Yun Fu

67

Papers

173

Total Citations

Papers (67)

Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection

Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering

Accessing Vision Foundation Models via ImageNet-1K

VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models

NeurIPS 2025arXiv

Outlier-Aware Post-Training Quantization for Image Super-Resolution

Scale-Free Graph-Language Models

Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement

OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning Denoising

Bilinear Heterogeneous Information Machine for RGB-D Action Recognition

Deep Sequential Context Networks for Action Prediction

Low-Rank Embedded Ensemble Semantic Dictionary for Zero-Shot Learning

Residual Dense Network for Image Super-Resolution

Tell Me Where to Look: Guided Attention Inference Network

Large Scale Incremental Learning

Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution

TDAN: Temporally-Deformable Alignment Network for Video Super-Resolution

HyperSTAR: Task-Aware Hyperparameters for Deep Networks

Cross-Domain Document Object Detection: Benchmark Suite and Method

Screencast Tutorial Video Understanding

Rethinking Classification and Localization for Object Detection

Adversarial Feature Hallucination Networks for Few-Shot Learning

MR Image Super-Resolution With Squeeze and Excitation Reasoning Attention Network

Learning To Learn Across Diverse Data Biases in Deep Face Recognition

Adaptive Trajectory Prediction via Transferable GNN

Towards Layer-Wise Image Vectorization

Frame Flexible Network

Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction

NeRFInvertor: High Fidelity NeRF-GAN Inversion for Single-Shot Real Image Animation

Real-Time Neural Light Field on Mobile Devices

Q: How To Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!

Temporal Subspace Clustering for Human Motion Segmentation

Attention Bridging Network for Knowledge Transfer

Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective

Visual Semantic Reasoning for Image-Text Matching

Multimodal Style Transfer via Graph Cuts

Generative Multi-View Human Action Recognition

Laplace Landmark Localization

Context Reasoning Attention Network for Image Super-Resolution

ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation

Efficient Converted Spiking Neural Network for 3D and 2D Classification

GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation

Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution

BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation

Texture Hallucination for Large-Factor Painting Super-Resolution

Generative View-Correlation Adaptation for Semi-Supervised Multi-View Learning

LatticeNet: Towards Lightweight Image Super-resolution with Lattice Block

R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis

Single-Stream Multi-level Alignment for Vision-Language Pretraining

Matching on Balanced Nonlinear Representations for Treatment Effects Estimation

Dynamic High-Pass Filtering and Multi-Spectral Attention for Image Super-Resolution

REGEN: Learning Compact Video Embedding with (Re-)Generative Decoder

AdaFormer: Efficient Transformer with Adaptive Token Sparsification for Image Super-resolution

SkipDiff: Adaptive Skip Diffusion Model for High-Fidelity Perceptual Image Super-resolution

Rewrite the Stars

Adapting to Length Shift: FlexiLength Network for Trajectory Prediction

PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation

Neural Sparse Representation for Image Restoration

Learning to Mutate with Hypergradient Guided Population

Aligned Structured Sparsity Learning for Efficient Image Super-Resolution

Slow Learning and Fast Inference: Efficient Graph Similarity Computation via Knowledge Distillation

Parameter-Efficient Masking Networks

What Makes a "Good" Data Augmentation in Knowledge Distillation - A Statistical Perspective

Look More but Care Less in Video Recognition

SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds

Latent Graph Inference with Limited Supervision

UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild

Exploring Question Decomposition for Zero-Shot VQA