SouYoung Jin

I am a postdoctoral associate at the Computer Science and Artificial Intelligence Laboratory (CSAIL) at the Massachusetts Institute of Technology (MIT), working with Aude Oliva. Previously I earned my PhD in College of Information and Computer Sciences (CICS), University of Massachusetts, Amherst (UMass Amherst), where I researched on improving face clustering in videos under Erik Learned-Miller in the Computer Vision Lab.

My research interests are in Computer Vision and Machine Learning. Here is my CV.


  • Mathew Monfort*, SouYoung Jin*, Alexander Liu, David Harwath, Rogerio Feris, James Glass, and Aude Oliva. Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions. Computer Vision and Pattern Recognition (CVPR), 2021.
    [pdf] [supp] [project page]

  • Alexander H Liu, SouYoung Jin, Cheng-I Jeff Lai, Andrew Rouditchenko, Aude Oliva, and James Glass. Cross-Modal Discrete Representation Learning. arXiv preprint arXiv:2106.05438, 2021. [pdf]

  • Ashish Singh*, Hang Su*, SouYoung Jin, Huaizu Jiang, Chetan Manjesh, Geng Luo, Ziwei He, Li Hong, Erik G. Learned-Miller, and Rosemary Cowell. Half&Half: New Tasks and Benchmarks for Studying Visual Common Sense. CVPR 2019 Workshop on Vision Meets Cognition, 2019. [pdf]

  • Aruni RoyChowdhury, Prithvijit Chakrabarty, Ashish Singh, SouYoung Jin, Huaizu Jiang, Liangliang Cao, and Erik Learned-Miller. Automatic adaptation of object detectors to new domains using self-training. Computer Vision and Pattern Recognition (CVPR), 2019.
    [pdf] [project page]

  • SouYoung Jin*, Aruni RoyChowdhury*, Huaizu Jiang, Ashish Singh, Aditya Prasad, Deep Chakraborty, and Erik Learned-Miller. Unsupervised hard example mining from videos for improved object detection. European Conference on Computer Vision (ECCV), 18 pages, 2018.
    [pdf] [project page]

  • SouYoung Jin, Hang Su, Chris Stauffer, and Erik Learned-Miller. End-to-end face detection and cast grouping in movies using Erdos-Renyi clustering. International Conference on Computer Vision (ICCV), 10 pages, 2017. spotlight [pdf] [supp] [code] [project page]

  • Sou-Young Jin, Ho-Jin Choi, and Yu-Wing Tai. A Randomized Algorithm for Natural Object Colorization. Computer Graphics Forum (Special Issue on Eurographics), vol. 33, no. 2, 2014. [pdf] [supp]

  • Sou-Young Jin, Suwon Lee, Nur Aziza Azis, and Ho-Jin Choi. Jigsaw Puzzle Image Retrieval via Pairwise Compatibility Measurement. International Conference on Big Data and Smart Computing (BigComp), pages 123 – 127, Bangkok, Thailand, Jan. 15-17, 2014. [pdf]

  • Sou-Young Jin and Ho-Jin Choi. Essential Body-Joint and Atomic Action Detection for Human Activity Recognition Using Longest Common Subsequence Algorithm. Lecture Notes in Computer Science, vol. 7729, pages 148-159, 2013. [pdf]

  • Sou-Young Jin, Ho-Jin Choi, and Youssef Iraqi. Depth Consistency Evaluation for Error-Pose Detection. International Conference on Machine Vision (ICMV), 15-16 November 2013. [pdf]

  • Sou-Young Jin, Ho-Jin Choi. Clustering Space-Time Interest Points for Action Representation. International Conference on Machine Vision (ICMV), 15-16 November 2013. [pdf]

  • Sou-Young Ji, Young-Seob Jong, Chankyu Park, Kyo-Joong Oh, and Ho-Jin Choi. An Intelligent Multi-Sensor Surveillance System for Elderly Care. Smart Computing Review, vol. 2, no. 4, August 2012. [pdf]

  • Sou-Young Jin, Jae-Kyung Won, Hojin Lee, and Ho-Jin Choi. Construction of Automated Screening System to Predict Breast Cancer Diagnosis and Prognosis. Basic and Applied Pathology, vol. 5, issue 1, pages 15-18, 16 Mar. [pdf]