Lingqiao Liu

papers

1,207

total citations

papers (21)

Self-Supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection

CVPR 2022arXiv

282

citations

ZegCLIP: Towards Adapting CLIP for Zero-Shot Semantic Segmentation

CVPR 2023arXiv

253

citations

METransformer: Radiology Report Generation by Transformer With Multiple Learnable Expert Tokens

CVPR 2023arXiv

153

citations

Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization

NEURIPS 2022arXiv

citations

Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-Boosting Attention Mechanism

ECCV 2022arXiv

citations

Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework

CVPR 2024arXiv

citations

Domain Generalization via Rationale Invariance

ICCV 2023arXiv

citations

Learning Common Rationale To Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems

CVPR 2023arXiv

citations

The CLIP Model is Secretly an Image-to-Prompt Converter

NEURIPS 2023arXiv

citations

Attention-Driven GUI Grounding: Leveraging Pretrained Multimodal Large Language Models Without Fine-Tuning

AAAI 2025arXiv

citations

Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation

NEURIPS 2025arXiv

citations

Enhancing Close-up Novel View Synthesis via Pseudo-labeling

AAAI 2025arXiv

citations

One Last Attention for Your Vision-Language Model

ICCV 2025arXiv

citations

Dynamically Transformed Instance Normalization Network for Generalizable Person Re-identification

ECCV 2022

citations

OST: Improving Generalization of DeepFake Detection via One-Shot Test-Time Training

NEURIPS 2022

citations

Toward Re-Identifying Any Animal

NEURIPS 2023

citations

Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors

CVPR 2024

citations

Lingqiao Liu

papers (21)

Self-Supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection

ZegCLIP: Towards Adapting CLIP for Zero-Shot Semantic Segmentation

METransformer: Radiology Report Generation by Transformer With Multiple Learnable Expert Tokens

Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization

Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks

Training Quantized Neural Networks With a Full-Precision Auxiliary Module

Improved Test-Time Adaptation for Domain Generalization

Learning Conditional Attributes for Compositional Zero-Shot Learning

Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-Boosting Attention Mechanism

Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework

Domain Generalization via Rationale Invariance

Learning Common Rationale To Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems

The CLIP Model is Secretly an Image-to-Prompt Converter

Attention-Driven GUI Grounding: Leveraging Pretrained Multimodal Large Language Models Without Fine-Tuning

Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation

Enhancing Close-up Novel View Synthesis via Pseudo-labeling

One Last Attention for Your Vision-Language Model

Dynamically Transformed Instance Normalization Network for Generalizable Person Re-identification

OST: Improving Generalization of DeepFake Detection via One-Shot Test-Time Training

Toward Re-Identifying Any Animal

Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors

papers (21)

Self-Supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection

ZegCLIP: Towards Adapting CLIP for Zero-Shot Semantic Segmentation

METransformer: Radiology Report Generation by Transformer With Multiple Learnable Expert Tokens

Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization

Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks

Training Quantized Neural Networks With a Full-Precision Auxiliary Module

Improved Test-Time Adaptation for Domain Generalization

Learning Conditional Attributes for Compositional Zero-Shot Learning

Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-Boosting Attention Mechanism

Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework

Domain Generalization via Rationale Invariance

Learning Common Rationale To Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems

The CLIP Model is Secretly an Image-to-Prompt Converter

Attention-Driven GUI Grounding: Leveraging Pretrained Multimodal Large Language Models Without Fine-Tuning

Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation

Enhancing Close-up Novel View Synthesis via Pseudo-labeling

One Last Attention for Your Vision-Language Model

Dynamically Transformed Instance Normalization Network for Generalizable Person Re-identification

OST: Improving Generalization of DeepFake Detection via One-Shot Test-Time Training

Toward Re-Identifying Any Animal

Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors