Hi,
I am a Ph.D. candidate at Khoury College of Computer Sciences, Northeastern University, advised by Prof. Ehsan Elhamifar.
I received my B.S. from University of Sciences (Viet Nam) where I was fortunate to study in Advanced Program in Computer Science.
If you are interested in my research or collaboration, I can be reached via:
My research interests lie in significantly reducing the amount of annotations needed to train deep learning systems for visual recognition, detection and segmentation tasks.
Specifically, I design methods that decompose complex concepts into primitive components that can be combined to enable learning with few or zero training samples, with missing annotations and with weak supervision.
Research Areas:
I am currently working on:
Compositional Learning
is accepted at neurIPS 2020. Code is available on Github.Self-Supervised Multi-Task Procedure Learning from Instructional Videos
is accepted at ECCV 2020. Code is available on Github.
[Supplementary Materials] [Slide] ![]() |
Compositional Zero-Shot Learning via Fine-Grained Dense Feature Composition NeurIPS 2020
|
![]() |
Self-Supervised Multi-Task Procedure Learning from Instructional Videos ECCV 2020
|
|
Active Metasurfaces Design by Conditional Generative Adversarial Networks International Conference on Metamaterials, Photonic Crystals and Plasmonics, 2020 |
[Supplementary Materials] [Slide] ![]() |
A Shared Multi-Attention Framework for Multi-Label Zero-Shot Learning CVPR 2020 Oral Presentation
|
[Supplementary Materials] [Slide] ![]() |
Fine-Grained Generalized Zero-Shot Learning via Dense Attribute-Based Attention CVPR 2020
|
[Supplementary Materials] [Slide] ![]() |
Interactive Multi-Label CNN Learning with Partial Labels CVPR 2020
|
![]() |
Seeing Many Unseen Labels via Shared Multi-Attention Models ICCVW 2019 Workshop on Multi-Discipline Approach for Learning Concepts - Zero-Shot, One-Shot, Few-Shot and Beyond |
I am always proud of serving the research community as: