Liang Liu

papers

1,011

total citations

papers (21)

Rethinking Mobile Block for Efficient Attention-based Models

ICCV 2023arXiv

206

citations

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

CVPR 2020arXiv

197

citations

AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model

AAAI 2024arXiv

144

citations

SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking

CVPR 2024arXiv

citations

Weighing Counts: Sequential Crowd Counting by Reinforcement Learning

ECCV 2020arXiv

citations

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

CVPR 2023arXiv

citations

Learning From Noisy Labels With Decoupled Meta Label Purifier

CVPR 2023arXiv

citations

Rethinking Reverse Distillation for Multi-Modal Anomaly Detection

AAAI 2024

citations

Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detection

ECCV 2024arXiv

citations

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

ICCV 2023arXiv

citations

T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving

CVPR 2025arXiv

citations

FRIH: Fine-Grained Region-Aware Image Harmonization

AAAI 2024arXiv

citations

LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views

ICML 2024arXiv

citations

Audio-Visual Semantic Graph Network for Audio-Visual Event Localization

CVPR 2025

citations

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

ICCV 2023

citations

DTVNet: Dynamic Time-lapse Video Generation via Single Still Image

ECCV 2020

citations

DualGraph: A Graph-Based Method for Reasoning About Label Noise

CVPR 2021

citations

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

CVPR 2022

citations

Liang Liu

papers (21)

Rethinking Mobile Block for Efficient Attention-based Models

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

AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model

SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking

Weighing Counts: Sequential Crowd Counting by Reinforcement Learning

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

Learning From Noisy Labels With Decoupled Meta Label Purifier

Rethinking Reverse Distillation for Multi-Modal Anomaly Detection

Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detection

FReeNet: Multi-Identity Face Reenactment

Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection

Learning With Noisy Labels via Self-Supervised Adversarial Noisy Masking

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

T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving

FRIH: Fine-Grained Region-Aware Image Harmonization

LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views

Audio-Visual Semantic Graph Network for Audio-Visual Event Localization

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

DTVNet: Dynamic Time-lapse Video Generation via Single Still Image

DualGraph: A Graph-Based Method for Reasoning About Label Noise

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

papers (21)

Rethinking Mobile Block for Efficient Attention-based Models

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

AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model

SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking

Weighing Counts: Sequential Crowd Counting by Reinforcement Learning

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

Learning From Noisy Labels With Decoupled Meta Label Purifier

Rethinking Reverse Distillation for Multi-Modal Anomaly Detection

Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detection

FReeNet: Multi-Identity Face Reenactment

Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection

Learning With Noisy Labels via Self-Supervised Adversarial Noisy Masking

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

T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving

FRIH: Fine-Grained Region-Aware Image Harmonization

LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views

Audio-Visual Semantic Graph Network for Audio-Visual Event Localization

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

DTVNet: Dynamic Time-lapse Video Generation via Single Still Image

DualGraph: A Graph-Based Method for Reasoning About Label Noise

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