Jinhui Tang

papers

3,753

total citations

papers (28)

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection

NEURIPS 2020arXiv

1,626

citations

Causal Intervention for Weakly-Supervised Semantic Segmentation

NEURIPS 2020arXiv

521

citations

Feature Pyramid Transformer

ECCV 2020arXiv

295

citations

Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection

CVPR 2021arXiv

295

citations

Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation

ECCV 2022arXiv

citations

Deep Blind Video Super-Resolution

ICCV 2021arXiv

citations

DLGSANet: Lightweight Dynamic Local and Global Self-Attention Networks for Image Super-Resolution

ICCV 2023arXiv

citations

Self-Regulation for Semantic Segmentation

ICCV 2021arXiv

citations

Efficient Visual State Space Model for Image Deblurring

CVPR 2025arXiv

citations

Semantic Scene Completion With Cleaner Self

CVPR 2023arXiv

citations

FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration

ICCV 2025arXiv

citations

MGNet: Learning Correspondences via Multiple Graphs

AAAI 2024arXiv

citations

Vision-centric Token Compression in Large Language Model

NEURIPS 2025arXiv

citations

Unleashing Network Potentials for Semantic Scene Completion

CVPR 2024arXiv

citations

PNP: Robust Learning From Noisy Labels by Probabilistic Noise Prediction

CVPR 2022

citations

Multi-Scale Residual Low-Pass Filter Network for Image Deblurring

ICCV 2023

citations

Multi-scale Activation, Refinement, and Aggregation: Exploring Diverse Cues for Fine-Grained Bird Recognition

AAAI 2025arXiv

citations

Deep Discriminative Spatial and Temporal Network for Efficient Video Deblurring

CVPR 2023

citations

NoiseCtrl: A Sampling-Algorithm-Agnostic Conditional Generation Method for Diffusion Models

CVPR 2025

citations

Exploiting Frequency Dynamics for Enhanced Multimodal Event-based Action Recognition

ICCV 2025

citations

Tensor-aggregated LoRA in Federated Fine-tuning

ICCV 2025

citations

EMControl: Adding Conditional Control to Text-to-Image Diffusion Models via Expectation-Maximization

AAAI 2025

citations

Improving OCR-Based Image Captioning by Incorporating Geometrical Relationship

CVPR 2021

citations

Jinhui Tang

papers (28)

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection

Causal Intervention for Weakly-Supervised Semantic Segmentation

Feature Pyramid Transformer

Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection

Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution

Cascaded Deep Video Deblurring Using Temporal Sharpness Prior

ShuffleMixer: An Efficient ConvNet for Image Super-Resolution

IMAGDressing-v1: Customizable Virtual Dressing

Social Adaptive Module for Weakly-supervised Group Activity Recognition

Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation

Deep Blind Video Super-Resolution

DLGSANet: Lightweight Dynamic Local and Global Self-Attention Networks for Image Super-Resolution

Self-Regulation for Semantic Segmentation

Efficient Visual State Space Model for Image Deblurring

Semantic Scene Completion With Cleaner Self

FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration

MGNet: Learning Correspondences via Multiple Graphs

Vision-centric Token Compression in Large Language Model

Unleashing Network Potentials for Semantic Scene Completion

PNP: Robust Learning From Noisy Labels by Probabilistic Noise Prediction

Multi-Scale Residual Low-Pass Filter Network for Image Deblurring

Multi-scale Activation, Refinement, and Aggregation: Exploring Diverse Cues for Fine-Grained Bird Recognition

Deep Discriminative Spatial and Temporal Network for Efficient Video Deblurring

NoiseCtrl: A Sampling-Algorithm-Agnostic Conditional Generation Method for Diffusion Models

Exploiting Frequency Dynamics for Enhanced Multimodal Event-based Action Recognition

Tensor-aggregated LoRA in Federated Fine-tuning

EMControl: Adding Conditional Control to Text-to-Image Diffusion Models via Expectation-Maximization

Improving OCR-Based Image Captioning by Incorporating Geometrical Relationship

papers (28)

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection

Causal Intervention for Weakly-Supervised Semantic Segmentation

Feature Pyramid Transformer

Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection

Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution

Cascaded Deep Video Deblurring Using Temporal Sharpness Prior

ShuffleMixer: An Efficient ConvNet for Image Super-Resolution

IMAGDressing-v1: Customizable Virtual Dressing

Social Adaptive Module for Weakly-supervised Group Activity Recognition

Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation

Deep Blind Video Super-Resolution

DLGSANet: Lightweight Dynamic Local and Global Self-Attention Networks for Image Super-Resolution

Self-Regulation for Semantic Segmentation

Efficient Visual State Space Model for Image Deblurring

Semantic Scene Completion With Cleaner Self

FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration

MGNet: Learning Correspondences via Multiple Graphs

Vision-centric Token Compression in Large Language Model

Unleashing Network Potentials for Semantic Scene Completion

PNP: Robust Learning From Noisy Labels by Probabilistic Noise Prediction

Multi-Scale Residual Low-Pass Filter Network for Image Deblurring

Multi-scale Activation, Refinement, and Aggregation: Exploring Diverse Cues for Fine-Grained Bird Recognition

Deep Discriminative Spatial and Temporal Network for Efficient Video Deblurring

NoiseCtrl: A Sampling-Algorithm-Agnostic Conditional Generation Method for Diffusion Models

Exploiting Frequency Dynamics for Enhanced Multimodal Event-based Action Recognition

Tensor-aggregated LoRA in Federated Fine-tuning

EMControl: Adding Conditional Control to Text-to-Image Diffusion Models via Expectation-Maximization

Improving OCR-Based Image Captioning by Incorporating Geometrical Relationship