Xiaowei Hu

papers

4,829

total citations

papers (24)

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

ECCV 2020arXiv

2,159

citations

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

CVPR 2023arXiv

994

citations

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

NEURIPS 2022arXiv

citations

K-LITE: Learning Transferable Visual Models with External Knowledge

NEURIPS 2022arXiv

citations

Instance Shadow Detection

CVPR 2020arXiv

citations

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

ICML 2024arXiv

citations

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

CVPR 2023arXiv

citations

IDRNet: Intervention-Driven Relation Network for Semantic Segmentation

NEURIPS 2023arXiv

citations

Learning Shadow Correspondence for Video Shadow Detection

ECCV 2022arXiv

citations

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

NEURIPS 2022arXiv

citations

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

ICCV 2023arXiv

citations

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

ECCV 2024arXiv

citations

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

AAAI 2024

citations

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

CVPR 2023

citations

EchoTraffic: Enhancing Traffic Anomaly Understanding with Audio-Visual Insights

CVPR 2025

citations

Fast Image Super-Resolution via Consistency Rectified Flow

ICCV 2025

citations

Single-Stage Instance Shadow Detection With Bidirectional Relation Learning

CVPR 2021

citations

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

CVPR 2023

citations

Xiaowei Hu

papers (24)

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

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

GLIPv2: Unifying Localization and Vision-Language Understanding

Scaling Up Vision-Language Pre-Training for Image Captioning

VinVL: Revisiting Visual Representations in Vision-Language Models

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

Injecting Semantic Concepts Into End-to-End Image Captioning

Compressing Visual-Linguistic Model via Knowledge Distillation

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

K-LITE: Learning Transferable Visual Models with External Knowledge

Instance Shadow Detection

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

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

IDRNet: Intervention-Driven Relation Network for Semantic Segmentation

Learning Shadow Correspondence for Video Shadow Detection

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

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

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

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

EchoTraffic: Enhancing Traffic Anomaly Understanding with Audio-Visual Insights

Fast Image Super-Resolution via Consistency Rectified Flow

Single-Stage Instance Shadow Detection With Bidirectional Relation Learning

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

papers (24)

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

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

GLIPv2: Unifying Localization and Vision-Language Understanding

Scaling Up Vision-Language Pre-Training for Image Captioning

VinVL: Revisiting Visual Representations in Vision-Language Models

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

Injecting Semantic Concepts Into End-to-End Image Captioning

Compressing Visual-Linguistic Model via Knowledge Distillation

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

K-LITE: Learning Transferable Visual Models with External Knowledge

Instance Shadow Detection

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

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

IDRNet: Intervention-Driven Relation Network for Semantic Segmentation

Learning Shadow Correspondence for Video Shadow Detection

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

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

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

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

EchoTraffic: Enhancing Traffic Anomaly Understanding with Audio-Visual Insights

Fast Image Super-Resolution via Consistency Rectified Flow

Single-Stage Instance Shadow Detection With Bidirectional Relation Learning

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