Yongwei Nie

papers

847

total citations

papers (14)

A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction

ICCV 2021arXiv

317

citations

MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction

ICCV 2021arXiv

244

citations

Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction

CVPR 2022arXiv

144

citations

Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detection

ECCV 2024arXiv

citations

RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Images

CVPR 2025arXiv

citations

Simplification Is All You Need against Out-of-Distribution Overconfidence

CVPR 2025

citations

EntityErasure: Erasing Entity Cleanly via Amodal Entity Segmentation and Completion

CVPR 2025

citations

Multi-RoI Human Mesh Recovery with Camera Consistency and Contrastive Losses

ECCV 2024arXiv

citations

When Shadow Removal Meets Intrinsic Image Decomposition: A Joint Learning Framework Using Unpaired Data

AAAI 2025

citations

Occlusion-Insensitive Talking Head Video Generation via Facelet Compensation

AAAI 2025

citations

Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detection

NEURIPS 2025arXiv

citations

Yongwei Nie

papers (14)

A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction

MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction

Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction

Fine-Grained Face Swapping via Regional GAN Inversion

Learning Dynamic Style Kernels for Artistic Style Transfer

RecDreamer: Consistent Text-to-3D Generation via Uniform Score Distillation

Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detection

RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Images

Simplification Is All You Need against Out-of-Distribution Overconfidence

EntityErasure: Erasing Entity Cleanly via Amodal Entity Segmentation and Completion

Multi-RoI Human Mesh Recovery with Camera Consistency and Contrastive Losses

When Shadow Removal Meets Intrinsic Image Decomposition: A Joint Learning Framework Using Unpaired Data

Occlusion-Insensitive Talking Head Video Generation via Facelet Compensation

Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detection

papers (14)

A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction

MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction

Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction

Fine-Grained Face Swapping via Regional GAN Inversion

Learning Dynamic Style Kernels for Artistic Style Transfer

RecDreamer: Consistent Text-to-3D Generation via Uniform Score Distillation

Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detection

RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Images

Simplification Is All You Need against Out-of-Distribution Overconfidence

EntityErasure: Erasing Entity Cleanly via Amodal Entity Segmentation and Completion

Multi-RoI Human Mesh Recovery with Camera Consistency and Contrastive Losses

When Shadow Removal Meets Intrinsic Image Decomposition: A Joint Learning Framework Using Unpaired Data

Occlusion-Insensitive Talking Head Video Generation via Facelet Compensation

Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detection