SouYoung Jin


SouYoung Jin is a postdoc in MIT’s Department of Electrical Engineering and Computer Science. Working with her adviser Aude Oliva, she is interested in developing and improving techniques in computer vision, especially video understanding. She earned a BS from Dongguk University, an MS from the Korea Advanced Institute of Science and Technology, and a PhD from the University of Massachusetts, Amherst.


  • Monfort, M., Jin, S., Liu, A.H., Harwath, D., Feris, R., Glass, J.,  Oliva, A., (2021). Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 
  • Singh, A., Su, H., Jin, S., Jiang, H., Manjesh, C., Luo, G., He, Z., Hong, L., Learned-Miller, E. G., Cowell, R. (2019). Half&Half: New Tasks and Benchmarks for Studying Visual Common Sense. CVPR Workshop on Vision Meets Cognition.
  • Jin, S., RoyChowdhury, A., Jiang, H., Singh, A., Prasad, A., Chakraborty, D., Learned-Miller, E. G. (2018). Unsupervised hard example mining from videos for improved object detection. European Conference on Computer Vision (ECCV).
  • Jin, S., Su, H., Stauffer, C., Learned-Miller, E. G. (2017). End-to-end face detection and cast grouping in movies using Erdos-Renyi clustering. International Conference on Computer Vision (ICCV).