal of Intelligent Networks     Open Access  
International Journal of Intelligent Systems Technologies and Applications     Hybrid Journal   (Followers: 2)
International Journal of Intercultural Relations     Hybrid Journal   (Followers: 16)
International Journal of IT Standards and Standardization Research     Full-text available via subscription  
International Journal of IT/Business Alignment and Governance     Full-text available via subscription  
International Journal of Knowledge and Systems Science     Full-text available via subscription   (Followers: 1)
International Journal of Knowledge Engineering and Soft Data Paradigms     Hybrid Journal   (Followers: 1)
International Journal of Knowledge Society Research     Full-text available via subscription  
International Journal of Leadership in Education: Theory and Practice     Hybrid Journal   (Followers: 23)
International Journal of Logistics Research and Applications : A Leading Journal of Supply Chain Management     Hybrid Journal   (Followers: 16)
International Journal of Management & Information Technology     Open Access   (Followers: 2)
International Journal of Management Innovation Systems     Open Access  
International Journal of Mathematical Modelling & Computations     Open Access   (Followers: 3)
International Journal of Mathematical Sciences and Computing     Open Access  
International Journal of Mathematics & Computation     Full-text available via subscription  
International Journal of Mathematics in Operational Research     Hybrid Journal   (Followers: 2)
International Journal of Medical Engineering and Informatics     Hybrid Journal   (Followers: 4)
International Journal of Medical Informatics     Hybrid Journal   (Followers: 10)
International Journal of Metadata, Semantics and Ontologies     Hybrid Journal   (Followers: 9)
International Journal of Metaheuristics     Hybrid Journal   (Followers: 1)
International Journal of Mobile Communications     Hybrid Journal   (Followers: 8)
International Journal of Mobile Computing and Multimedia Communications     Full-text available via subscription   (Followers: 2)
International Journal of Mobile Network Design and Innovation     Hybrid Journal   (Followers: 1)
International Journal of Modeling, Simulation, and Scientific Computing     Hybrid Journal   (Followers: 3)
International Journal of Modelling, Identification and Control     Hybrid Journal   (Followers: 1)
International Journal of Modern Education and Computer Science     Open Access   (Followers: 2)
International Journal of Multimedia Data Engineering and Management     Full-text available via subscription   (Followers: 2)
International Journal of Multimedia Information Retrieval     Partially Free   (Followers: 8)
International Journal of Nanotechnology and Molecular Computation     Full-text available via subscription   (Followers: 4)
International Journal of Natural Computing Research     Hybrid Journal  
International Journal of Neural Systems     Hybrid Journal   (Followers: 4)
International Journal of Online Marketing     Full-text available via subscription   (Followers: 5)
International Journal of Organizational and Collective Intelligence     Hybrid Journal   (Followers: 1)
International Journal of Parallel, Emergent and Distributed Systems     Hybrid Journal   (Followers: 3)
International Journal of Pattern Recognition and Artificial Intelligence     Hybrid Journal   (Followers: 12)
International Journal of Performance Arts and Digital Media     Hybrid Journal   (Followers: 12)
International Journal of Pervasive Computing and Communications     Hybrid Journal   (Followers: 3)
International Journal of Polymer Science     Open Access   (Followers: 25)
International Journal of Process Systems Engineering     Hybrid Journal   (Followers: 1)
International Journal of Quantum Information     Hybrid Journal   (Followers: 6)
International Journal of Reasoning-based Intelligent Systems     Hybrid Journal  
International Journal of Reconfigurable and Embedded Systems     Open Access   (Followers: 6)
International Journal of Reconfigurable Computing     Open Access  
International Journal of Refractory Metals and Hard Materials     Hybrid Journal   (Followers: 5)
International Journal of Reliability, Quality and Safety Engineering     Hybrid Journal   (Followers: 14)
International Journal of Reliable and Quality E-Healthcare     Full-text available via subscription   (Followers: 2)
International Journal of Research Studies in Computing     Open Access  
International Journal of RF and Microwave Computer-Aided Engineering     Hybrid Journal   (Followers: 26)
International Journal of Sediment Research     Full-text available via subscription   (Followers: 2)
International Journal of Sensor Networks     Hybrid Journal   (Followers: 2)
International Journal of Service and Computing Oriented Manufacturing     Hybrid Journal   (Followers: 2)
International Journal of Shape Modeling     Hybrid Journal   (Followers: 1)
International Journal of Signs and Semiotic Systems     Full-text available via subscription  
International Journal of Smart Grid and Green Communications     Hybrid Journal   (Followers: 2)
International Journal of Social and Organizational Dynamics in IT     Full-text available via subscription   (Followers: 1)
International Journal of Sociotechnology and Knowledge Development     Full-text available via subscription   (Followers: 1)
International Journal of Soft Computing and Networking     Hybrid Journal   (Followers: 2)
International Journal of Soft Computing and Software Engineering     Open Access   (Followers: 13)
International Journal of Software Engineering and Knowledge Engineering     Hybrid Journal   (Followers: 6)
International Journal of Spatio-Temporal Data Science     Hybrid Journal  
International Journal of Speech Technology     Hybrid Journal   (Followers: 7)
International Journal of Strategic Change Management     Hybrid Journal   (Followers: 7)
International Journal of Strategic Communication     Hybrid Journal   (Followers: 5)
