Home | People | Research | Publications | Demos |
News | Jobs |
Prospective
Students |
About | Internal |
|
|
|||||||
I am a PhD candidate at UC San Diego, advised by Professor Nuno Vasconcelos. Prior to joining UCSD, I received the BEng in Electronic Engineering at the Chinese University of Hong Kong in 2017. My research centers around building reliable computer vision systems under various forms of dataset and model bias. Specifically, I work on developing bias mitigation techniques for data and models, applying them to challenging vision problems such as temporal video understanding and multimodal learning from visual, text and audio modalities.
|
SViTT: Temporal Learning of Sparse Video-Text Transformers |
|
VALHALLA: Visual Hallucination for Machine Translation |
|
Improving Video Model Transfer with Dynamic Representation Learning |
|
BEV-Net: Assessing Social Distancing Compliance by Joint People Localization and Geometric Reasoning |
|
Learning Representations from Audio-Visual Spatial Alignment |
|
Background Data Resampling for Outlier-Aware Classification |
|
REPAIR: Removing Representation Bias by Dataset Resampling |
|
RESOUND: Towards Action Recognition without Representation Bias |
|
|||
|
Intel Labs |
Summer 2022 |
|
MIT-IBM Watson AI Lab |
Summer 2021 |
|
University of California, San Diego |
2018–Present |
©
SVCL