Match tier
Confirmed
Presence
Current · Arkansas
Last published
2026
Sources
OpenAlex · ORCID
Refreshed
2026-08-06
N
Ngan Le
Affiliation confirmed via AI analysis of OpenAlex, ORCID, and web sources.
Federal Grant PI
Assistant Professor
Faculty Researcher
27 h-index
244 pubs
3,950 cited
Research Areas
Biomedical Subjects
Links
Biography and Research Information
OverviewAI-generated summary
Ngan Le's research focuses on developing trustworthy, robust, and efficient multimodal frameworks for video analytics, particularly addressing challenges related to imperfect data such as limited labels, noise, bias, and unseen data. Her work also investigates real-time applications on edge devices. Dr. Le is proficient in analyzing diverse data modalities, including image, video, point cloud, volumetric data, time series, and remote sensing data, with expertise spanning image processing, scene understanding, multiple object tracking, and behavior analysis.
Her funded research includes a CAREER award from the National Science Foundation (NSF) for "Trustworthy, Robust, and Efficient Multimodal Framework for Video Analytics," totaling $499,556. She also serves as a Co-PI on two NSF Convergence Accelerator grants: "Cultivate IQ - Empowering Regional Food Systems" ($4,998,818) and "Data-driven Agriculture to Bridge Small Farms to Regional Food Supply Chains" ($743,651).
Dr. Le's scholarly contributions are reflected in her h-index of 13 and 384 citations across 36 publications. Her recent publications include work on "SAM3D: Segment Anything Model in Volumetric Medical Images," "Amodal Instance Segmentation with Diffusion Shape Prior Estimation," and "FG-CXR: A Radiologist-Aligned Gaze Dataset for Enhancing Interpretability in Chest X-Ray Report Generation."
Metrics
- h-index: 27
- Publications: 244
- Citations: 3,950
Selected Publications
-
VentVision: A multimodal vision-based system for automated vent-based chick sexing (2026)
-
SSL-MTab: Self-Supervised Distillation for Missing Data in Tabular Prediction Tasks (2026)
-
MiGa: Multi-chicken gait assessment (2026)
-
Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective (2026)
-
DualFit: A Two-Stage Virtual Try-On via Warping and Synthesis (2025)
-
Learning Human Motion with Temporally Conditional Mamba (2025)
-
BiMa: Towards Biases Mitigation for Text-Video Retrieval via Scene Element Guidance (2025)
-
TolerantECG: A Foundation Model for Imperfect Electrocardiogram (2025)
-
MAARTA:Multi-agentic Adaptive Radiology Teaching Assistant (2025)
-
CattleFever: An automated cattle fever estimation system (2025)
-
Robotic-CLIP: Fine-Tuning CLIP on Action Data for Robotic Applications (2025)
-
BroilerTrack: Automatic multi-camera multi-broiler tracking (2025)
-
Land8Fire: A Complete Study on Wildfire Segmentation Through Comprehensive Review, Human-Annotated Multispectral Dataset, and Extensive Benchmarking (2025)
-
Collaborative Integration of AI and Human Expertise to Improve Detection of Chest Radiograph Abnormalities (2025)
-
Facial chick sexing: An automated chick sexing system from chick facial image (2025)
Federal Grants 3 $6,242,025 total
NSF
Co-PI
Dec 2023 - Nov 2026
NSF Convergence Accelerator Track J Phase 2: Cultivate IQ - Empowering Regional Food Systems
NSF
Co-PI
Dec 2022 - Nov 2025
NSF
PI
Sep 2025 - Aug 2030
CAREER: Trustworthy, Robust, and Efficient Multimodal Framework for Video Analytics.
Collaboration Network
Top Collaborators
Kashu Yamazaki
Carnegie Mellon University (US)
12 shared publications
- Spiking Neural Networks and Their Applications: A Review
- Deep reinforcement learning in computer vision: a comprehensive survey
- CLIP-TSA: Clip-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection
- AerialFormer: Multi-Resolution Transformer for Aerial Image Segmentation
- VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning
Showing 5 of 12 shared publications
Viet-Khoa Vo-Ho
University of Arkansas at Fayetteville (US)
11 shared publications
- Spiking Neural Networks and Their Applications: A Review
- CLIP-TSA: Clip-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection
- AOE-Net: Entities Interactions Modeling with Adaptive Attention Mechanism for Temporal Action Proposals Generation
- VLCAP: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning
- Narrow Band Active Contour Attention Model for Medical Segmentation
Showing 5 of 11 shared publications
Khoa Luu
University of Arkansas at Fayetteville
9 shared publications
In database
- Deep reinforcement learning in computer vision: a comprehensive survey
- Non-volume preserving-based fusion to group-level emotion recognition on crowd videos
- VLCAP: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning
- Multi-camera multi-object tracking on the move via single-stage global association approach
- Narrow Band Active Contour Attention Model for Medical Segmentation
Showing 5 of 9 shared publications
Minh–Triet Tran
University of Arkansas at Fayetteville (US)
7 shared publications
- MEGANet: Multi-Scale Edge-Guided Attention Network for Weak Boundary Polyp Segmentation
- AOE-Net: Entities Interactions Modeling with Adaptive Attention Mechanism for Temporal Action Proposals Generation
- EmbryosFormer: Deformable Transformer and Collaborative Encoding-Decoding for Embryos Stage Development Classification
- ABN: Agent-Aware Boundary Networks for Temporal Action Proposal Generation
- Agent-Environment Network for Temporal Action Proposal Generation
Showing 5 of 7 shared publications
Sang Truong
University of Arkansas at Fayetteville (US)
5 shared publications