International Journal of Strategic Information Technology and Applications     Full-text available via subscription   (Followers: 1)
International Journal of Stress Management     Full-text available via subscription   (Followers: 6)
International Journal of Student Project Reporting     Hybrid Journal   (Followers: 4)
International Journal of Swarm Intelligence     Hybrid Journal   (Followers: 2)
International Journal of Swarm Intelligence Research     Full-text available via subscription   (Followers: 3)
International Journal of System Dynamics Applications     Full-text available via subscription  
International Journal of Systems Science     Hybrid Journal   (Followers: 2)
International Journal of Systems Science : Operations & Logistics     Hybrid Journal  
International Journal of Systems, Control and Communications     Hybrid Journal   (Followers: 6)
International Journal of Technoethics     Full-text available via subscription   (Followers: 2)
International Journal of Technology and Educational Marketing     Full-text available via subscription   (Followers: 2)
International Journal of Technology and Human Interaction     Full-text available via subscription   (Followers: 2)
International Journal of Technology Diffusion     Full-text available via subscription   (Followers: 1)
International Journal of Technology Marketing     Hybrid Journal   (Followers: 3)
International Journal of Telecommunications & Emerging Technologies     Full-text available via subscription   (Followers: 1)
International Journal of the Digital Human     Hybrid Journal   (Followers: 2)
International Journal of Trust Management in Computing and Communications     Hybrid Journal   (Followers: 1)
International Journal of Ultra Wideband Communications and Systems     Hybrid Journal  
International Journal of Virtual Reality     Open Access   (Followers: 1)
International Journal of Virtual Technology and Multimedia     Hybrid Journal   (Followers: 2)
International Journal of Web Services Research     Full-text available via subscription  
International Journal of Wireless and Microwave Technologies     Open Access   (Followers: 12)
International Journal of Wireless Information Networks     Hybrid Journal   (Followers: 2)
International Journal on Advances in ICT for Emerging Regions (ICTer)     Open Access   (Followers: 2)
International Journal on Artificial Intelligence Tools     Hybrid Journal   (Followers: 9)
International Journal on Digital Libraries     Hybrid Journal   (Followers: 544)
International Journal on Document Analysis and Recognition (IJDAR)     Hybrid Journal   (Followers: 2)
International Journal on Smart Sensing and Intelligent Systems     Open Access  
International Journal on Software Tools for Technology Transfer (STTT)     Hybrid Journal   (Followers: 4)
International Review of Law, Computers & Technology     Hybrid Journal   (Followers: 3)
International Review of Research in Open and Distance Learning     Open Access   (Followers: 24)
International Transaction of Electrical and Computer Engineers System     Open Access   (Followers: 2)
Internet of Things     Hybrid Journal   (Followers: 2)
Internet of Things and Cyber-Physical Systems     Open Access   (Followers: 1)
Internet Technology Letters     Hybrid Journal  
IoT     Open Access  
IPSJ Transactions on Computer Vision and Applications     Open Access   (Followers: 1)
Iran Journal of Computer Science     Hybrid Journal  
ISPRS Open Journal of Photogrammetry and Remote Sensing     Open Access   (Followers: 3)
ISSS Journal of Micro and Smart Systems     Hybrid Journal   (Followers: 3)
Issues in Informing Science and Information Technology     Open Access   (Followers: 2)
IT Journal Research and Development     Open Access  
ITM Web of Conferences     Open Access  
ITNOW     Hybrid Journal   (Followers: 1)
J-ENSITEC : Journal Of Engineering and Sustainable Technology     Open Access   (Followers: 4)
JISTEM : Journal of Information Systems and Technology Management     Open Access   (Followers: 6)
JMIR mHealth and uHealth     Open Access   (Followers: 3)
Johnson Matthey Technology Review     Open Access  
Jornal Brasileiro de TeleSSaúde     Open Access  
Journal of Computer Science & Systems Biology     Open Access   (Followers: 3)
Journal of 3D Printing in Medicine     Hybrid Journal  
Journal of Advanced Computer Science & Technology     Open Access   (Followers: 3)
Journal of Advances in Information Systems and Technology     Open Access  
Journal of Advances in Mathematics and Computer Science     Open Access  
Journal of Aggression Maltreatment & Trauma     Hybrid Journal   (Followers: 5)
Journal of Algorithms & Computational Technology     Open Access  
Journal of Altmetrics     Open Access   (Followers: 7)
Journal of Ambient Intelligence and Humanized Computing     Hybrid Journal   (Followers: 1)
Journal of Applied & Computational Mathematics     Open Access  
Journal of Applied and Computational Topology     Hybrid Journal  
Journal of Applied Bioinformatics & Computational Biology     Hybrid Journal   (Followers: 4)
Journal of Applied Communication Research     Hybrid Journal   (Followers: 10)
Journal of Applied Informatics and Technology     Open Access  
Journal of Applied Intelligent System     Open Access  
Journal of Approximation Theory     Hybrid Journal   (Followers: 1)
Journal of Artificial Intelligence     Open Access   (Followers: 18)
Journal of Automated Reasoning     Hybrid Journal  
Journal of Automation and Control     Open Access   (Followers: 9)
Journal of Banking and Financial Technology     Hybrid Journal   (Followers: 1)
Journal of Big Data     Open Access   (Followers: 16)
Journal of Bioinformatics and Computational Biology     Hybrid Journal   (Followers: 19)
Journal of Biomedical Informatics     Partially Free   (Followers: 9)
Journal of Cases on Information Technology     Full-text available via subscription   (Followers: 3)
Journal of Chemical Information and Modeling     Hybrid Journal   (Followers: 18)
Journal of Chemical Theory and Computation     Hybrid Journal   (Followers: 21)
Journal of Circuits, Systems, and Computers     Hybrid Journal   (Followers: 4)

