Computer Vision and Image Understanding Lab - VideoAndMovie

Computer Vision and Image Understanding (CVIU) Lab was founded by Dr. Khoa Luu in Fall 2018 after he moved to the University of Arkansas from Carnegie Mellon University, USA. CVIU Lab promotes advanced research in Computer Vision, Deep Learning, Biometrics, Machine Intelligence, and Quantum Machine Learning technologies.

HyperGLM: HyperGraph for Video Scene Graph Generation and Anticipation

5:45

HyperGLM: HyperGraph for Video Scene Graph Generation and Anticipation

Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding

5:21

Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding

CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos

5:26

CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos

EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding

5:01

EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding

HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding

4:26

HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding

Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding

4:29

Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding

Type-to-Track: Retrieve Any Object via Prompt-based Tracking

5:51

Type-to-Track: Retrieve Any Object via Prompt-based Tracking

Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments

4:57

Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments

Micron-BERT: BERT-based Facial Micro-Expression Recognition

3:44

Micron-BERT: BERT-based Facial Micro-Expression Recognition

FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding

5:01

FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding

Vec2Face: Unveil Human Faces from their Blackbox Features in Face Recognition

5:03

Vec2Face: Unveil Human Faces from their Blackbox Features in Face Recognition

The Right to Talk: An Audio-Visual Transformer Approach

5:00

The Right to Talk: An Audio-Visual Transformer Approach

BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation

4:36

BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation

DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition

5:01

DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition