Minh Hoai

35

Papers

27

Total Citations

Papers (35)

Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers

Count What You Want: Exemplar Identification and Few-Shot Counting of Human Actions in the Wild

Few-shot Personalized Scanpath Prediction

Blur2Blur: Blur Conversion for Unsupervised Image Deblurring on Unknown Domains

Error Detection in Egocentric Procedural Task Videos

HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances

HOIST-Former: Hand-held Objects Identification Segmentation and Tracking in the Wild

Improving Human Action Recognition by Non-Action Classification

Region Ranking SVM for Image Classification

Noisy Label Recovery for Shadow Detection in Unfamiliar Domains

Good View Hunting: Learning Photo Composition From Dense View Pairs

Pulling Actions out of Context: Explicit Separation for Effective Combination

GIF2Video: Color Dequantization and Temporal Interpolation of GIF Images

Active Vision for Early Recognition of Human Actions

Predicting Goal-Directed Human Attention Using Inverse Reinforcement Learning

Learning Visual Emotion Representations From Web Data

Learning To Count Everything

Progressive Semantic Segmentation

Dictionary-Guided Scene Text Recognition

Explore Image Deblurring via Encoded Blur Kernel Space

Lipstick Ain't Enough: Beyond Color Matching for In-the-Wild Makeup Transfer

Forward Propagation, Backward Regression, and Pose Association for Hand Tracking in the Wild

Whose Hands Are These? Hand Detection and Hand-Body Association in the Wild

Object Detection With Self-Supervised Scene Adaptation

HyperCUT: Video Sequence From a Single Blurry Image Using Unsupervised Ordering

Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention

Leave-One-Out Kernel Optimization for Shadow Detection

Shadow Detection With Conditional Generative Adversarial Networks

Contextual Attention for Hand Detection in the Wild

Toward Realistic Single-View 3D Object Reconstruction With Unsupervised Learning From Multiple Images

Interactive Class-Agnostic Object Counting

Target-Absent Human Attention

Few-Shot Object Counting and Detection

Multi-view Gaze Target Estimation

Region-Level Data Attribution for Text-to-Image Generative Models