  First | 1 2 3 4 5 6 7 | Last

Similar Journals
Journal Cover
International Journal of Multimedia Information Retrieval
Journal Prestige (SJR): 0.268
Citation Impact (citeScore): 1
Number of Followers: 8  
 
  Partially Free Journal Partially Free Journal
ISSN (Print) 2192-6611 - ISSN (Online) 2192-662X
Published by Springer-Verlag Homepage  [2469 journals]
  • InceptionDepth-wiseYOLOv2: improved implementation of YOLO framework for
           pedestrian detection

    • Free pre-print version: Loading...

      Abstract: Pedestrian detection is one of the most challenging research areas in computer vision, as it involves classifying the image and localizing the pedestrian. Its applications, especially in automated surveillance and robotics, are exceedingly sought-after. Compared to traditional hand-crafted methods, convolutional neural networks (CNNs) have superior detection results. The single-stage detection networks, particularly the You Only Look Once (YOLO) network, have attained a satisfactory performance in object detection without compromising the computation speed and are among the state-of-the-art CNN-based methods. The YOLO framework can be leveraged to use in pedestrian detection as well. In this work, we propose an improved YOLOv2, called InceptionDepth-wiseYOLOv2. The proposed model uses a modified DarkNet53 engineered for a robust feature formation. Three inception depth-wise convolution modules are integrated at varying levels in DarkNet53, leading to a comprehensive feature of an object in the image. The proposed method is compared with state-of-the-art detection methods, i.e., FasterRCNN, YOLOv2 with various base networks, YOLOv3, and Single Shot Multibox Detector. Detection Error Trade-off Curve, Precision–Recall Curve, Log Average Miss Rate, and Average Precision performance metrics are used to compare the methods. The analysis for the count of pedestrians detected concerning their height is also carried out. The experimental study used three benchmark pedestrian datasets: the INRIA Pedestrian, PASCAL VOC 2012, and Caltech Pedestrian.
      PubDate: 2022-05-11
       
  • Semantic-enhanced discriminative embedding learning for cross-modal
           retrieval

    • Free pre-print version: Loading...

