My research interest now lies in the fields of protein-protein interaction prediction and de novo protein design. I am working on developing approaches to harness the invaluable data encapsulated within the metagenome.
Here we introduce three novel modules for Segment Anything Model (SAM) for efficient few-shot medical image segmentation, experiments on popular abdominal CT and MRI dataset showed average improvements of 10.21% and 1.80% in terms of DSC, respectively.
[PDF] [Code]
Utilizing insights from BERT and MAE, we developed a sequence classification model to accurately predict students' performance through a series of gameplay actions, earning us a prestigious bronze medal (top 5.6%).
[Contest Link]
Utilizing Euclidean Alignment and Independent Component Analysis (ICA), we generated a substantial volume of high-quality data, successfully mitigating the over-fitting issue prevalent in EEG based Brain-Computer Interfaces. Impressively, I secured the 20th position among 283 global teams predominantly comprised of master's and Ph.D. students.
[Contest Link] [Code]
By incorporating a lightweight Convolutional Block Attention Module into ArcFace and optimizing the training with challenging images isolated using MCTNN, I successfully honed the network's focus on distinguishing features such as the eyes and hairline, thereby enhancing the performance by a notable 4%.
[PDF]
By adeptly merging a transformer-based tracker with YOLOv5, I successfully developed a system capable of mitigating player and ball occlusion issues, enabling automatic and precise tracking of the small soccer ball at real-time FPS through a whole game.
Contribution: I proposed to use MTCNN + Arcface to process pictures sequentially, first extract faces and then identify masks with feature vectors. We got a pretty good result on off-line test set.
