Swarnendu Ghosh

According to our database1, Swarnendu Ghosh authored at least 19 papers between 2014 and 2021.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.



In proceedings 
PhD thesis 


On csauthors.net:


Two-phase Dynamic Routing for Micro and Macro-level Equivariance in Multi-Column Capsule Networks.
Pattern Recognit., 2021

Multi scale mirror connection based encoder decoder network for text localization.
Pattern Recognit. Lett., 2020

Improved word-level handwritten Indic script identification by integrating small convolutional neural networks.
Neural Comput. Appl., 2020

SynCGAN: Using learnable class specific priors to generate synthetic data for improving classifier performance on cytological images.
CoRR, 2020

Reshaping inputs for convolutional neural network: Some common and uncommon methods.
Pattern Recognit., 2019

SegFast-V2: Semantic image segmentation with less parameters in deep learning for autonomous driving.
Int. J. Mach. Learn. Cybern., 2019

Understanding Deep Learning Techniques for Image Segmentation.
ACM Comput. Surv., 2019

Using dynamic routing to extract intermediate features for developing scalable capsule networks.
CoRR, 2019

Handwritten Indic Character Recognition using Capsule Networks.
CoRR, 2019

GSD-Net: Compact Network for Pixel-Level Graphical Symbol Detection.
Proceedings of the 13th IAPR International Workshop on Graphics Recognition, 2019

The journey of graph kernels through two decades.
Comput. Sci. Rev., 2018

Combining Multi-level Contexts of Superpixel using Convolutional Neural Networks to perform Natural Scene Labeling.
CoRR, 2018

Deep learning for word-level handwritten Indic script identification.
CoRR, 2018

SegFast: A Faster SqueezeNet based Semantic Image Segmentation Technique using Depth-wise Separable Convolutions.
Proceedings of the ICVGIP 2018: 11th Indian Conference on Computer Vision, 2018

Representing image captions as concept graphs using semantic information.
Proceedings of the 2016 International Conference on Advances in Computing, 2016

A multi-cue information based approach to contour detection by utilizing superpixel segmentation.
Proceedings of the 2016 International Conference on Advances in Computing, 2016

Comparison of Different Graph Distance Metrics for Semantic Text Based Classification.
Polytech. Open Libr. Int. Bull. Inf. Technol. Sci., 2014

Using Graphs and Semantic Information to Improve Text Classifiers.
Proceedings of the Advances in Natural Language Processing, 2014

JU-Evora: A Graph Based Cross-Level Semantic Similarity Analysis using Discourse Information.
Proceedings of the 8th International Workshop on Semantic Evaluation, 2014