About | Minjae Kang

Hi! I’m Minjae, a PhD student in the Department of Computing at Imperial College London under the supervision of Professor Björn W. Schuller.

My research is in audio-visual, and I’m particularly interested in video understanding, multimodal generation and generative models. I recently graduated with an MSc in Artificial Intelligence at King’s College London and worked on audio-visual generation during my MSc.

Please feel free to get in touch if you would like to work together!

Selected Publications

Seeing Soundscapes: Audio-Visual Generation and Separation from Soundscapes Using Audio-Visual Separator

Minjae Kang and Martim Brandão

arXiv: 2504.18283, 2025

Bib PAPER

@misc{Kang2025soundscapes,
  author = {Kang, Minjae and Brandão, Martim},
  title = {Seeing Soundscapes: Audio-Visual Generation and Separation from Soundscapes Using Audio-Visual Separator},
  eprint = {2504.18283},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
  year = {2025},
  url = {https://arxiv.org/abs/2504.18283}
}

GammaGAN: Gamma-Scaled Class Embeddings for Conditional Video Generation

Minjae Kang and Yong Seok Heo

Sensors, 2023

Bib PAPER

@article{Kang2023gammagan,
  author = {Kang, Minjae and Heo, Yong Seok},
  title = {{GammaGAN}: Gamma-Scaled Class Embeddings for Conditional Video Generation},
  journal = {Sensors},
  year = {2023},
  volume = {42},
  number = {19},
  pages = {8103},
  doi = {10.3390/s23198103},
  url = {https://doi.org/10.3390/s23198103}
}