Chengjie Wang

75

Papers

359

Total Citations

Papers (75)

Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detection

A Diffusion-Based Framework for Multi-Class Anomaly Detection

FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis

PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning

Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detection

LLaVA-KD: A Framework of Distilling Multimodal Large Language Models

Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation

FRIH: Fine-Grained Region-Aware Image Harmonization

MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection

Beyond Prototypes: Semantic Anchor Regularization for Better Representation Learning

VTON-HandFit: Virtual Try-on for Arbitrary Hand Pose Guided by Hand Priors Embedding

LORS: Low-rank Residual Structure for Parameter-Efficient Network Stacking

CustAny: Customizing Anything from A Single Example

Learning by Analogy: Reliable Supervision From Transformations for Unsupervised Optical Flow Estimation

Learning Salient Boundary Feature for Anchor-free Temporal Action Localization

Learning Dynamic Alignment via Meta-Filter for Few-Shot Learning

Learning To Restore Hazy Video: A New Real-World Dataset and a New Method

Learning To Aggregate and Personalize 3D Face From In-the-Wild Photo Collection

Learning To Restore 3D Face From In-the-Wild Degraded Images

Ranking Distance Calibration for Cross-Domain Few-Shot Learning

Learning To Memorize Feature Hallucination for One-Shot Image Generation

Surface Representation for Point Clouds

En-Compactness: Self-Distillation Embedding & Contrastive Generation for Generalized Zero-Shot Learning

ISDNet: Integrating Shallow and Deep Networks for Efficient Ultra-High Resolution Segmentation

Class-Aware Contrastive Semi-Supervised Learning

IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation

Learning Distinctive Margin Toward Active Domain Adaptation

Blind Face Restoration via Integrating Face Shape and Generative Priors

Physically-Guided Disentangled Implicit Rendering for 3D Face Modeling

Adaptive Assignment for Geometry Aware Local Feature Matching

Learning With Noisy Labels via Self-Supervised Adversarial Noisy Masking

Learning From Noisy Labels With Decoupled Meta Label Purifier

Multi-Centroid Task Descriptor for Dynamic Class Incremental Inference

Multimodal Industrial Anomaly Detection via Hybrid Fusion

Learning To Measure the Point Cloud Reconstruction Loss in a Representation Space

Better "CMOS" Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution

MixTeacher: Mining Promising Labels With Mixed Scale Teacher for Semi-Supervised Object Detection

High-Fidelity Generalized Emotional Talking Face Generation With Multi-Modal Emotion Space Learning

Learning Neural Proto-Face Field for Disentangled 3D Face Modeling in the Wild

Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework

Uniformity in Heterogeneity: Diving Deep Into Count Interval Partition for Crowd Counting

Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model Adaption

Instance and Category Supervision are Alternate Learners for Continual Learning

Towards Universal Dataset Distillation via Task-Driven Diffusion

Learning Versatile 3D Shape Generation with Improved Auto-regressive Models

Remembering Normality: Memory-guided Knowledge Distillation for Unsupervised Anomaly Detection

Transferable Decoding with Visual Entities for Zero-Shot Image Captioning

Learning Global-aware Kernel for Image Harmonization

Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking

Temporal Distinct Representation Learning for Action Recognition

SSCGAN: Facial Attribute Editing via Style Skip Connections

Adversarial Semantic Data Augmentation for Human Pose Estimation

SeedFormer: Patch Seeds Based Point Cloud Completion with Upsample Transformer

Designing One Unified Framework for High-Fidelity Face Reenactment and Swapping

ColorFormer: Image Colorization via Color Memory Assisted Hybrid-Attention Transformer

StyleFace: Towards Identity-Disentangled Face Generation on Megapixels

tSF: Transformer-Based Semantic Filter for Few-Shot Learning

Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation

Rethinking Mobile Block for Efficient Attention-based Models

SVFR: A Unified Framework for Generalized Video Face Restoration

Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editing

Real-IAD D³: A Real-World 2D/Pseudo-3D/3D Dataset for Industrial Anomaly Detection

Sonic: Shifting Focus to Global Audio Perception in Portrait Animation

MobileMamba: Lightweight Multi-Receptive Visual Mamba Network

OracleFusion: Assisting the Decipherment of Oracle Bone Script with Structurally Constrained Semantic Typography

ID-Sculpt: ID-aware 3D Head Generation from Single In-the-wild Portrait Image

MatchDet: A Collaborative Framework for Image Matching and Object Detection

Unsupervised Continual Anomaly Detection with Contrastively-Learned Prompt

AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model

PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization

DSFD: Dual Shot Face Detector

Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model

SoftPatch: Unsupervised Anomaly Detection with Noisy Data

Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation

Real3D-AD: A Dataset of Point Cloud Anomaly Detection