Projects

Table of contents

1. Knowledge-grounded Dialog System
2. RepPoints-x-Libra-R-CNN-x-Transformer-self-attention
3. Small Sample Learning
4. UTrack
5. NoQueue

Knowledge-grounded Dialog System

Description: Contributed to the implementation of knowledge-grounded dialog system submitted for Dialog Systems Technology Challenge 9 (DSTC9). Top 12 Finalists. Published in DSTC9 Workshop at AAAI21.
Paper: arXiv
Project Code: Github

RepPoints-x-Libra-R-CNN-x-Transformer-self-attention

Description: This project builds upon the RepPoints model by Yang et. al. We balance the training of the model using Libra R-CNN and then further improve the performance using Transformer Attention. We also implement our KQRAttention mechanism to improve the inference speed of the model.
Project Code: Github

Small Sample Learning

Food Classification from a small training sample. Project for Huawei AI Cloud Developer Challenge 2019 (Top 10 Finalists).
Project Code: Github

UTrack

Android mobile application to keep track of university applications. Features multi-device data synchronization.
Project Code: Github

NoQueue

Django based web-app to schedule food pickup from restaurants.
Project Code: Github

_{^{Note: The project list might not be the latest. Please check Github.}}