Yifan Liu

papers

1,728

total citations

papers (29)

A Simple Baseline for Semi-Supervised Semantic Segmentation With Strong Data Augmentation

ICCV 2021arXiv

142

citations

Efficient Semantic Video Segmentation with Per-frame Inference

ECCV 2020arXiv

139

citations

Inter-X: Towards Versatile Human-Human Interaction Analysis

CVPR 2024arXiv

citations

CTVIS: Consistent Training for Online Video Instance Segmentation

ICCV 2023arXiv

citations

Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation

ICCV 2023arXiv

citations

Representative Graph Neural Network

ECCV 2020arXiv

citations

Generic Perceptual Loss for Modeling Structured Output Dependencies

CVPR 2021arXiv

citations

GTP-4o: Modality-prompted Heterogeneous Graph Learning for Omni-modal Biomedical Representation

ECCV 2024arXiv

citations

Controllable Shadow Generation Using Pixel Height Maps

ECCV 2022arXiv

citations

SegPrompt: Boosting Open-World Segmentation via Category-Level Prompt Learning

ICCV 2023arXiv

citations

Semantic-Guided Multi-Mask Image Harmonization

ECCV 2022arXiv

citations

InstantSplamp: Fast and Generalizable Stenography Framework for Generative Gaussian Splatting

ICLR 2025

citations

Video Task Decathlon: Unifying Image and Video Tasks in Autonomous Driving

ICCV 2023arXiv

citations

MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models

CVPR 2025arXiv

citations

High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field

AAAI 2024arXiv

citations

Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions

ICCV 2025arXiv

citations

Back-Modality: Leveraging Modal Transformation for Data Augmentation

NEURIPS 2023

citations

InfoBridge: Balanced Multimodal Integration through Conditional Dependency Modeling

ICCV 2025

citations

Learning Efficient and Generalizable Human Representation with Human Gaussian Model

ICCV 2025arXiv

citations

Anti-Tamper Protection for Unauthorized Individual Image Generation

ICCV 2025arXiv

citations

3DPPE: 3D Point Positional Encoding for Transformer-based Multi-Camera 3D Object Detection

ICCV 2023

citations

GaussianReg: Rapid 2D/3D Registration for Emergency Surgery via Explicit 3D Modeling with Gaussian Primitives

ICCV 2025

citations

Amodal Scene Analysis via Holistic Occlusion Relation Inference and Generative Mask Completion

AAAI 2024

citations

MirageRoom: 3D Scene Segmentation with 2D Pre-trained Models by Mirage Projection

CVPR 2024

citations

Instance-Aware Embedding for Point Cloud Instance Segmentation

ECCV 2020

citations

FedPD: Federated Open Set Recognition with Parameter Disentanglement

ICCV 2023

citations

Yifan Liu

papers (29)

Channel-Wise Knowledge Distillation for Dense Prediction

U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation

ZegCLIP: Towards Adapting CLIP for Zero-Shot Semantic Segmentation

A Simple Baseline for Semi-Supervised Semantic Segmentation With Strong Data Augmentation

Efficient Semantic Video Segmentation with Per-frame Inference

Inter-X: Towards Versatile Human-Human Interaction Analysis

CTVIS: Consistent Training for Online Video Instance Segmentation

Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation

Representative Graph Neural Network

Generic Perceptual Loss for Modeling Structured Output Dependencies

GTP-4o: Modality-prompted Heterogeneous Graph Learning for Omni-modal Biomedical Representation

Controllable Shadow Generation Using Pixel Height Maps

SegPrompt: Boosting Open-World Segmentation via Category-Level Prompt Learning

Semantic-Guided Multi-Mask Image Harmonization

InstantSplamp: Fast and Generalizable Stenography Framework for Generative Gaussian Splatting

Video Task Decathlon: Unifying Image and Video Tasks in Autonomous Driving

MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models

High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field

Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions

Back-Modality: Leveraging Modal Transformation for Data Augmentation

InfoBridge: Balanced Multimodal Integration through Conditional Dependency Modeling

Learning Efficient and Generalizable Human Representation with Human Gaussian Model

Anti-Tamper Protection for Unauthorized Individual Image Generation

3DPPE: 3D Point Positional Encoding for Transformer-based Multi-Camera 3D Object Detection

GaussianReg: Rapid 2D/3D Registration for Emergency Surgery via Explicit 3D Modeling with Gaussian Primitives

Amodal Scene Analysis via Holistic Occlusion Relation Inference and Generative Mask Completion

MirageRoom: 3D Scene Segmentation with 2D Pre-trained Models by Mirage Projection

Instance-Aware Embedding for Point Cloud Instance Segmentation

FedPD: Federated Open Set Recognition with Parameter Disentanglement

papers (29)

Channel-Wise Knowledge Distillation for Dense Prediction

U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation

ZegCLIP: Towards Adapting CLIP for Zero-Shot Semantic Segmentation

A Simple Baseline for Semi-Supervised Semantic Segmentation With Strong Data Augmentation

Efficient Semantic Video Segmentation with Per-frame Inference

Inter-X: Towards Versatile Human-Human Interaction Analysis

CTVIS: Consistent Training for Online Video Instance Segmentation

Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation

Representative Graph Neural Network

Generic Perceptual Loss for Modeling Structured Output Dependencies

GTP-4o: Modality-prompted Heterogeneous Graph Learning for Omni-modal Biomedical Representation

Controllable Shadow Generation Using Pixel Height Maps

SegPrompt: Boosting Open-World Segmentation via Category-Level Prompt Learning

Semantic-Guided Multi-Mask Image Harmonization

InstantSplamp: Fast and Generalizable Stenography Framework for Generative Gaussian Splatting

Video Task Decathlon: Unifying Image and Video Tasks in Autonomous Driving

MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models

High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field

Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions

Back-Modality: Leveraging Modal Transformation for Data Augmentation

InfoBridge: Balanced Multimodal Integration through Conditional Dependency Modeling

Learning Efficient and Generalizable Human Representation with Human Gaussian Model

Anti-Tamper Protection for Unauthorized Individual Image Generation

3DPPE: 3D Point Positional Encoding for Transformer-based Multi-Camera 3D Object Detection

GaussianReg: Rapid 2D/3D Registration for Emergency Surgery via Explicit 3D Modeling with Gaussian Primitives

Amodal Scene Analysis via Holistic Occlusion Relation Inference and Generative Mask Completion

MirageRoom: 3D Scene Segmentation with 2D Pre-trained Models by Mirage Projection

Instance-Aware Embedding for Point Cloud Instance Segmentation

FedPD: Federated Open Set Recognition with Parameter Disentanglement