Special Session on

“Feature Extraction and Learning on Image and Text Data”


Mukesh Prasad, Javier Andreu-Perez, Massimo Piccardi, Rajiv Ratn Shah, Weiping Ding, Guandong Xu

Aims and Scope:

The current resurgence of neural networks in the form of deep learning have shown remarkable results in fundamental computer vision tasks such as segmentation, tracking, detection, recognition, classification, clustering and feature learning. The deep features extracted from deep neural network architectures are robust and have good representation for most of these fundamental computer vision tasks. At the same time, deep representations are playing an equivalently important role in a variety of tasks of natural language processing (NLP) including, but not limited to, entity recognition, machine translation, extractive and abstractive summarization, dialogue systems and more. Although deep learning has shown tremendous amount of success in the fundamental tasks in many areas of image and text analysis, the intuitive understanding of the architectures is yet to be explored in details. There is a need of further exploration of architectures which are best suited for specific tasks. Another open issue it the training of neural network architectures to be followed by the transfer of the learned features to another unknown task, which requires transfer learning and fine tuning. Therefore, transfer learning also has a significant research scope, both from a theoretical and application perspective. Conversely, traditional machine learning approaches used to rely on hand-crafted features such edges, texture, SIFT, etc. The fusion of such features were used to tackle many complex computer vision and NLP problems and they poorly generalized to unknown samples.

Recent advances in both feature extraction and learning on image and text data have allowed us to develop promising solutions that are being increasingly used in our society. For this reason, this special session aims to bring together researchers, scientists, engineers and students to discuss the state of the art and the new trends in deep feature extraction and learning on image and text data. The idea of the session is to present recent theories and applications in deep learning, transfer learning, reinforcement learning and some other feature extraction/learning techniques for various image and text oriented tasks, such as object recognition, image retrieval/classification, annotation, multimedia processing, image super-resolution, text mining and text analysis. Special attention will be devoted to handle advanced issues of network architecture design, real-time performance criteria for various applications, and diverse application areas.


The main topics of this special session include, but are not limited to, the following:

· Cross domain transfer learning

· Real-time object segmentation, detection and recognition in complex environment

· Human gesture/activity recognition

· Visual analysis of crowds, surveillance systems and applications

· Document image analysis and systems

· Handwriting recognition

· Writer identification

· Text classification/analysis

· Machine translation

· Automated summarization

· Sparse representation and low-rank representation for feature extraction

· Contextual scene understanding and summarization

· Ensemble of traditional and deep learning techniques

· Methods applicable to Forensic Science

· Drone-based applications

· Novel reinforcement learning algorithms with deep neural network representations

· Multimodal feature extraction

· Multimodal deep learning

Special Session Organizers:

Dr. Mukesh Prasad (Mukesh.Prasad@uts.edu.au)

University of Technology Sydney, Australia

Dr. Javier Andreu-Perez (javier.andreu@essex.ac.uk)

University of Essex, UK

Prof. Massimo Piccardi (massimo.piccardi@uts.edu.au)

University of Technology Sydney, Australia

Dr. Rajiv Ratn Shah (rajivratn@iiitd.ac.in)

Indraprastha Institute of Information Technology, India

Dr. Weiping Ding (dwp9988@hotmail.com)

Nantong University, China

Prof. Guandong Xu (guandong.xu@uts.edu.au)

University of Technology Sydney, Australia

Important Dates:

Paper submission due: 30th Jan. 2020

Notification of acceptance: 15th Mar. 2020

Camera-ready deadline: 15th Apr. 2020

Author registration deadline: 15th Apr. 2020

Information about IEEE WCCI 2020: https://wcci2020.org/

We look forward to receiving your high-quality submissions!!