Yunhong Wang

37

Papers

127

Total Citations

Papers (37)

HIPTrack: Visual Tracking with Historical Prompts

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

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

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

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

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

AGS: Affordable and Generalizable Substitute Training for Transferable Adversarial Attack

Leveraging Predicate and Triplet Learning for Scene Graph Generation

ActiveDC: Distribution Calibration for Active Finetuning

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

Understanding Heterophily for Graph Neural Networks

Binary Coding for Partial Action Analysis With Limited Observation Ratios

Zero-Shot Action Recognition With Error-Correcting Output Codes

Fast Person Re-Identification via Cross-Camera Semantic Binary Transformation

Learning Face Age Progression: A Pyramid Architecture of GANs

Attentive Relational Networks for Mapping Images to Scene Graphs

KE-GAN: Knowledge Embedded Generative Adversarial Networks for Semi-Supervised Scene Parsing

Led3D: A Lightweight and Efficient Deep Approach to Recognizing Low-Quality 3D Faces

Adaptive NMS: Refining Pedestrian Detection in a Crowd

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

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

Bi-GCN: Binary Graph Convolutional Network

Cross-View Gait Recognition With Deep Universal Linear Embeddings

Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast

Lagrange Motion Analysis and View Embeddings for Improved Gait Recognition

Learning Discriminative Representations for Skeleton Based Action Recognition

Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation for Anomaly Detection

Denoising Diffusion Autoencoders are Unified Self-supervised Learners

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

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

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

Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles

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

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

SeriesBench: A Benchmark for Narrative-Driven Drama Series Understanding

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

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