Seonghak Lee dltjdgkr6220@naver.com

Conference

- Lightweight Wasserstein Audio-Visual Model for Unified Speech Enhancement and Separation

Jisoo Park*, Seonghak Lee*, Guisik Kim, Taewoo Kim, Junseok Kwon, IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Honolulu, Hawaii, USA, 2025 [pdf] [code]

ACK: 2021-0-01341, Artificial Intelligence Graduate School Program

* Equal contribution

- Leveraging Stereo Vision with Deep Learning for Joint Deflection Measurement in SideWalks

Seonghak Lee+, Jisoo Park+, Paul Hyunbin Cho, ZongKai Xia, Loucif Hebbache, IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, USA, 2025 [pdf]

+This work was done when they were working at University of Toronto.

- WildTalker: Talking Portrait Synthesis In the Wild

Seonghak Lee*, Jisoo Park*, and Junseok Kwon, The 18th European Conference on Computer Vision (ECCV) Workshop, 3D Modeling, Reconstruction, and Generation in the Wild, Milano, Italy, 2024 [project] [pdf] [code]

* Equal contribution

- POTF: Prompt-based Object-centric Tensorial Field

Seonghak Lee*, Jisoo Park*, and Junseok Kwon, International Conference on ICT Convergence (ICTC), Jeju, Korea, Oct. 2024 [pdf]

(*equal contribution)

ACK: BK21 FOUR

Journal

- SOTA: Sequential Optimal Transport Approximation For Visual Tracking in Wild Scenario

Seonghak Lee, Jisoo Park, Radu Timofte, Junseok Kwon, IEEE Access (ACCESS), Vol. 12, no. 1, page 177028-177037, 2024 [pdf]

ACK: 2021-0-01341, Artificial Intelligence Graduate School Program, Chung-Ang University Research Grants

Patents

Page updated

Google Sites

Report abuse