Xiaoyu Wang

Affiliations

HKUST

papers

538

total citations

papers (20)

Towards Semi-Supervised Deep Facial Expression Recognition With an Adaptive Confidence Margin

CVPR 2022arXiv

citations

Robust Partial Matching for Person Search in the Wild

CVPR 2020arXiv

citations

ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer

ECCV 2022arXiv

citations

NAR-Former: Neural Architecture Representation Learning Towards Holistic Attributes Prediction

CVPR 2023arXiv

citations

SynFog: A Photo-realistic Synthetic Fog Dataset based on End-to-end Imaging Simulation for Advancing Real-World Defogging in Autonomous Driving

CVPR 2024arXiv

citations

Fcaformer: Forward Cross Attention in Hybrid Vision Transformer

ICCV 2023arXiv

citations

ParCNetV2: Oversized Kernel with Enhanced Attention

ICCV 2023arXiv

citations

Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient Noise

ICLR 2024arXiv

citations

CoPRA: Bridging Cross-domain Pretrained Sequence Models with Complex Structures for Protein-RNA Binding Affinity Prediction

AAAI 2025arXiv

citations

Connecting Compression Spaces with Transformer for Approximate Nearest Neighbor Search

ECCV 2022arXiv

citations

NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning

NEURIPS 2023arXiv

citations

Decentralized Federated Learning with Model Caching on Mobile Agents

AAAI 2025arXiv

citations

Accelerating Deep Learning with Millions of Classes

ECCV 2020

citations

Unleashing the Full Potential of Product Quantization for Large-Scale Image Retrieval

NEURIPS 2023

citations

Xiaoyu Wang

Affiliations

papers (20)

Towards Semi-Supervised Deep Facial Expression Recognition With an Adaptive Confidence Margin

Robust Partial Matching for Person Search in the Wild

ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer

All-to-Key Attention for Arbitrary Style Transfer

DynaFed: Tackling Client Data Heterogeneity With Global Dynamics

Removing Adversarial Noise in Class Activation Feature Space

Boosting Weakly-Supervised Temporal Action Localization With Text Information

On the Convergence of Step Decay Step-Size for Stochastic Optimization

A Simple and Effective Framework for Pairwise Deep Metric Learning

NAR-Former: Neural Architecture Representation Learning Towards Holistic Attributes Prediction

SynFog: A Photo-realistic Synthetic Fog Dataset based on End-to-end Imaging Simulation for Advancing Real-World Defogging in Autonomous Driving

Fcaformer: Forward Cross Attention in Hybrid Vision Transformer

ParCNetV2: Oversized Kernel with Enhanced Attention

Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient Noise

CoPRA: Bridging Cross-domain Pretrained Sequence Models with Complex Structures for Protein-RNA Binding Affinity Prediction

Connecting Compression Spaces with Transformer for Approximate Nearest Neighbor Search

NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning

Decentralized Federated Learning with Model Caching on Mobile Agents

Accelerating Deep Learning with Millions of Classes

Unleashing the Full Potential of Product Quantization for Large-Scale Image Retrieval

papers (20)

Towards Semi-Supervised Deep Facial Expression Recognition With an Adaptive Confidence Margin

Robust Partial Matching for Person Search in the Wild

ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer

All-to-Key Attention for Arbitrary Style Transfer

DynaFed: Tackling Client Data Heterogeneity With Global Dynamics

Removing Adversarial Noise in Class Activation Feature Space

Boosting Weakly-Supervised Temporal Action Localization With Text Information

On the Convergence of Step Decay Step-Size for Stochastic Optimization

A Simple and Effective Framework for Pairwise Deep Metric Learning

NAR-Former: Neural Architecture Representation Learning Towards Holistic Attributes Prediction

SynFog: A Photo-realistic Synthetic Fog Dataset based on End-to-end Imaging Simulation for Advancing Real-World Defogging in Autonomous Driving

Fcaformer: Forward Cross Attention in Hybrid Vision Transformer

ParCNetV2: Oversized Kernel with Enhanced Attention

Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient Noise

CoPRA: Bridging Cross-domain Pretrained Sequence Models with Complex Structures for Protein-RNA Binding Affinity Prediction

Connecting Compression Spaces with Transformer for Approximate Nearest Neighbor Search

NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning

Decentralized Federated Learning with Model Caching on Mobile Agents

Accelerating Deep Learning with Millions of Classes

Unleashing the Full Potential of Product Quantization for Large-Scale Image Retrieval