Special Session on
Deep Learning Models and Applications for Computer Vision

Aim and Scope

The methods of deep learning are geared on the learning of feature hierarchies. Convolutional networks, which were developed in the early 1990s, were the first application of deep learning to the problem of vision. Unsupervised learning algorithms may build effective feature hierarchies even when there is a scarcity of labelled data, which is one of the primary reasons why these methods have recently attracted an increased amount of attention. When there is a large amount of labelled data available, supervised learning methods can be utilised to train extremely large networks on extremely big datasets by making advantage of high-performance computing hardware. On a number of different vision tasks, such as category-level object recognition, object detection, and semantic segmentation, it has been demonstrated that such vast networks perform better than the stateof- the-art methods that were used in the past. Neural networks, hierarchical probabilistic models, and a wide variety of unsupervised and supervised feature learning algorithms are all a part of the deep learning family of methods. Deep learning is a rich family of approaches. The reasons for the success of these strategies, as well as the boundaries of their applicability, have been the subject of substantial discussion. There are a lot of unanswered problems concerning how they may be adapted to specific applications, how they can be scaled up, and how they can make use of hardware that is massively parallel. Authors are encouraged to submit manuscripts on any aspect of computer vision that pertains to deep learning for consideration in this special session of the conference. Work that demonstrates novel applications of deep learning methods, new learning algorithms, and work that provides insights into the capabilities of the approaches as well as their limitations is very much appreciated.

List of Topics Covered in this session: The following are some of the subjects that are pertinent to this discussion; however, this list is not limited to:

  • Recent developments in deep learning techniques for visual processing
  • Visual features Deep learning algorithms and models
  • Deep network compression and acceleration
  • Deep learning-based image segmentation
  • Deep learning-based image detection
  • Deep learning-based image recognition
  • Deep learning-based image verification
  • Deep learning-based image quality assessment
  • Deep generative networks
  • Attention models and transformer networks
  • CNN + RNN Models for video understanding
  • Video analysis and annotation
  • YOLO model and Vision Transformers
  • Deep learning based visual object tracking
  • Unconventional uses for the techniques of deep learning
  • Analyses comparing various deep learning approaches

Paper Submission

Potential authors may submit their manuscripts for presentation consideration through ICETCI 2024 submission system electronically at , following the conference guidelines. All submissions will go through peer review process. To submit your paper to this special session, you have to choose our special session title on the submission page.

Important Dates

Paper submission deadline: Mar 23, 2024
Apr 15, 2024
Paper acceptance notification date: Jun 20, 2024
Final paper submission and early registration deadline: Jun 30, 2024


Dr. A. Robert Singh
Assistant Professor
Department of Computational Intelligence, SRM Institute of Science and Technology, SRM Nagar, Kattankulathur, Tamil Nadu-603203, India ,

Dr. A. Robert Singh is working as Assistant Professor at Department of Computational Intelligence of SRM Institute of Science and Technology, Kattankulathur, Chennai. He was graduated at Anna University. He has completed post graduate in Computer Science and Engineering from St. Peter’s University, Chennai. He has secured his doctoral degree from Kalasalingam Academy of Research and Education, Anand Nagar, Krishnankoil. He has received a rich number of national level recognitions. He is a member of IEEE, IEI and ACM. His research interests are Computer Vision, Image Processing and Deep Learning particularly applied to medical image analysis. He is an active member in the computer vision and medical imaging community, regularly served as reviewer for international conferences and prestigious journals. He has a good number of publications in reputed journals and conferences.

Dr. A. Suganya
Assistant Professor
School of Computing, Sastra Deemed to be University Thanjavur Tamil Nadu-613401, India

Dr. A. Suganya works as Assistant Professor at School of Computing, Sastra Deemed to be University, Thanjavur, Tamil Nadu. She has received a B.E (CSE) from Anna University, India. She completed her M.E (CSE) from Manonmaniam Sundaranar University, India. She completed her Ph.D in Faculty of Information and Communication Engineering from Anna University, Chennai. She is a waiver of Maulana Azad National fellowship (MANF) from Ministry of Minority Affairs, Government of India. She is acting as a reviewer in reputed international conferences and international journals. She has a good number of publications in reputed conferences and journals. Her research interests are computer vision, medical image processing, natural language processing, machine learning, deep learning, multimedia coding and the Internet of Things (IoT).