Computer Vision and Image Understanding Lab, University of Arkansas

BiMaL

[ICCV'21] BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation

DirecFormer

[CVPR'22] DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition

DyGLIP

[CVPR 2021] DyGLIP: A Dynamic Graph Model with Link Prediction for Accurate Multi-Camera Multiple Object Tracking

FREDOM

[CVPR 2023] FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding

InsectFoundationModel

Insect Foundation AI Model and Dataset for Precision Agriculture

Intraformer

Intraformer: A Transformer based Approach to Unsupervised Long-tail Face, Facial Expression and Visual Recognition

Micron-BERT

[CVPR 2023] Micron-BERT: BERT-based Facial Micro-Expression Recognition

Right2Talk

[ICCV'21] The Right to Talk: An Audio-Visual Transformer Approach

SPARTAN

[CVPRW 2023] SPARTAN: Self-supervised Spatiotemporal Transformers Approach to Group Activity Recognition

Type-to-Track

[NeurIPS 2023] Type-to-Track: Retrieve Any Object via Prompt-based Tracking

uark-cviu/Micron-BERT

[CVPR 2023] Micron-BERT: BERT-based Facial Micro-Expression Recognition

uark-cviu/DyGLIP

[CVPR 2021] DyGLIP: A Dynamic Graph Model with Link Prediction for Accurate Multi-Camera Multiple Object Tracking

uark-cviu/DirecFormer

[CVPR'22] DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition

uark-cviu/Intraformer

Intraformer: A Transformer based Approach to Unsupervised Long-tail Face, Facial Expression and Visual Recognition

uark-cviu/Right2Talk

[ICCV'21] The Right to Talk: An Audio-Visual Transformer Approach

uark-cviu/Type-to-Track

[NeurIPS 2023] Type-to-Track: Retrieve Any Object via Prompt-based Tracking

uark-cviu/FREDOM

[CVPR 2023] FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding

uark-cviu/InsectFoundationModel

Insect Foundation AI Model and Dataset for Precision Agriculture

uark-cviu/ASPIRe

[CVPR 2024] HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding

uark-cviu/BiMaL

[ICCV'21] BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation

uark-cviu/SPARTAN

[CVPRW 2023] SPARTAN: Self-supervised Spatiotemporal Transformers Approach to Group Activity Recognition

uark-cviu/Algonauts2023

uark-cviu/SAGA-TrackNet

Multi-Camera Multi-Object Tracking on the Move via Single-Stage Global Association Approach

uark-cviu/uark-cviu.github.io

uark-cviu/CoMaL

Conditional Maximum Likelihood

uark-cviu/FairCL

uark-cviu/GASG

uark-cviu/QuantumVisualFeatureEncodingRevisited