Li Sun

papers

693

total citations

papers (20)

Cross Attention Based Style Distribution for Controllable Person Image Synthesis

ECCV 2022arXiv

citations

Style Transformer for Image Inversion and Editing

CVPR 2022arXiv

citations

Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction

NEURIPS 2023arXiv

citations

Motif-Aware Riemannian Graph Neural Network with Generative-Contrastive Learning

AAAI 2024arXiv

citations

LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering

ICML 2024arXiv

citations

Novel View Synthesis on Unpaired Data by Conditional Deformable Variational Auto-Encoder

ECCV 2020arXiv

citations

Bootstrapping ViTs: Towards Liberating Vision Transformers From Pre-Training

CVPR 2022arXiv

citations

Bridging the Gap Between Label- and Reference-Based Synthesis in Multi-Attribute Image-to-Image Translation

ICCV 2021arXiv

citations

Towards Effective, Efficient and Unsupervised Social Event Detection in the Hyperbolic Space

AAAI 2025arXiv

citations

ID-Unet: Iterative Soft and Hard Deformation for View Synthesis

CVPR 2021arXiv

citations

RecursiveDet: End-to-End Region-Based Recursive Object Detection

ICCV 2023arXiv

citations

Pioneer: Physics-informed Riemannian Graph ODE for Entropy-increasing Dynamics

AAAI 2025arXiv

citations

Angle Robustness Unmanned Aerial Vehicle Navigation in GNSS-Denied Scenarios

AAAI 2024arXiv

citations

Structural Entropy Guided Probabilistic Coding

AAAI 2025arXiv

citations

How To Prevent the Continuous Damage of Noises To Model Training?

CVPR 2023

citations

Tree-Like Decision Distillation

CVPR 2021

citations

MSA2: Multi-task Framework with Structure-aware and Style-adaptive Character Representation for Open-set Chinese Text Recognition

ICCV 2025

citations

Li Sun

papers (20)

Can contrastive learning avoid shortcut solutions?

DG-Font: Deformable Generative Networks for Unsupervised Font Generation

QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translation

Cross Attention Based Style Distribution for Controllable Person Image Synthesis

Style Transformer for Image Inversion and Editing

Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction

Motif-Aware Riemannian Graph Neural Network with Generative-Contrastive Learning

LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering

Novel View Synthesis on Unpaired Data by Conditional Deformable Variational Auto-Encoder

Bootstrapping ViTs: Towards Liberating Vision Transformers From Pre-Training

Bridging the Gap Between Label- and Reference-Based Synthesis in Multi-Attribute Image-to-Image Translation

Towards Effective, Efficient and Unsupervised Social Event Detection in the Hyperbolic Space

ID-Unet: Iterative Soft and Hard Deformation for View Synthesis

RecursiveDet: End-to-End Region-Based Recursive Object Detection

Pioneer: Physics-informed Riemannian Graph ODE for Entropy-increasing Dynamics

Angle Robustness Unmanned Aerial Vehicle Navigation in GNSS-Denied Scenarios

Structural Entropy Guided Probabilistic Coding

How To Prevent the Continuous Damage of Noises To Model Training?

Tree-Like Decision Distillation

MSA2: Multi-task Framework with Structure-aware and Style-adaptive Character Representation for Open-set Chinese Text Recognition

papers (20)

Can contrastive learning avoid shortcut solutions?

DG-Font: Deformable Generative Networks for Unsupervised Font Generation

QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translation

Cross Attention Based Style Distribution for Controllable Person Image Synthesis

Style Transformer for Image Inversion and Editing

Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction

Motif-Aware Riemannian Graph Neural Network with Generative-Contrastive Learning

LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering

Novel View Synthesis on Unpaired Data by Conditional Deformable Variational Auto-Encoder

Bootstrapping ViTs: Towards Liberating Vision Transformers From Pre-Training

Bridging the Gap Between Label- and Reference-Based Synthesis in Multi-Attribute Image-to-Image Translation

Towards Effective, Efficient and Unsupervised Social Event Detection in the Hyperbolic Space

ID-Unet: Iterative Soft and Hard Deformation for View Synthesis

RecursiveDet: End-to-End Region-Based Recursive Object Detection

Pioneer: Physics-informed Riemannian Graph ODE for Entropy-increasing Dynamics

Angle Robustness Unmanned Aerial Vehicle Navigation in GNSS-Denied Scenarios

Structural Entropy Guided Probabilistic Coding

How To Prevent the Continuous Damage of Noises To Model Training?

Tree-Like Decision Distillation

MSA2: Multi-task Framework with Structure-aware and Style-adaptive Character Representation for Open-set Chinese Text Recognition