Yan Song

Yan Song is currently an associate professor with Nanjing University of Science and Technology, Nanjing, China. She received the Ph.D. degree in computer application technology from Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China, in 2011. She visited University of Maryland as a visiting scholar from 2018 to 2019. Her current research interests include video content analysis and understanding, and her main focus is on human action recognition and detection in videos. Prof. Song has published over 30 journal and conference papers in the area, including IEEE TCSVT, IEEE SPL, ICME etc. She served as a reviewer for Journal of Visual Communication and Image Representation and Neurocomputing, etc. [中文版]

★ Selected Publications

[1] Yan Song, Chengcheng Ning, Lingling Fa, et al. Multi-part boosting LSTMS for skeleton based human activity analysis, IEEE International Conference on Multimedia & Expo Workshops, 2017: 605-608.

[2] Yan Song, Shi Liu, Jinhui Tang. Describing Trajectory of Surface Patch for Human Action Recognition on RGB and Depth Videos, IEEE Signal Processing Letters, pp: 426-429, Vol. 22, No. 4, 2015

[3] Yan Song, Yang Lin. Combining RGB and Depth Features for Action Recognition based on Sparse Representation, Proceeding of the 7th International Conference on Internet Multimedia Computing and Service 2015, Zhangjiajie, China, Aug. 2015.

[4] Yan Song，Jinhui Tang, Fan Liu, Shuicheng Yan. Body Surface Context: A New Robust Feature for Action Recognition From Depth Videos, IEEE Trans. on Circuits and Systems for Video Technology, pp: 952 -964, 24(6), 2014

[5] Haiyu Jiang, Yan Song*, Jiang He, et al. Cross Fusion for Egocentric Interactive Action Recognition, International Conference on Multimedia Modeling, 2020: 714-726.

[6] He J, Song Y*, Jiang H. Bi-direction Feature Pyramid Temporal Action Detection Network, Asian Conference on Pattern Recognition. Springer, Cham, 2019: 889-901.

[7] Minglei Yang, Yan Song*, Xiangbo Shu, et al. Temporal Action Localization Based on Temporal Evolution Model and Multiple Instance Learning, International Conference on Multimedia Modeling, 2019: 341-351.

[8] Lingling Fa, Yan Song, Xiangbo Shu. Global and local C3D ensemble system for first person interactive action recognition, International Conference on Multimedia Modeling, 2018: 153-164.

[9] Xinran Liu, Yan Song*, Jinhui Tang. Effective Action Detection Using Temporal Context and Posterior Probability of Length, International Conference on Multimedia Modeling, 2018: 106-117.

[10] Ai X, Song Y*, Li Z. Unsupervised Video Summarization Based on Consistent Clip Generation. 2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM), 2018: 1-7.

[11] ChengchengNing, HuajunZhou, YanSong*, JinhuiTang.InceptionSingleShotMultibox Detector for Object Detection, IEEE International Conference on Multimedia & Expo Workshops, 2017: 549-554.