      Abstract: Cross-modal retrieval requires the retrieval from image to text and vice versa. Most existing methods leverage attention mechanism to explore advanced encoding network and utilize the ranking losses to reduce modal gap. Although these methods have achieved remarkable performance, they still suffer from some drawbacks that hinder the model from learning discriminative semantic embeddings. For example, the attention mechanism may assign larger weights to irrelevant parts than relevant parts, which prevents the model from learning discriminative attention distribution. In addition, traditional ranking losses could disregard relatively discriminative information due to the lack of appropriate hardest negative sample mining and information weighting schemes. In this paper, in order to alleviate these issues, a novel semantic-enhanced discriminative embedding learning method is proposed to enhance the discriminative ability of the model, which mainly consists of three modules. The attention-guided erasing module enables the attention model pay more attention to the relevant parts and reduce the interferences of irrelevant parts by erasing non-attention parts. The large-scale negative sampling module leverages momentum-updated memory banks to expand the number of negative samples, which helps increase the probability of hardest negative being sampled. Moreover, the weighted InfoNCE loss module designs a weighted scheme to assign a larger weight to a harder pair. We evaluate the proposed modules by integrating them into three existing cross-modal retrieval models. Extensive experiments demonstrate that integrating each proposed module to the existing models can steadily improve the performance of all models.
      PubDate: 2022-05-11
       
  • RGBD deep multi-scale network for background subtraction

    • Free pre-print version: Loading...

      Abstract: This paper proposes a novel deep learning model called deep multi-scale network (DMSN) for background subtraction. This convolutional neural network is built to use RGB color channels and Depth maps as inputs with which it can fuse semantic and spatial information. In comparison with previous deep learning background subtraction techniques that lack information due to its use of only RGB channels, our RGBD version is able to overcome most of the drawbacks, especially in some particular kinds of challenges. Further, this paper introduces a new protocol for the SBM-RGBD dataset, concerning scene-independent evaluation, dedicated to Deep Learning methods to set up a competitive platform that includes more challenging situations. The proposed method proved its efficiency in solving the background subtraction in complex situations at different levels. The experimental results verify that the proposed work outperforms the state of the art on SBM-RGBD and GSM datasets.
      PubDate: 2022-05-10
       
  • Music emotion recognition based on segment-level two-stage learning

    • Free pre-print version: Loading...

      Abstract: Abstract In most Music Emotion Recognition (MER) tasks, researchers tend to use supervised learning models based on music features and corresponding annotation. However, few researchers have considered applying unsupervised learning approaches to labeled data except for feature representation. In this paper, we propose a segment-based two-stage model combining unsupervised learning and supervised learning. In the first stage, we split each music excerpt into contiguous segments and then utilize an autoencoder to generate segment-level feature representation. In the second stage, we feed these time-series music segments to a bidirectional long short-term memory deep learning model to achieve the final music emotion classification. Compared with the whole music excerpts, segments as model inputs could be the proper granularity for model training and augment the scale of training samples to reduce the risk of overfitting during deep learning. Apart from that, we also apply frequency and time masking to segment-level inputs in the unsupervised learning part to enhance training performance. We evaluate our model on two datasets. The results show that our model outperforms state-of-the-art models, some of which even use multimodal architectures. And the performance comparison also evidences the effectiveness of audio segmentation and the autoencoder with masking in an unsupervised way.
      PubDate: 2022-04-25
       
  • DC-GNN: drop channel graph neural network for object classification and
           part segmentation in the point cloud

    • Free pre-print version: Loading...

