Xiaowei Hu

31

Papers

269

Total Citations

Papers (31)

Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection

Towards Real-World Adverse Weather Image Restoration: Enhancing Clearness and Semantics with Vision-Language Models

Semi-supervised TEE Segmentation via Interacting with SAM Equipped with Noise-Resilient Prompting

Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modeling

Richer Convolutional Features for Edge Detection

Deeply Supervised Salient Object Detection With Short Connections

Direction-Aware Spatial Context Features for Shadow Detection

Depth-Attentional Features for Single-Image Rain Removal

Instance Shadow Detection

VinVL: Revisiting Visual Representations in Vision-Language Models

Single-Stage Instance Shadow Detection With Bidirectional Relation Learning

Injecting Semantic Concepts Into End-to-End Image Captioning

Scaling Up Vision-Language Pre-Training for Image Captioning

Matching Is Not Enough: A Two-Stage Framework for Category-Agnostic Pose Estimation

Video Dehazing via a Multi-Range Temporal Alignment Network With Physical Prior

InternImage: Exploring Large-Scale Vision Foundation Models With Deformable Convolutions

Learning Weather-General and Weather-Specific Features for Image Restoration Under Multiple Adverse Weather Conditions

Deep Multi-Model Fusion for Single-Image Dehazing

Mask-ShadowGAN: Learning to Remove Shadows From Unpaired Data

Compressing Visual-Linguistic Model via Knowledge Distillation

SILT: Shadow-Aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels

Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks

Learning Shadow Correspondence for Video Shadow Detection

UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling

EchoTraffic: Enhancing Traffic Anomaly Understanding with Audio-Visual Insights

Fast Image Super-Resolution via Consistency Rectified Flow

NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis

K-LITE: Learning Transferable Visual Models with External Knowledge

GLIPv2: Unifying Localization and Vision-Language Understanding

Sparse2Dense: Learning to Densify 3D Features for 3D Object Detection

IDRNet: Intervention-Driven Relation Network for Semantic Segmentation