About me
A picture taken at sunshine coast. A beautiful night made me feel I was in the heaven
I am a senior machine learning engineer at Nvidia. Previously, I was a research fellow at DATA61, CSIRO (ICV group). I received my Ph.D. from Monash University (Australia), supervised by A/Prof. Mehrtash Harandi and Prof. Tom Drummond. I completed my bachelor degree at Monash University and Central University (2+2 program). My previous research interest largely lies in efficient adaptation algorithms for deep learning models (Few-Shot Learning) in the context of computer vision.
Now, I’m currently interested and have been working on:
- 3D scene reconstruction and novel view synthesis (Neural Radiance Field).
- 3D reconstruction of surfaces/dense point cloud from images.
- Game automation development
Recent News
- I started my position at Nvidia as a senior machine learning engineer! (Shanghai)
- I joined CSIRO as a Research Fellow since Feb, 2023 (Brisbane).
- I completed the Ph.D degree in Dec, 2022 (Melbourne).
Recent Research Highlights
- Learning Instance and Task-Aware Dynamic Kernels for Few-Shot Learning
Rongkai Ma, Pengfei Fang, Gil Avrahham, Yan Zuo, Tianyu Zhu, Tom Drummond, Mehrtash Harandi. In Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27, 2022, Proceedings. 2022. - Adaptive Poincaré point to set distance for few-shot classification
Rongkai Ma, Pengfei Fang, Tom Drummond, Mehrtash Harandi. In Proceedings of the 36th AAAI conference on artificial intelligence. 2022. - Rethinking Generalization in Few-Shot Classification
Markus Hiller*, Rongkai Ma*, Mehrtash Harandi, Tom Drummond. In Advances in Neural Information Processing Systems (NeurIPS) 35. 2022. - Looking beyond two frames: End-to-end multi-object tracking using spatial and temporal transformers
Tianyu Zhu, Markus Hiller, Mahsa Ehsanpour, Rongkai Ma, Tom Drummond, Ian Reid, Hamid Rezatofighi. In IEEE Transactions on Pattern Analysis and Machine Intelligence. 2022. - Learning Online for Unified Segmentation and Tracking Models
Tianyu Zhu*, Rongkai Ma*, Mehrtash Harandi, Tom Drummond. In 2021 International Joint Conference on Neural Networks (IJCNN). 2021. - Divide and Conquer: Rethinking the Training Paradigm of Neural Radiance Fields
Rongkai Ma,Leo Lebrat, Rodrigo Santa Cruz, Gil Avraham, Yan Zuo, Clinton Fookes. In arxiv. 2024.