Tang Sheng, Ph.D., is currently a professor and doctoral supervisor of the Institute of Computing Technology of the Chinese Academy of Sciences, and a member of the Multimedia Special Committees of the China Computer Federation (CCF) and the China Society of Image and Graphics (CSIG), Experts in national key R&D programs. With the support of the National 973, 863, Key R&D Plan, Natural Science Foundation and 242 Information Security and other projects, he has led his team to engage in multimedia content analysis and understanding, computer vision and artificial intelligence research since 2006, and published more than 20 papers in the international top conferences such as ICCV, CVPR, AAAI, IJCAI, ACM Multimedia and top journals such as IEEE T-PAMI, T-IP etc., with more than 3500 citations. A number of image and video analysis systems developed have been applied in relevant national ministries and commissions and deployed in many places across the country with remarkable application effects. He organized the video evaluation of the first national audio and video retrieval and recognition challenge in 2014. He also led his team to achieve outstanding results in the international video retrieval evaluation TRECVID 2008 and the internationally famous ImageNet Large-scale Visual Recognition Challenge (ILSVRC 2016), and was invited to give presentations in these workshops. His team won the first prizes in the ICCV 2019 Large Vocabulary Instance Segmentation (LVIS) Challenge and in the ACM Multimedia 2021 Multi-modal Product Identification Challenge. He won the second prize in the National Natural Science Award, three first prizes in Beijing Science and Technology Award, one first prize in the Science and Technology Award of CCF, and two first prizes in the Science and Technology Award of the Chinese Institute of Electronics.