Kyungmin Kim

kyungk7 [at] uci.edu

I am a Ph.D. student at Intelligent Dynamics Lab (advisor: Prof. Roy Fox), University of California, Irvine. My research interests lie at Reinforcement Learning and Computer Vision with an emphasis on scene understanding. From Sep. 2019 to Jan. 2020, I interned at Mobile Vision team in Facebook Reality Labs under the guidance of Peter Vajda.

CV | Google Scholar | Github

News

[09/2021] Joined Indylab @UCI as a Ph.D. student.
[05/2020] Start working as a contingent worker for research collaboration at Facebook.
[09/2019] Off to Facebook @ Menlo Park, CA for internship.

Education

Sep. 2021 - Present Ph.D. in Computer Science, University of California, Irvine (GPA: 4.0/4.0)

Mar. 2017 - Feb. 2022 M.S. in Computer Science, Yonsei University (GPA: 4.3/4.3)

Mar. 2013 - Feb. 2017 B.S. in Computer Science and Engineering, Yonsei University (GPA: 4.2/4.3, Rank: 2/91)

Work Experience

May 2020 - July 2021 Contingent Worker for Research Collaboration, Facebook

Sep. 2019 - Jan. 2020 Research Intern, Facebook

Jun. 2016 - Dec. 2016 (Part-time) Research Intern, Korea Institute of Science and Technology (KIST)

Publications

(* indicates equal contribution)

Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actors

Kolby Nottingham, Yasaman Razeghi, Kyungmin Kim, JB Lanier, Pierre Baldi, Roy Fox, Sameer SinghPreprint, 2023.[Paper] [Project Page]

CAG-QIL: Context-Aware Actionness Grouping via Q Imitation Learning for Online Temporal Action Localization

Hyolim Kang, Kyungmin Kim, Yumin Ko, Seon Joo KimICCV, 2021.

Rethinking the Self-Attention in Vision Transformers

Kyungmin Kim, Bichen Wu, Xiaoliang Dai, Peizhao Zhang, Zhicheng Yan, Peter Vajda, Seon Joo KimCVPRW, 2021.

Winning the CVPR’2021 Kinetics-GEBD Challenge: Contrastive Learning Approach

Hyolim Kang, Jinwoo Kim, Kyungmin Kim, Taehyun Kim, Seon Joo KimCVPRW, 2021.

Teaching machines to understand baseball games: Large-scale baseball video database for multiple video understanding tasks

Kyungmin Kim*, Minho Shim*, Young Hwi Kim*, Seon Joo KimEuropean Conference on Computer Vision (ECCV), 2018.[Paper] [Project Page]

ACK.

There are many researchers to thank, those who I have learned from or had the opportunity to work with, including but not limited to: Peizhao Zhang (Facebook Reality Labs), Bichen Wu (Facebook Reality Labs), Zijian He (Facebook Reality Labs), Zhicheng Yan (Facebook AI), Mike Zheng Shou (Facebook AI), Chen Change Cavan Loy (Nanyang Technological University professor), Paul Hongsuck Seo (Google Research), and Seoung Wug Oh (Adobe Research).

Last updated on July 27th, 2023