Qilong Wang

papers

6,207

total citations

papers (19)

ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

CVPR 2020arXiv

5,378

citations

Neural Blind Deconvolution Using Deep Priors

CVPR 2020arXiv

313

citations

Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification

CVPR 2022arXiv

233

citations

What Deep CNNs Benefit From Global Covariance Pooling: An Optimization Perspective

CVPR 2020arXiv

citations

AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning

CVPR 2024arXiv

citations

Tuning Pre-trained Model via Moment Probing

ICCV 2023arXiv

citations

Generative Inbetweening through Frame-wise Conditions-Driven Video Generation

CVPR 2025arXiv

citations

Integrating Visual Interpretation and Linguistic Reasoning for Geometric Problem Solving

ICCV 2025

citations

TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognition

CVPR 2025arXiv

citations

DALIP: Distribution Alignment-based Language-Image Pre-Training for Domain-Specific Data

ICCV 2025arXiv

citations

CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification

CVPR 2025arXiv

citations

DropCov: A Simple yet Effective Method for Improving Deep Architectures

NEURIPS 2022

citations

ImagineFSL: Self-Supervised Pretraining Matters on Imagined Base Set for VLM-based Few-shot Learning

CVPR 2025

citations

Unknown Text Learning for CLIP-based Few-Shot Open-set Recognition

ICCV 2025

citations

Decoupled Multi-Predictor Optimization for Inference-Efficient Model Tuning

ICCV 2025arXiv

citations

Reliable and Interpretable Personalized Federated Learning

CVPR 2023

citations

Qilong Wang

papers (19)

ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

Neural Blind Deconvolution Using Deep Priors

Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification

Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark

Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters

Temporal-attentive Covariance Pooling Networks for Video Recognition

What Deep CNNs Benefit From Global Covariance Pooling: An Optimization Perspective

AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning

Tuning Pre-trained Model via Moment Probing

Generative Inbetweening through Frame-wise Conditions-Driven Video Generation

Integrating Visual Interpretation and Linguistic Reasoning for Geometric Problem Solving

TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognition

DALIP: Distribution Alignment-based Language-Image Pre-Training for Domain-Specific Data

CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification

DropCov: A Simple yet Effective Method for Improving Deep Architectures

ImagineFSL: Self-Supervised Pretraining Matters on Imagined Base Set for VLM-based Few-shot Learning

Unknown Text Learning for CLIP-based Few-Shot Open-set Recognition

Decoupled Multi-Predictor Optimization for Inference-Efficient Model Tuning

Reliable and Interpretable Personalized Federated Learning

papers (19)

ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

Neural Blind Deconvolution Using Deep Priors

Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification

Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark

Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters

Temporal-attentive Covariance Pooling Networks for Video Recognition

What Deep CNNs Benefit From Global Covariance Pooling: An Optimization Perspective

AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning

Tuning Pre-trained Model via Moment Probing

Generative Inbetweening through Frame-wise Conditions-Driven Video Generation

Integrating Visual Interpretation and Linguistic Reasoning for Geometric Problem Solving

TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognition

DALIP: Distribution Alignment-based Language-Image Pre-Training for Domain-Specific Data

CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification

DropCov: A Simple yet Effective Method for Improving Deep Architectures

ImagineFSL: Self-Supervised Pretraining Matters on Imagined Base Set for VLM-based Few-shot Learning

Unknown Text Learning for CLIP-based Few-Shot Open-set Recognition

Decoupled Multi-Predictor Optimization for Inference-Efficient Model Tuning

Reliable and Interpretable Personalized Federated Learning