Ngo Hoang Bach

PhD Student, Computer Science · UNC Charlotte (Spring 2027)

I'm a computer-vision researcher focused on trustworthy computer vision. I'm an incoming PhD student at UNC Charlotte, working with Prof. Hieu Le on calibration, interpretability, and robustness to distribution shift. Currently based in Ho Chi Minh City, Vietnam.

Email / GitHub / Scholar / LinkedIn / CV

News

01

Sep 2026 Learning to Generate Multiple Objects from Dense and Occluded Layouts accepted at NeurIPS 2026. arXiv · Project page
Aug 2026 Admitted to the PhD program in Computer Science at UNC Charlotte (Spring 2027), joining Prof. Hieu Le.
Dec 2024 CrossPAR: Enhancing Pedestrian Attribute Recognition accepted at ACCV 2024.
Jun 2024 Divide and Conquer Boosting for Enhanced Traffic Safety Description and Analysis with Large Vision Language Model accepted at the CVPR Workshop (AI City Challenge). Paper · Pipeline
Jun 2023 Comprehensive Visual Features for Vehicle Retrieval accepted at the CVPR Workshop (AI City Challenge).

Publications

02

Learning to Generate Multiple Objects from Dense and Occluded Layouts

Bach-Hoang Ngo, Si-Tri Ngo, Hieu Le, Trung-Nghia Le

NeurIPS 2026

Arxiv Project

diffusion models image generation layout control occlusion

Text → Image retrieval

An Efficient Framework for Text-to-Image Retrieval using Complete Feature Aggregation and Cross-Knowledge Conversion

Bach-Hoang Ngo, Minh-Huy An, Khanh-Nguyen Tran Anh, Minh-Duc Bui, Quoc-Viet Dinh

Pattern Analysis and Applications 28 (4), 176 — 2025

Springer DOI

text-to-image retrieval feature aggregation knowledge distillation

CrossPAR architecture diagram

CrossPAR: Enhancing Pedestrian Attribute Recognition with Vision-Language Fusion and Human-Centric Pre-Training

Bach-Hoang Ngo, Si-Tri Ngo, Phu-Duc Le, Quang-Minh Phan, Minh-Triet Tran

ACCV 2024

PDF Springer

pedestrian attributes vision-language person recognition

Divide and Conquer pipeline overview

Divide and Conquer Boosting for Enhanced Traffic Safety Description and Analysis with Large Vision Language Model

Khai-Trinh Xuan, Khoi-Nguyen Nguyen, Bach-Hoang Ngo, Vu-Dinh Xuan, Minh-Hung An, Quang-Vinh Dinh

CVPR Workshop (AI City Challenge) 2024

PDF CVF

traffic safety vision-language models accident analysis

Vehicle retrieval architecture diagram

Comprehensive Visual Features and Pseudo Labeling for Robust Natural Language-Based Vehicle Retrieval

Bach-Hoang Ngo, Dat-Thanh Nguyen, Nhi-Thien Do-Tran

CVPR Workshop (AI City Challenge) 2023

PDF Code

vehicle retrieval re-identification metric learning

Education

03

2027 —

PhD, Computer Science

UNC Charlotte

Incoming Spring 2027. Advisor: Prof. Hieu Le.
Research focus: trustworthy computer vision — calibration, interpretability, and robustness to distribution shift.

2022 — 2026

B.S., Computer Science

University of Science, VNU-HCM · APCS Program

Advanced Program in Computer Science (APCS).
Focus on computer vision and machine learning. First-author publications at CVPR Workshops, ACCV, NeurIPS, and Springer Pattern Analysis and Applications.

2023

Research & Mentorship Lead

GDGoC — HCMUS

Directed student-led research projects in computer vision and ML.
Organized reading groups, workshops, and mentored junior researchers on their first papers.

Contact

04

The best way to reach me is by email. I am happy to discuss research collaborations, paper reviews, mentoring, or anything related to trustworthy computer vision.

nlmbao2015@gmail.com