Scholar
Dong Nie
Google Scholar ID: wk0hUKgAAAAJ
unc
Citations & Impact
Citations
9,146
H-index
42
i10-index
62
Publications
20
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- Successfully defended the dissertation in June 2019 at the University of North Carolina at Chapel Hill. Participated in many other medical imaging related projects. For more information, check the GitHub page.
Research Experience
- After graduation, started working in the industry. Initially focused on HD mapping using deep learning and geometric-based computer vision for recognition (image and point cloud) and localization (SFM). Later, became the head of perception for intelligent driving, leading a team working on 3D detection (image and point cloud), multi-object tracking, fusion, and auto-labeling. Also, has industry experience with large language models (LLM), including large multi-modality models (LMM). After 4.5 years in the first company, began a new journey in a second company, where worked on video AI related projects and partially on ranking AI (search, ads, and recsys are still the dominant roles in the internet industry even after more than ten years).
Education
- From September 2015 to May 2019, pursued a Ph.D. at the Department of Computer Science, University of North Carolina at Chapel Hill, focusing on Medical Image Analysis with Deep Learning. In the first year (August 2014 - May 2015) of the Ph.D., worked on probabilistic graphical model and RBM. From the second year onwards, moved to medical image analysis, specifically working on adversarial confidence learning with applications in medical image segmentation and synthesis, and another major research topic was low-contrast (blurry) boundary delineation. Prior to UNC, studied at the University of Chinese Academy of Sciences in Computer Science, researching natural language processing (NLP), especially sentiment analysis and named entity recognition.
Background
- Research interests include computer vision oriented topics: 2D/3D detection, Image/Instance/Panoptic Segmentation, Point Cloud Understanding and vision foundation models; natural language processing based topics: named entity recognition, sentiment analysis and embeddings, chatbot; x-modality related topics: cross-modality assisted imaging acceleration and Image/Video/Text Generation (from brain signals, e.g., fMRI/EEG/X-Ray to images/videos/text); large model based topics: PEFT, post-training, model-scaling, model-system co-design.
Miscellany
- Has broad interest in research and engineering works, covering areas such as computer vision, natural language processing, x-modality technologies, and large models.
Co-authors