The MediA recoGnition and UnderStanding (MAGUS) Group focuses on the technological innovation and applications in media recognition and understanding. We aim at discovering solutions to core problems and improving machine intelligence to boost revenue of various industries. Our ultimate goal is to become the leading provider of intelligent solutions across industries. In recent years, we have made some progress in the fields of visual media semantic understanding and environment perception for unmanned systems with papers published in high-ranked journals like MM, TOMM, and TMM, and have received multiple honors in the technical challenges hosted by influential conferences such as MM, ICME, and ECCV. Some of our research findings have been transformed into industrial applications to serve leading companies including ATA, Samsung, CSIC, and SGCC.
One paper was accepted to ICMR 2023. Congratulations to Beibei Zhang, Yaqun Fang, Fan Yu!
One paper was accepted to ICME 2023. Congratulations to Ruichao Hou, Boyue Xu!
Beibei Zhang and Yaqun Fang won 1st place in the Movie-Level Track (Group 2) and 3rd place in the Scene-Level Track (Group 1&2) of MM 2022 Deep Video Understanding Challenge. Congratulations to Beibei Zhang and Yaqun Fang!
Fan Yu, Zhixiang Zhao, Yuchen Wang, and Yi Xu won 3rd place in MM 2022 PIC-HCVG Challenge. Congratulations to Fan Yu, Zhixiang Zhao, Yuchen Wang, and Yi Xu!
One paper was accepted to MM 2022. Congratulations to Yunqing He!
One paper was accepted to ICME 2022. Congratulations to Ruichao Hou!
ViROI Dataset for Visual Relation of Interest Detection was released and available for download.
Join Us
    MAGUS recruits undergraduate and postgraduate students who are interested in research and innovative applications in the field of multimedia computing. If you want to join MAGUS, please scan the QR code on the left to submit the application.
Contact Us
Address: Feiyimin Building, Gulou Campus of Nanjing University, 22 Hankou Road, Nanjing, Jiangsu Province