      Abstract: Abstract In the recent years, the problem of 3D shape analysis in the point cloud is considered as one of the challenging research topics in the field of computer vision. The major issues here are effective representation of the 3D information, meaningful feature extraction and subsequent task of classification. In this research paper, a deep learning-based network called Drop Channel Graph Neural Network (DC-GNN) is proposed for object classification and part segmentation. The DC-GNN model employs the idea of k-NN-based drop channel with hierarchical feature selection approach at each layer for dynamic graph construction, and further, with the help of Multi-Layer Perceptron Networks accomplishes the task of object classification. The same DC-GNN model is extended to carry out part segmentation in the point cloud data using the ShapeNet-Part benchmark dataset. The proposed network reports the state-of-the-art classification accuracy of 93.64% with ModelNet-40 dataset (Source-Code-https://github.com/merazlab/DC-GNN).
      PubDate: 2022-04-21
       
  • Multi-sensor human activity recognition using CNN and GRU

    • Free pre-print version: Loading...

      Abstract: Abstract In the current era of rapid technological innovation, human activity recognition (HAR) has emerged as a principal research area in the field of multimedia information retrieval. The capacity to monitor people remotely is a main determinant of HAR’s central role. Multiple gyroscope and accelerometer sensors can be used to aggregate data which can be used to recognise human activities—one of the key research objectives of this study. Optimal results are attained through the use of deep learning models to carry out HAR in the collected data. We propose the use of a hierarchical multi-resolution convolutional neural networks in combination with gated recurrent uni. We conducted an experiment on the mHealth and UCI data sets, the results of which demonstrate the efficiency of the proposed model, as it achieved acceptable accuracies: 99.35% in the mHealth data set and 94.50% in the UCI data set.
      PubDate: 2022-04-19
       
  • A local representation-enhanced recurrent convolutional network for image
           captioning

    • Free pre-print version: Loading...

      Abstract: Abstract Image captioning is a challenging task that aims to generate a natural description for an image. The word prediction is dependent on local linguistic contexts and fine-grained visual information and is also guided by previous linguistic tokens. However, current captioning works do not fully utilize local visual and linguistic information, generating coarse or incorrect descriptions. Also, captioning decoders have less recently focused on convolutional neural network (CNN), which has the advantage in extracting features. To solve these problems, we propose a local representation-enhanced recurrent convolutional network (Lore-RCN). Specifically, we propose a visual convolutional network to obtain enhanced local linguistic context, which incorporates selected local visual information and models short-term neighboring. Furthermore, we propose a linguistic convolutional network to obtain enhanced linguistic representation, which models long- and short-term correlations explicitly to leverage guiding information from previous linguistic tokens. Experiments conducted on COCO and Flickr30k datasets have verified the superiority of our proposed recurrent CNN-based model.
      PubDate: 2022-04-12
       
  • Siamese coding network and pair similarity prediction for near-duplicate
           image detection

    • Free pre-print version: Loading...

      Abstract: Abstract Near-duplicate detection in a dataset involves finding the elements that are closest to a new query element according to a given similarity function and proximity threshold. The brute force approach is very computationally intensive as it evaluates the similarity between the queried item and all items in the dataset. The potential application domain is an image sharing website that checks for plagiarism or piracy every time a new image is uploaded. Among the various approaches, near-duplicate detection was effectively addressed by SimPair LSH (Fisichella et al., in Decker, Lhotská, Link, Spies, Wagner (eds) Database and expert systems applications, Springer, 2014). As the name suggests, SimPair LSH uses locality sensitive hashing (LSH) and computes and stores in advance a small set of near-duplicate pairs present in the dataset and uses them to reduce the candidate set returned for a given query using the Triangle inequality. We develop an algorithm that predicts how the candidate set will be reduced. We also develop a new efficient method for near-duplicate image detection using a deep Siamese coding neural network that is able to extract effective features from images useful for building LSH indices. Extensive experiments on two benchmark datasets confirm the effectiveness of our deep Siamese coding network and prediction algorithm.
      PubDate: 2022-04-12
       
  • Anomaly detection using edge computing in video surveillance system:
           review

    • Free pre-print version: Loading...

