About MLMR
To solve the problems about the intelligent processing of mass multimedia information in the network, we research the corresponding theories and techniques in the fields of information retrieval, pattern recognition, machine learning, computer vision and parallel and distributed computing. Based on the research outcomes, we try to develop more convinient and more transparent multimedia information retrieval systems which are oriented at mobile, medical, and other specifical applications. We emphasize the tight combination of theory research and creative applications: taking the theoretical outcomes as the basis of creative applications and using creative applications to guide and agglomerate our research directions. Therefore, we focus on the development and utilization of the retrieval systems, from which the key scientific problems to be solved are discovered and tackled. Then with the solution of these key scientific problems, the systems will be advanced and promoted for sustainable development.
Around the target above, the present four main research directions in our lab are pattern recognition and machine learning, image retrieval, medical image analysis, and Video retrieval. Supported by these research directions, three systems under construction are the smart-phone-captured image retrieval system, the imaging manifestation based medical image retrieval system, and the video retrieval system.