- sCL-ST: Supervised Contrastive Learning With Semantic Transformations for Multiple Lead ECG Arrhythmia Classification
- AOE-Net: Entities Interactions Modeling with Adaptive Attention Mechanism for Temporal Action Proposals Generation
- VLCAP: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning
- ABN: Agent-Aware Boundary Networks for Temporal Action Proposal Generation
- CarcassFormer: an end-to-end transformer-based framework for simultaneous localization, segmentation and classification of poultry carcass defect
Donald Adjeroh
Donaldson (United States) (US)
5 shared publications
- sCL-ST: Supervised Contrastive Learning With Semantic Transformations for Multiple Lead ECG Arrhythmia Classification
- ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection
- Multimodality Multi-Lead ECG Arrhythmia Classification using Self-Supervised Learning
- FG-CXR: A Radiologist-Aligned Gaze Dataset for Enhancing Interpretability in Chest X-Ray Report Generation
- ItpCtrl-AI: End-to-end interpretable and controllable artificial intelligence by modeling radiologists’ intentions
Trong Thang Pham
University of Arkansas at Fayetteville
5 shared publications
In database
- I-AI: A Controllable & Interpretable AI System for Decoding Radiologists’ Intense Focus for Accurate CXR Diagnoses
- FG-CXR: A Radiologist-Aligned Gaze Dataset for Enhancing Interpretability in Chest X-Ray Report Generation
- GazeSearch: Radiology Findings Search Benchmark
- TolerantECG: A Foundation Model for Imperfect Electrocardiogram
- CattleFever: An automated cattle fever estimation system
Kha Gia Quach
4 shared publications
- Non-volume preserving-based fusion to group-level emotion recognition on crowd videos
- Multi-camera multi-object tracking on the move via single-stage global association approach
- A Multi-task Contextual Atrous Residual Network for Brain Tumor Detection & Segmentation
- LIAAD: Lightweight attentive angular distillation for large-scale age-invariant face recognition
Patel Brijesh
West Virginia University (US)
4 shared publications
- Multi-module Recurrent Convolutional Neural Network with Transformer Encoder for ECG Arrhythmia Classification
- sCL-ST: Supervised Contrastive Learning With Semantic Transformations for Multiple Lead ECG Arrhythmia Classification
- Multimodality Multi-Lead ECG Arrhythmia Classification using Self-Supervised Learning
- FG-CXR: A Radiologist-Aligned Gaze Dataset for Enhancing Interpretability in Chest X-Ray Report Generation
Thinh Phan
University of Arkansas at Fayetteville
4 shared publications
In database
- ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection
- Multimodality Multi-Lead ECG Arrhythmia Classification using Self-Supervised Learning
- FG-CXR: A Radiologist-Aligned Gaze Dataset for Enhancing Interpretability in Chest X-Ray Report Generation
- VentVision: A multimodal vision-based system for automated vent-based chick sexing
Minh Nhat Vu
TU Wien (AT)
4 shared publications
- Open-Vocabulary Affordance Detection in 3D Point Clouds
- Language-Conditioned Affordance-Pose Detection in 3D Point Clouds
- Language-Driven 6-DoF Grasp Detection Using Negative Prompt Guidance
- Lightweight Language-driven Grasp Detection using Conditional Consistency Model
Chi Nhan Duong
3 shared publications
- Non-volume preserving-based fusion to group-level emotion recognition on crowd videos
- Multi-camera multi-object tracking on the move via single-stage global association approach
- LIAAD: Lightweight attentive angular distillation for large-scale age-invariant face recognition
Duc-Quang Vu
National Central University (TW)
3 shared publications
- Teaching Yourself: A Self-Knowledge Distillation Approach to Action Recognition
- (2+1)D Distilled ShuffleNet: A Lightweight Unsupervised Distillation Network for Human Action Recognition
- Deep Learning for Human Action Recognition: A Comprehensive Review
Jia‐Ching Wang
National Central University (TW)
3 shared publications
- Teaching Yourself: A Self-Knowledge Distillation Approach to Action Recognition
- (2+1)D Distilled ShuffleNet: A Lightweight Unsupervised Distillation Network for Human Action Recognition
- Deep Learning for Human Action Recognition: A Comprehensive Review
Thanh-Dat Truong
University of Arkansas at Fayetteville
3 shared publications
In database
- LIAAD: Lightweight attentive angular distillation for large-scale age-invariant face recognition
- Self-Supervised Domain Adaptation in Crowd Counting
- OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation
Similar Researchers
Based on overlapping research topics
Yoshiko Ikebe
University of Arkansas at Fayetteville
Machine Learning Applications
Computer Graphics and Visualization Techniques
Medical Imaging Techniques and Applications
Rupesh Konduru
Southern Arkansas University
Machine Learning Applications
Computer Graphics and Visualization Techniques
Medical Imaging Techniques and Applications
Ahmad Al Shami
Southern Arkansas University
Machine Learning Applications
Computer Graphics and Visualization Techniques
Medical Imaging Techniques and Applications
Kiruthikan Sithamparanathan
University of Arkansas at Fayetteville
Machine Learning Applications
Computer Graphics and Visualization Techniques
Robotics and Sensor-Based Localization
Ryan Socha
University of Arkansas at Fayetteville
Machine Learning Applications
Computer Graphics and Visualization Techniques
Advanced Neural Network Applications
Christian Young
Southern Arkansas University
Machine Learning Applications
Computer Graphics and Visualization Techniques
Medical Imaging Techniques and Applications