Visual Information Coding Meets Machine Learning: Large-Scale Challenges (VICML 2015)


The aim of this session is to present new solutions addressing challenges of large-scale multimedia applications. The session will focus on new groundbreaking technologies exploring large collections of images, videos, audios and text documents. Besides the recent impressive achievements in the domain of local descriptors developed for various types of multimedia contents and deep learning neural networks, most of these technologies face numerous shortcomings related to the complexity, memory and robustness. Also most popular relational database and data warehouses management systems do not provide efficient solutions for handling visual information. These problems have a multidisciplinary nature and require expertise from computer vision, image processing, coding, machine learning and database management. Therefore, this session should serve as an additional opportunity for multidisciplinary researchers to exchange their experience and ideas on the above open problems.

List of topics

Topics include but are not limited to:

  • New methods of efficient content representation targeting complexity-memory-robustness trade-off
  • New techniques of data encoding for fast retrieval and recognition
  • New methods of benchmarking and optimization targeting comparison of description based and natural network based systems
  • Machine learning architectures for visual recognition
  • Mobile visual search systems
  • Fine-grained recognition systems
  • Cloud computing and architectures for computer vision
  • Security and privacy-preserving retrieval and recognition systems
  • Novel algorithms based on computational intelligence for analyzing online analytical processing (OLAP) data
  • Optimization of processes associated with relational databases performance
  • SQL language extensions for handling multimedia, large text objects, and spatial data
  • NoSQL databases for visual data
  • Applications

Information for authors

The submitted papers should present results of original and unpublished research. The papers will be reviewed by the CYBCONF 2015 International Program Committee. Accepted papers will be presented at the conference and will be included in the conference proceedings. Papers must be prepared using IEEE templates for conference proceedings. All papers must be submitted electronically via the conference submission system.

Important dates

Paper submission: March 22, 2015
Notification of acceptance: April 15, 2015
Final paper submission and Early registration: April 30, 2015
Conference: June 24-26, 2015


Marcin Korytkowski, Częstochowa University of Technology, Poland

Taras Holotyak, University of Geneva, Switzerland

Rafal Scherer, Częstochowa University of Technology, Poland, e-mail:

Slava Voloshynovskiy, University of Geneva, Switzerland

Program committee

  • Ireneusz Czarnowski – Gdynia Maritime University
  • Boguslaw Cyganek – AGH University of Science and Technology
  • Jacek Mandziuk – Warsaw University of Technology
  • Ngoc Thanh Nguyen – Wroclaw Univ. of Technology
  • Jacek Ruminski – Gdansk University of Technology
  • Przemyslaw Sliwinski – Wrocław University of Technology
  • Julian Szymanski – Gdańsk University of Technology
  • Robert Wrembel – Poznan University of Technology