Yi Zhang

54

Papers

147

Total Citations

Papers (54)

Point Segment and Count: A Generalized Framework for Object Counting

Concept-Guided Prompt Learning for Generalization in Vision-Language Models

Language Representations Can be What Recommenders Need: Findings and Potentials

DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data

Patient-Level Anatomy Meets Scanning-Level Physics: Personalized Federated Low-Dose CT Denoising Empowered by Large Language Model

CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generation

Enhanced then Progressive Fusion with View Graph for Multi-View Clustering

Correcting Large Language Model Behavior via Influence Function

See Further When Clear: Curriculum Consistency Model

Sample-Level Cross-View Similarity Learning for Incomplete Multi-View Clustering

FocalDreamer: Text-Driven 3D Editing via Focal-Fusion Assembly

Tackling Vision Language Tasks through Learning Inner Monologues

Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology

Exploring Regional Clues in CLIP for Zero-Shot Semantic Segmentation

EasyDrag: Efficient Point-based Manipulation on Diffusion Models

Domain Separation Graph Neural Networks for Saliency Object Ranking

Line-Based Multi-Label Energy Optimization for Fisheye Image Rectification and Calibration

IDR: Self-Supervised Image Denoising via Iterative Data Refinement

A Simple Baseline for Video Restoration With Grouped Spatial-Temporal Shift

Frequency-Modulated Point Cloud Rendering With Easy Editing

Semantics-Enhanced Adversarial Nets for Text-to-Image Synthesis

Salient Object Ranking With Position-Preserved Attention

Rethinking Noise Synthesis and Modeling in Raw Denoising

Localized Simple Multiple Kernel K-Means

3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation

Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification

Learning Shape Primitives via Implicit Convexity Regularization

Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape

The Euclidean Space is Evil: Hyperbolic Attribute Editing for Few-shot Image Generation

Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation

Explicit Occlusion Reasoning for Multi-Person 3D Human Pose Estimation

Learning Degradation Representations for Image Deblurring

Optimal Transport for Label-Efficient Visible-Infrared Person Re-identification

Deep Visual Analogy-Making

Attributive Reasoning for Hallucination Diagnosis of Large Language Models

Large-scale Multi-view Tensor Clustering with Implicit Linear Kernels

Adaptive Parameter Selection for Tuning Vision-Language Models

RAGDiffusion: Faithful Cloth Generation via External Knowledge Assimilation

Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning

DepMGNN: Matrixial Graph Neural Network for Video-based Automatic Depression Assessment

Cross-Modal Few-Shot Learning with Second-Order Neural Ordinary Differential Equations

InstantSticker: Realistic Decal Blending via Disentangled Object Reconstruction

Hawkes-Enhanced Spatial-Temporal Hypergraph Contrastive Learning Based on Criminal Correlations

Spectral Filtering for General Linear Dynamical Systems

Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets

Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality

ICNet: Intra-saliency Correlation Network for Co-Saliency Detection

Measuring and Reducing Model Update Regression in Structured Prediction for NLP

Stability and Generalization of Kernel Clustering: from Single Kernel to Multiple Kernel

Learning threshold neurons via edge of stability

A Unified Conditional Framework for Diffusion-based Image Restoration

Generalization and Equilibrium in Generative Adversarial Nets (GANs)

Stronger Generalization Bounds for Deep Nets via a Compression Approach

Efficient Full-Matrix Adaptive Regularization