Browsing Department of Physical Science by Author "Kokul, T."

Browsing Department of Physical Science by Author "Kokul, T."

Sort by: Order: Results:

  • A Comprehensive Study on Deep Image Classification with Small Datasets 
    Gayani, C.; Kokul, T.; Amalka, P. (Springer, 17-12-19)
    Convolutional Neural Networks (CNNs) showed state-of-the-art accuracyin image classification on large-scale image datasets. However, CNNs showconsiderable poor performance in classifying tiny data since their large number ...
  • Deep Match Tracker Classifying when Dissimilar, Similarity Matching when Not 
    Kokul, T.; Fookes, C.; Sridharan, S.; Ramanan, A.; Pinidiyaarachchi, U.A.J. (IEEE, IEEE International Conference on Image Processing (ICIP)., 07-10-18)
    Visual tracking frameworks employing ConvolutionalNeural Networks (CNNs) have shown state-of-the-art performancedue to their hierarchical feature representation. Whileclassification and update based deep neural net tracking ...
  • Gate connected convolutional neural network for object tracking 
    Kokul, T.; Fookes, C.; Sridharan, C.; Ramanan, A.; Pinidiyaarachchi, U.A.J. (IEEE, IEEE International Conference on Image Processing (ICIP), 17-09-17)
    Convolutional neural networks (CNNs) have been employedin visual tracking due to their rich levels of feature representation.While the learning capability of a CNN increaseswith its depth, unfortunately spatial information ...
  • Online Multi-Person Tracking-by-detection Method Using ACF and Particle Filter 
    Kokul, T.; Ramanan, A.; Pinidiyaarachchi, U.A.J. (IEEE, IEEE Seventh International Conference on Intelligent Computing and Information Systems (ICICIS), 12-12-15)
    Automatically detecting and tracking multiple persons in videos is one of the main research interests in computer vision based applications. This paper presents a tracking-by-detection approach for tracking people in dynamic ...
  • A Performance Evaluation of various SVM Tools and Different Feature Selection Strategies 
    Kokul, T. (Postgraduate Institute of Science, University of Peradeniya, 06-10-15)
    Support vector machine (SVM) is an efficient classification technique which is widely used in many machine learning applications due to the property of outperforming other classifiers in its generalization performance. ...
  • Single Image Defogging using Depth Estimation and Scene-Specific Dark Channel Prior 
    Kokul, T.; Anparasy, S. (IEEE, 19-01-21)
    Quality of outdoor images are often degraded under bad weather conditions by the extensive presence of suspended particles in the atmosphere such as fog and haze. Although, many single image defogging approaches have been ...
  • Target-Specific Siamese Attention Network for Real-time Object Tracking 
    Kokul, T.; Fookes, C.; Sridharan, S.; Ramanan, A.; Pinidiyaarachchi, A. (IEEE Transactions on Information Forensics and Security, 16-08-19)
    Deep similarity trackers are able to track above real-time speed. However, their accuracy is considerably lower than deep classification based trackers since they avoid valuable online cues. To feed the target-specific ...
  • Underwater Image Enhancement using Scene-Specific Red Channel Prior and Fusion 
    Anparasy, S.; Kokul, T. (IEEE, 10-12-21)
    Quality of underwater images are reduced with the depth since light is absorbed and scattered by the suspended particles in water. Although several optical model-based and model-free underwater image enhancement methods ...

Search


Browse

My Account