The goal of this project is to solve some of the most fundamental yet challenging problems in computer vision - object detection, localisation and recognition in large-scale. With the development of hardware, people nowadays have much more images in the size of G bytes than before. In the light of this, the research in the direction of processing big data attracts wide public attention. Due to large-scale visual object categories, the inter-class variation and computational complexity will further increase the difficulties in addition to large intra-class variation. The main focus of this project is set to improve the accuracy and efficiency of the-state-of-arts for large-scale visual object recognition.

The project is mainly carried out using the funding from Academy of Finland.


Dr. Ke (Cory) Chen E-mail Post-doc Researcher
Joni Kamarainen E-mail Professor

Selected Publications

Learning to Count with Back-Propagated Information

By Ke Chen and Joni-Kristian Kamarainen22th Int. Conf. on Pattern Recognition (ICPR2014) 2014.

Our method learns to count people from images (crowd counting). The method also helps to select low level features that correlate well with the number of people which is achieved by the novel concept of cumulative attribues.

Download: PDF, BibTex, Source Code


Data sets

State-of-the-art large scale image data set (inc. the annual ILSVRC challenge)

Authors and teams

Geoffrey E. Hinton
The father of deep neural networks that hit the jackpot in 2012
Fei-Fei Li
The creator of the Caltech-101 and ImageNet
Andrew Zisserman's group
Home of the Visual Bag of Words (BoW) approach