Zhenguang Liu

papers

530

total citations

papers (17)

Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation

CVPR 2022arXiv

citations

Let All Be Whitened: Multi-Teacher Distillation for Efficient Visual Retrieval

AAAI 2024arXiv

citations

FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning

CVPR 2025arXiv

citations

MTVHunter: Smart Contracts Vulnerability Detection Based on Multi-Teacher Knowledge Translation

AAAI 2025arXiv

citations

Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation

AAAI 2025arXiv

citations

SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos

AAAI 2025arXiv

citations

HVIS: A Human-like Vision and Inference System for Human Motion Prediction

AAAI 2025arXiv

citations

Optimizing Human Pose Estimation Through Focused Human and Joint Regions

AAAI 2025arXiv

citations

Rethinking Human Motion Prediction with Symplectic Integral

CVPR 2024

citations

Harnessing Frequency Spectrum Insights for Image Copyright Protection Against Diffusion Models

CVPR 2025arXiv

citations

Motion Prediction Using Trajectory Cues

ICCV 2021

citations

PhyCamo: A Robust Physical Camouflage via Contrastive Learning for Multi-View Physical Adversarial Attack

AAAI 2025

citations

CrossMatch: Source-Free Domain Adaptive Semantic Segmentation via Cross-Modal Consistency Training

ICCV 2023

citations

Zhenguang Liu

papers (17)

LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting

Deep Dual Consecutive Network for Human Pose Estimation

Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection

Invariant Feature Learning for Generalized Long-Tailed Classification

Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation

Let All Be Whitened: Multi-Teacher Distillation for Efficient Visual Retrieval

FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning

MTVHunter: Smart Contracts Vulnerability Detection Based on Multi-Teacher Knowledge Translation

Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation

SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos

HVIS: A Human-like Vision and Inference System for Human Motion Prediction

Optimizing Human Pose Estimation Through Focused Human and Joint Regions

Rethinking Human Motion Prediction with Symplectic Integral

Harnessing Frequency Spectrum Insights for Image Copyright Protection Against Diffusion Models

Motion Prediction Using Trajectory Cues

PhyCamo: A Robust Physical Camouflage via Contrastive Learning for Multi-View Physical Adversarial Attack

CrossMatch: Source-Free Domain Adaptive Semantic Segmentation via Cross-Modal Consistency Training

papers (17)

LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting

Deep Dual Consecutive Network for Human Pose Estimation

Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection

Invariant Feature Learning for Generalized Long-Tailed Classification

Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation

Let All Be Whitened: Multi-Teacher Distillation for Efficient Visual Retrieval

FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning

MTVHunter: Smart Contracts Vulnerability Detection Based on Multi-Teacher Knowledge Translation

Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation

SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos

HVIS: A Human-like Vision and Inference System for Human Motion Prediction

Optimizing Human Pose Estimation Through Focused Human and Joint Regions

Rethinking Human Motion Prediction with Symplectic Integral

Harnessing Frequency Spectrum Insights for Image Copyright Protection Against Diffusion Models

Motion Prediction Using Trajectory Cues

PhyCamo: A Robust Physical Camouflage via Contrastive Learning for Multi-View Physical Adversarial Attack

CrossMatch: Source-Free Domain Adaptive Semantic Segmentation via Cross-Modal Consistency Training