      Abstract: Abstract The current concept of smart cities influences urban planners and researchers to provide modern, secured and sustainable infrastructure and gives a decent quality of life to its residents. To fulfill this need, video surveillance cameras have been deployed to enhance the safety and well-being of the citizens. Despite technical developments in modern science, abnormal event detection in surveillance video systems is challenging and requires exhaustive human efforts. In this paper, we focus on evolution of anomaly detection followed by survey of various methodologies developed to detect anomalies in intelligent video surveillance. Further, we revisit the surveys on anomaly detection in the last decade. We then present a systematic categorization of methodologies for anomaly detection. As the notion of anomaly depends on context, we identify different objects-of-interest and publicly available datasets in anomaly detection. Since anomaly detection is a time-critical application of computer vision, we explore the anomaly detection using edge devices and approaches explicitly designed for them. The confluence of edge computing and anomaly detection for real-time and intelligent surveillance applications is also explored. Further, we discuss the challenges and opportunities involved in anomaly detection using the edge devices.
      PubDate: 2022-03-29
       
  • PDS-Net: A novel point and depth-wise separable convolution for real-time
           object detection

    • Free pre-print version: Loading...

      Abstract: Abstract Numerous recent object detectors and classifiers have shown acceptable performance in recent years by using convolutional neural networks and other efficient architectures. However, most of them continue to encounter difficulties like overfitting, increased computational costs, and low efficiency and performance in real-time scenarios. This paper proposes a new lightweight model for detecting and classifying objects in images. This model presents a backbone for extracting in-depth features and a spatial feature pyramid network (SFPN) for accurately detecting and categorizing objects. The proposed backbone uses point-wise separable (PWS) and depth-wise separable convolutions, which are more efficient than standard convolution. The PWS convolution utilizes a residual shortcut link to reduce computation time. We also propose a SFPN that comprises concatenation, transformer encoder–decoder, and feature fusion modules, which enables the simultaneous processing of multi-scale features, the extraction of low-level characteristics, and the creation of a pyramid of features to increase the effectiveness of the proposed model. The proposed model outperforms all of the existing backbones for object detection and classification in three publicly accessible datasets: PASCAL VOC 2007, PASCAL VOC 2012, and MS-COCO. Our extensive experiments show that the proposed model outperforms state-of-the-art detectors, with mAP improvements of 2.4% and 2.5% on VOC 2007, 3.0% and 2.6% on VOC 2012, and 2.5% and 3.6% on MS-COCO in the small and large sizes of the images, respectively. In the MS-COCO dataset, our model achieves FPS of 39.4 and 33.1 in a single GPU for the small ( \(320 \times 320\) ) and large ( \(512 \times 512\) ) sizes of the images, respectively, which shows that our method can run in real-time.
      PubDate: 2022-03-24
       
  • Caption TLSTMs: combining transformer with LSTMs for image captioning

    • Free pre-print version: Loading...

      Abstract: Image to captions has attracted widespread attention over the years. Recurrent neural networks (RNN) and their corresponding variants have been the mainstream when it comes to dealing with image captioning task for a long time. However, transformer-based models have shown powerful and promising performance on visual tasks contrary to classic neural networks. In order to extract richer and more robust multimodal intersection feature representation, we improve the original abstract scene graph to caption model and propose the Caption TLSTMs which is made up of two LSTMs with Transformer blocks in the middle of them in this paper. Compared with the model before improvement, the architecture of our Caption TLSTMs enables the entire network to make the most of the long-term dependencies and feature representation ability of the LSTM, while encoding the multimodal textual, visual and graphic information with the transformer blocks as well. Finally, experiments on VisualGenome and MSCOCO datasets have shown good performance in improving the general image caption generation quality, demonstrating the effectiveness of the Caption TLSTMs model.
      PubDate: 2022-03-23
       
  • Few2Decide: towards a robust model via using few neuron connections to
           decide

    • Free pre-print version: Loading...

      Abstract: Abstract Researches have shown that image classification networks are vulnerable to adversarial examples, which seriously limits their application in safely critical scenarios. Existing defense methods usually employ adversarial training or adjust the network structure to resist adversarial attack. Although these defense methods can improve the model robustness to some extent, they often significantly decrease the accuracy on the clean data and bring additional computational cost. In this work, we analyze the impact of adversarial example on neuron connections and propose a Few2Decide method to train a robust model by dropping part of non-robust connections in the fully connected layer. Our model can get high perturbed data accuracy without increasing trainable parameters, meanwhile, get high clean data accuracy. Experimental results prove that our method can provide a robust model and achieve state-of-the-art performance on the CIFAR-10 dataset. Specifically, our Few2Decide method achieves 73.01% adversarial accuracy on the CIFAR-10 dataset under the challenging untargeted attack in white-box settings with an attack strength 8/255, using ResNet-20[4 \(\times \) ] architecture.
      PubDate: 2022-01-30
      DOI: 10.1007/s13735-021-00223-4
       
  • Interactive video retrieval evaluation at a distance: comparing sixteen
           interactive video search systems in a remote setting at the 10th Video
           Browser Showdown

    • Free pre-print version: Loading...

