Machine learning for image processing

DPTNet: A Dual-Path Transformer Architecture for Scene Text Detection

A parallel attention mechanism for image manipulation detection and localization

ScaleMix: Intra- and inter-layer multiscale feature combination for change detection

Depth Estimation for a Single Omnidirectional Image with Reversed-gradient Warming-up Thresholds Discriminator

A Physically Explainable Framework for Human-Related Anomaly Detection

HIERARCHICAL TRANSFORMER FOR MULTI-LABEL TRAILER GENRE CLASSIFICATION

PCSalMix: Gradient Saliency-based Mix Augmentation for Point Cloud Classification

Improving Occluded Human Pose Estimation via Linked Joints

SEMI-SUPERVISED SEMANTIC SEGMENTATION WITH STRUCTURED OUTPUT SPACE ADAPTION

PRRD: PIXEL-REGION RELATION DISTILLATION FOR EFFICIENT SEMANTIC SEGMENTATION

Two-stream Decoder Feature Normality Estimating Network for Industrial Anomaly Detection

Sample-aware Knowledge Distillation for Long-tailed Learning