GCNN 2022: Graph Convolutional Neural Network for Computer Vision: Trends and Applications |
Submission link | https://easychair.org/conferences/?conf=gcnn2022 |
Abstract registration deadline | November 30, 2022 |
Abstract Acceptance | December 31, 2022 |
Submission deadline | May 31, 2023 |
Submission Link | https://easychair.org/conferences/?conf=gcnn2022 |
Graphs enhance collaboration between the tangible objects in our surroundings. Collections of objects connected by links make up graphs. The amalgamation of neural networks into graph approaches improved the incorporation of Graph Convolutional Neural Networks (GCNN). It is a semi-supervised learning approach over graph data. The convergence of Machine Learning, Computer Vision and Natural Language Processing with optimization techniques has opened up the possibility of metaheuristic optimization development in the area of computational intelligence. The challenges in integrating these technologies brought new dimensions in visualizing and solving the learning problems with graphs. By displaying the graph in a reduced dimensional space its capabilities and expressive ability are improved. The goal of this book chapter, is to analyze the possible areas that GCNN can work and break the barrier in moving closer to obtain the global optimal outcome for machine learning and deep learning application problems. Graphs enhance collaboration between the tangible objects in our surroundings. Collections of objects connected by links make up graphs. The amalgamation of neural networks into graph approaches improved the incorporation of Graph Convolutional Neural Networks (GCNN). It is a semi-supervised learning approach over graph data. The convergence of Machine Learning, Computer Vision and Natural Language Processing with optimization techniques has opened up the possibility of metaheuristic optimization development in the area of computational intelligence. The challenges in integrating these technologies brought new dimensions in visualizing and solving the learning problems with graphs. By displaying the graph in a reduced dimensional space its capabilities and expressive ability are improved. The goal of this book chapter, is to analyze the possible areas that GCNN can work and break the barrier in moving closer to obtain the global optimal outcome for machine learning and deep learning application problems.
Submission Guidelines
All chapters must be original and not simultaneously submitted to another book chapters / conference / journal.
List of Topics
- Role of Graph Convolution Neural Network in Computer Vision Applications
- Scene Graph Generation from static images: Overview, Methods, and Applications
- Transformation from CNN to graph-structured data: node classification and edge prediction
- Research Trends and Challenges of GCNN over CNN and Digital Image Processing Techniques
- Classification of graph filtering operations and Inductive learning by exploiting multiple graphs in GCNN
- GCNN based Combinatorial Optimization (CO) approaches in Computer Vision
- GCNN based framework for molecular fingerprint prediction
- Graph CNN based approach for moving object detection
- Analyze, detect and prevent the traffic flow using Spatio-temporal GCNN
- Detection of chest disease from X-Ray images using GCNN
- Improved Precision for Visual Question Answering System using Graph CNN
- Analysis and Classification of Images using GCNN in Medical Imaging
- GCNN based approach for cancer diagnosis in histopathological image
- Understanding the graph structure of compounds and molecules using GCNN
- Zero-shot learning (ZSL) task in Image classification using knowledge graphs by applying GCNN
- Case Study and Use Cases of Dynamic graphs in GCNN for Computer Vision
Editors
Dr. A. Malini, Thiagarajar College of Engineering, Madurai, India
Dr. Rajesh Kumar Dhanaraj, Galgotias University, India
Prof. J.Felicia Lilian, Thiagarajar College of Engineering, Madurai, India
Dr. Vandana Sharma, Amity University, Noida Campus, India
Dr. George Ghinea, Brunel University London, UK
Contact
All questions about submissions should be emailed to ...
gcnntrends22@gmail.com