      Abstract: Abstract The Video Browser Showdown addresses difficult video search challenges through an annual interactive evaluation campaign attracting research teams focusing on interactive video retrieval. The campaign aims to provide insights into the performance of participating interactive video retrieval systems, tested by selected search tasks on large video collections. For the first time in its ten year history, the Video Browser Showdown 2021 was organized in a fully remote setting and hosted a record number of sixteen scoring systems. In this paper, we describe the competition setting, tasks and results and give an overview of state-of-the-art methods used by the competing systems. By looking at query result logs provided by ten systems, we analyze differences in retrieval model performances and browsing times before a correct submission. Through advances in data gathering methodology and tools, we provide a comprehensive analysis of ad-hoc video search tasks, discuss results, task design and methodological challenges. We highlight that almost all top performing systems utilize some sort of joint embedding for text-image retrieval and enable specification of temporal context in queries for known-item search. Whereas a combination of these techniques drive the currently top performing systems, we identify several future challenges for interactive video search engines and the Video Browser Showdown competition itself.
      PubDate: 2022-01-26
      DOI: 10.1007/s13735-021-00225-2
       
  • Enhancing the performance of 3D auto-correlation gradient features in
           depth action classification

    • Free pre-print version: Loading...

      Abstract: Abstract The 3D auto-correlation gradient features have demonstrated only limited success on depth action data, whereas the 2D auto-correlation gradient features have been successful in the domain. In this paper, we propose to calculate three depth motion map sequences from each depth action video by accumulating only the motion information of the action. We then obtain the three vectors of 3D auto-correlation gradient features by applying the space-time auto-correlation of gradients (STACOG) descriptor on the depth motion map sequences. The three vectors are then concatenated and passed to an unsupervised classifier to recognize the action. The experimental evaluation on four public datasets (MSR-Action3D, DHA, UTD-MHAD, and MSR-Gesture3D dataset) demonstrates the superiority of our proposed method over state-of-the-art methods.
      PubDate: 2022-01-16
      DOI: 10.1007/s13735-021-00226-1
       
  • Correction to: Different techniques for Alzheimer’s disease
           classification using brain images: a study

    • Free pre-print version: Loading...

      PubDate: 2021-12-01
      DOI: 10.1007/s13735-021-00222-5
       
  • AMS-CNN: Attentive multi-stream CNN for video-based crowd counting

    • Free pre-print version: Loading...

      Abstract: Abstract In recent years video-based crowd counting and density estimation (CCDE) have become essential for crowd analysis. Current approaches rarely exploit spatial–temporal features for CCDE, and they also usually do not consider measures to minimize the frame's background influence for obtaining crowd density maps, which has resulted in lower performance in terms of Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). Again, attention to individual feature set's response toward crowd counting is also neglected. To this end, we are motivated to design an end-to-end trainable attentive multi-stream convolutional neural network (AMS-CNN) for crowd counting. At first, a multi-stream CNN (MS-CNN) is designed to obtain crowd density maps. The MS-CNN comprises three streams to fuse deep spatial, temporal, and spatial foreground features from different cues of the crowd video dataset, like frames, the volume of frames, and foregrounds of frames. To improve the accuracy, we designed three stream-wise attention modules to generate attentive crowd density maps, and their relative average is obtained using a relative averaged attentive density-map (RAAD) layer. The relative averaged density map is concatenated with the MS-CNN output, followed by two-stage CNN blocks to get the final density map. The experiments are demonstrated on three publicly available crowd density video datasets: Mall, UCSD, and Venice. We obtained promising and better results in terms of MAE and RMSE as compared with state-of-the-art approaches.
      PubDate: 2021-12-01
      DOI: 10.1007/s13735-021-00220-7
       
  • A fast and robust affine-invariant method for shape registration under
           partial occlusion

    • Free pre-print version: Loading...

