sheldonfung98,SheldonFung,github

🎓 I hold a Ph.D. in Computer Vision, specializing in 2D/3D image processing using deep learning techniques.

🔍 My interests span across various domains within computer vision, including point cloud processing, bio-identification, object detection, and robotics. I'm passionate about exploring how cutting-edge technologies can enhance our understanding and interaction with the visual world.

🚀 Always eager to collaborate on innovative projects. Feel free to explore my repositories and reach out if you have any questions, suggestions, or opportunities for collaboration. Let's push the boundaries of technology together! Also, I'm available for hiring.

Gallery

Papers

Published Works

Deep detection for face manipulation • Deepfake detection

Feng, D., Lu, X., & Lin, X. (2020). Deep detection for face manipulation. In Neural Information Processing: 27th International Conference, ICONIP 2020, Bangkok, Thailand, November 18–22, 2020, Proceedings, Part V 27 (pp. 316-323). Springer International Publishing.

DeepKakeUCL • Deepfake detection

Fung, S., Lu, X., Zhang, C., & Li, C. T. (2021, July). Deepfakeucl: Deepfake detection via unsupervised contrastive learning. In 2021 international joint conference on neural networks (IJCNN) (pp. 1-8). IEEE.

I-Nema • Nematode dataset & identification

Lu, X., Fung, S., Wang, Y., Ouyang, W., Qing, X., & Li, H. I-Nema: A Large-Scale Microscopic Image Dataset for Nematode Recognition. Available at SSRN 4213402.

Anatomical Landmarks Localization for 3D Foot Point Clouds • point cloud keypoint detection

Fung, S., Lu, X., Mykolaitis, M., Razzak, I., Kostkevičius, G., & Ozerenskis, D. (2022, November). Anatomical Landmarks Localization for 3D Foot Point Clouds. In International Conference on Neural Information Processing (pp. 627-638). Cham: Springer International Publishing.

Veintr • Hand vein identification (Joint first author)

Lu, S., Fung, S., Pan, W., Wickramasinghe, N., & Lu, X. (2024). Veintr: robust end-to-end full-hand vein identification with transformer. The Visual Computer, 1-9.

TopFormer • Point cloud registration

Fung, S., Pan, W., Liu, X., Yearwood, J., Dazeley, R., & Lu, X. (2024, March). TopFormer: Topology-Aware Transformer for Point Cloud Registration. In International Conference on Computational Visual Media (pp. 112-128). Singapore: Springer Nature Singapore.