Yunchao Wei

73

Papers

93

Total Citations

Papers (73)

Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentation

VideoWorld: Exploring Knowledge Learning from Unlabeled Videos

Region-Adaptive Transform with Segmentation Prior for Image Compression

CoMBO: Conflict Mitigation via Branched Optimization for Class Incremental Segmentation

Dual-view X-ray Detection: Can AI Detect Prohibited Items from Dual-view X-ray Images like Humans?

PreFM: Online Audio-Visual Event Parsing via Predictive Future Modeling

NeurIPS 2025arXiv

Collapsed Language Models Promote Fairness

Attend and Enrich: Enhanced Visual Prompt for Zero-Shot Learning

NTClick: Achieving Precise Interactive Segmentation With Noise-tolerant Clicks

Transferable and Principled Efficiency for Open-Vocabulary Segmentation

Visual Relation Diffusion for Human-Object Interaction Detection

Perceptual Generative Adversarial Networks for Small Object Detection

Deep Self-Taught Learning for Weakly Supervised Object Localization

Object Region Mining With Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach

Adversarial Complementary Learning for Weakly Supervised Object Localization

Left-Right Comparative Recurrent Model for Stereo Matching

Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation

Geometry-Aware Distillation for Indoor Semantic Segmentation

Low-Rank Tensor Completion With a New Tensor Nuclear Norm Induced by Invertible Linear Transforms

Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis

Interactive Object Segmentation With Inside-Outside Guidance

Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation

Memory Aggregation Networks for Efficient Interactive Video Object Segmentation

Referring Image Segmentation via Cross-Modal Progressive Comprehension

Domain Consensus Clustering for Universal Domain Adaptation

VSPW: A Large-scale Dataset for Video Scene Parsing in the Wild

Large-Scale Video Panoptic Segmentation in the Wild: A Benchmark

M5Product: Self-Harmonized Contrastive Learning for E-Commercial Multi-Modal Pretraining

L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation

Learning To Segment Every Referring Object Point by Point

Adversarially Masking Synthetic To Mimic Real: Adaptive Noise Injection for Point Cloud Segmentation Adaptation

Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learning

Learning on Gradients: Generalized Artifacts Representation for GAN-Generated Images Detection

Towards Computational Baby Learning: A Weakly-Supervised Approach for Object Detection

Regional Interactive Image Segmentation Networks

Integral Object Mining via Online Attention Accumulation

SPGNet: Semantic Prediction Guidance for Scene Parsing

Self-Similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-Identification

AINet: Association Implantation for Superpixel Segmentation

Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-Modal Pretraining

Towards Complete Scene and Regular Shape for Distortion Rectification by Curve-Aware Extrapolation

Locating Noise is Halfway Denoising for Semi-Supervised Segmentation

Global Knowledge Calibration for Fast Open-Vocabulary Segmentation

SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model

CTP:Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation

CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentation

Collaborative Video Object Segmentation by Foreground-Background Integration

Content-Consistent Matching for Domain Adaptive Semantic Segmentation

Inter-Image Communication for Weakly Supervised Localization

Slim Scissors: Segmenting Thin Object from Synthetic Background

Instance As Identity: A Generic Online Paradigm for Video Instance Segmentation

SiRi: A Simple Selective Retraining Mechanism for Transformer-Based Visual Grounding

CCNet: Criss-Cross Attention for Semantic Segmentation

CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting

ReCoT: Reflective Self-Correction Training for Mitigating Confirmation Bias in Large Vision-Language Models

CharaConsist: Fine-Grained Consistent Character Generation

Memory Efficient Matting with Adaptive Token Routing

C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection

Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Domain Learning

Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection

PixelLM: Pixel Reasoning with Large Multimodal Model

Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection

Reversible Recursive Instance-Level Object Segmentation

Self-Erasing Network for Integral Object Attention

Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation

Consistent Structural Relation Learning for Zero-Shot Segmentation

Associating Objects with Transformers for Video Object Segmentation

Few-Shot Segmentation via Cycle-Consistent Transformer

Mask Matching Transformer for Few-Shot Segmentation

Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental Segmentation

Learning Mask-aware CLIP Representations for Zero-Shot Segmentation

RIO: A Benchmark for Reasoning Intention-Oriented Objects in Open Environments

SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process