Yunhong Wang

papers

1,759

total citations

papers (29)

SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection

ICCV 2023arXiv

citations

Understanding Heterophily for Graph Neural Networks

ICML 2024arXiv

citations

Leveraging Predicate and Triplet Learning for Scene Graph Generation

CVPR 2024arXiv

citations

AGS: Affordable and Generalizable Substitute Training for Transferable Adversarial Attack

AAAI 2024

citations

GeoBEV: Learning Geometric BEV Representation for Multi-view 3D Object Detection

AAAI 2025arXiv

citations

Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation for Anomaly Detection

ICCV 2023arXiv

citations

DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection

ICML 2024arXiv

citations

FSD-BEV: Foreground Self-Distillation for Multi-view 3D Object Detection

ECCV 2024arXiv

citations

APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers

CVPR 2025arXiv

citations

OpenRSD: Towards Open-prompts for Object Detection in Remote Sensing Images

ICCV 2025arXiv

citations

FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation

CVPR 2025arXiv

citations

SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking

CVPR 2025arXiv

citations

TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models

AAAI 2025arXiv

citations

MutDet: Mutually Optimizing Pre-training for Remote Sensing Object Detection

ECCV 2024arXiv

citations

ActiveDC: Distribution Calibration for Active Finetuning

CVPR 2024arXiv

citations

Cross-View Gait Recognition With Deep Universal Linear Embeddings

CVPR 2021

citations

SeriesBench: A Benchmark for Narrative-Driven Drama Series Understanding

CVPR 2025arXiv

citations

Unified Knowledge Maintenance Pruning and Progressive Recovery with Weight Recalling for Large Vision-Language Models

AAAI 2025

citations

Multi-modal Deepfake Detection via Multi-task Audio-Visual Prompt Learning

AAAI 2025

citations

Lagrange Motion Analysis and View Embeddings for Improved Gait Recognition

CVPR 2022

citations

Yunhong Wang

papers (29)

Multi-Scale Positive Sample Refinement for Few-Shot Object Detection

STMTrack: Template-Free Visual Tracking With Space-Time Memory Networks

Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation

Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast

Learning Discriminative Representations for Skeleton Based Action Recognition

Denoising Diffusion Autoencoders are Unified Self-supervised Learners

Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles

HIPTrack: Visual Tracking with Historical Prompts

Bi-GCN: Binary Graph Convolutional Network

SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection

Understanding Heterophily for Graph Neural Networks

Leveraging Predicate and Triplet Learning for Scene Graph Generation

AGS: Affordable and Generalizable Substitute Training for Transferable Adversarial Attack

GeoBEV: Learning Geometric BEV Representation for Multi-view 3D Object Detection

Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation for Anomaly Detection

DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection

FSD-BEV: Foreground Self-Distillation for Multi-view 3D Object Detection

APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers

OpenRSD: Towards Open-prompts for Object Detection in Remote Sensing Images

FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation

SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking

TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models

MutDet: Mutually Optimizing Pre-training for Remote Sensing Object Detection

ActiveDC: Distribution Calibration for Active Finetuning

Cross-View Gait Recognition With Deep Universal Linear Embeddings

SeriesBench: A Benchmark for Narrative-Driven Drama Series Understanding

Unified Knowledge Maintenance Pruning and Progressive Recovery with Weight Recalling for Large Vision-Language Models

Multi-modal Deepfake Detection via Multi-task Audio-Visual Prompt Learning

Lagrange Motion Analysis and View Embeddings for Improved Gait Recognition

papers (29)

Multi-Scale Positive Sample Refinement for Few-Shot Object Detection

STMTrack: Template-Free Visual Tracking With Space-Time Memory Networks

Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation

Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast

Learning Discriminative Representations for Skeleton Based Action Recognition

Denoising Diffusion Autoencoders are Unified Self-supervised Learners

Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles

HIPTrack: Visual Tracking with Historical Prompts

Bi-GCN: Binary Graph Convolutional Network

SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection

Understanding Heterophily for Graph Neural Networks

Leveraging Predicate and Triplet Learning for Scene Graph Generation

AGS: Affordable and Generalizable Substitute Training for Transferable Adversarial Attack

GeoBEV: Learning Geometric BEV Representation for Multi-view 3D Object Detection

Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation for Anomaly Detection

DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection

FSD-BEV: Foreground Self-Distillation for Multi-view 3D Object Detection

APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers

OpenRSD: Towards Open-prompts for Object Detection in Remote Sensing Images

FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation

SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking

TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models

MutDet: Mutually Optimizing Pre-training for Remote Sensing Object Detection

ActiveDC: Distribution Calibration for Active Finetuning

Cross-View Gait Recognition With Deep Universal Linear Embeddings

SeriesBench: A Benchmark for Narrative-Driven Drama Series Understanding

Unified Knowledge Maintenance Pruning and Progressive Recovery with Weight Recalling for Large Vision-Language Models

Multi-modal Deepfake Detection via Multi-task Audio-Visual Prompt Learning

Lagrange Motion Analysis and View Embeddings for Improved Gait Recognition