      Abstract: Abstract The acquisition of the planar images of the same object may be considerably different due to viewpoint dependencies, which influences the shape extraction, hence possibly making the curves partially visible and often accompanied by perspective distortions. In this paper, we propose a new contour alignment system relating to the special affine transformations that contain rotations and stretches, useful for describing planar contours which move in three-dimensional space and which are far enough away from the camera. The registration system that we suggest here includes a first optimization step relating to the dataset concerned. It consists in optimizing the number of correspondence points N between the curves to be registered. This is achieved by minimizing the conditioning of the correspondence matrix which is obtained by matching the re-sampling points by the equi-affine length of the two curves. This correspondence matrix is calculated for all the pairs of curves of the dataset by varying N. After extracting the optimal value of N, the estimation of the special affine transformation between a given couple of curves is realized by the pseudo-inverse of the correspondence matrix in the \(N_{0}\) resolution. This approach allows both providing the best accuracy and stabilizing the results of registration. We evaluate and compare our algorithm with other existing methods under different shape variations including noise, missing parts, and articulated deformations. The experiments are conducted on several known datasets.
      PubDate: 2021-11-30
      DOI: 10.1007/s13735-021-00224-3
       
  • Multimodal image and audio music transcription

    • Free pre-print version: Loading...

      Abstract: Abstract Optical Music Recognition (OMR) and Automatic Music Transcription (AMT) stand for the research fields that aim at obtaining a structured digital representation from sheet music images and acoustic recordings, respectively. While these fields have traditionally evolved independently, the fact that both tasks may share the same output representation poses the question of whether they could be combined in a synergistic manner to exploit the individual transcription advantages depicted by each modality. To evaluate this hypothesis, this paper presents a multimodal framework that combines the predictions from two neural end-to-end OMR and AMT systems by considering a local alignment approach. We assess several experimental scenarios with monophonic music pieces to evaluate our approach under different conditions of the individual transcription systems. In general, the multimodal framework clearly outperforms the single recognition modalities, attaining a relative improvement close to \(40\%\) in the best case. Our initial premise is, therefore, validated, thus opening avenues for further research in multimodal OMR-AMT transcription.
      PubDate: 2021-11-11
      DOI: 10.1007/s13735-021-00221-6
       
  • A review on deep learning in medical image analysis

    • Free pre-print version: Loading...

      Abstract: Abstract Ongoing improvements in AI, particularly concerning deep learning techniques, are assisting to identify, classify, and quantify patterns in clinical images. Deep learning is the quickest developing field in artificial intelligence and is effectively utilized lately in numerous areas, including medication. A brief outline is given on studies carried out on the region of application: neuro, brain, retinal, pneumonic, computerized pathology, bosom, heart, breast, bone, stomach, and musculoskeletal. For information exploration, knowledge deployment, and knowledge-based prediction, deep learning networks can be successfully applied to big data. In the field of medical image processing methods and analysis, fundamental information and state-of-the-art approaches with deep learning are presented in this paper. The primary goals of this paper are to present research on medical image processing as well as to define and implement the key guidelines that are identified and addressed.
      PubDate: 2021-09-04
      DOI: 10.1007/s13735-021-00218-1
       
  • Different techniques for Alzheimer’s disease classification using
           brain images: a study

    • Free pre-print version: Loading...

      Abstract: Abstract Alzheimer’s disease (AD) is a kind of dementia that is mostly experienced by people who are in the age of early 60s. In AD, brain cells that are responsible for forming memories and cognitive decisions, get affected which causes overall gray matter shrinkage in the human brain. Since AD patients are growing exponentially in the world, researchers are trying to develop an accurate mechanism for diagnosing the disease using brain images. In this paper, several research articles on AD classification are analyzed along with detailed observations. We have summarized as well as compared the research articles based on their classification performance. Although all the reviewed articles have the potential to classify AD, still there lies major future challenges. Among all the reviewed papers, it is found that the recent deep neural network-based classification techniques can produce the most promising results with an average performance rate of 93%.
      PubDate: 2021-05-19
      DOI: 10.1007/s13735-021-00210-9
       
 
JournalTOCs
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Email: journaltocs@hw.ac.uk
Tel: +00 44 (0)131 4513762
 


Your IP address: 100.24.115.215
 
Home (Search)
API
About JournalTOCs
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-