Recently, the Machine Learning and Media Analysis group (http://mima.sdu.edu.cn), MIMA for short, led by Prof. Xu Xinshun at the School of Software, has obtained a series of research achievements in the field of artificial intelligence. A number of research articles have been published in some prestigious international journals and conferences, including IEEE Transactions on Image Processing, IEEE Transactions on Multimedia,Pattern Recognition,IEEE Transactions on Circuits and Systems for Video Technology,AAAI,IJCAI,SIGIR,WWW,and MM.
The main research interests of MIMA group include machine learning,text/image/video content analysis, large-scale media retrieval, and text spotting. More specifically, MIMA group's research focuses on three fields.Firstly,In the field of machine learning, the group has conducted a lot of research work on multi-label learning, multi-instance learning, deep learning, learning to hash and other related methods and models. Especially in hashing learning field, MIMA group has conducted deep explorations and achieved much progress. Secondly,in text/image/video content analysis field, MIMA group has also carried out machine learning based researches and proposed some models to analyze the content of images or videos,for example, a dual-stream deep neural network for multimedia content analysis, a GAN based video caption model. These models could understand images/videos and generate corresponding labels or captions for them.Thirdly,in the field of text spotting, MIMA group has conducted researches on image/video scene text detection/recognition and proposed effective deep learning based models. These models are capable of detecting texts contained in images and further recognizing them. Moreover, the corresponding models have been successfully applied to some real applications, for example,sensitive information extraction and text extraction/recognition in college entrance examination.
These works were supported by National Natural Science Foundation of China, Program for New Century Excellent Talents in University of the Ministry of Education, the Key Science Technology Project of Shandong Province.
MIMA group homepage:http://mima.sdu.edu.cn
Zhen-Duo Chen, Chuan-Xiang Li, Xin Luo, Liqiang Nie, Wei Zhang, and Xin-Shun Xu*. SCRATCH: A scalable discrete matrix factorization hashing framework for cross-modal retrieval. IEEE Transactions on Circuits and Systems for Video Technology, 2019.
Written by Luo Xin
Edited by Che Huiqing