Xiaohui Shen

papers

954

total citations

papers (17)

Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

NEURIPS 2023arXiv

212

citations

Learning Progressive Joint Propagation for Human Motion Prediction

ECCV 2020

187

citations

SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing

CVPR 2022arXiv

107

citations

Randomized Autoregressive Visual Generation

ICCV 2025arXiv

citations

MaskBit: Embedding-free Image Generation via Bit Tokens

ICLR 2025arXiv

citations

Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses

ECCV 2020arXiv

citations

Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens

ICCV 2025arXiv

citations

COCONut: Modernizing COCO Segmentation

CVPR 2024arXiv

citations

Fashion Editing With Adversarial Parsing Learning

CVPR 2020arXiv

citations

MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval

CVPR 2024arXiv

citations

D-Attn: Decomposed Attention for Large Vision-and-Language Model

ICCV 2025arXiv

citations

R2Former: Unified Retrieval and Reranking Transformer for Place Recognition

CVPR 2023

citations

Video Object Detection via Object-level Temporal Aggregation

ECCV 2020

citations

A Unified 3D Human Motion Synthesis Model via Conditional Variational Auto-Encoder

ICCV 2021

citations

Xiaohui Shen

papers (17)

Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

Learning Progressive Joint Propagation for Human Motion Prediction

SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing

Randomized Autoregressive Visual Generation

MaskBit: Embedding-free Image Generation via Bit Tokens

Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses

Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation

ViTamin: Designing Scalable Vision Models in the Vision-Language Era

FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching

Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens

COCONut: Modernizing COCO Segmentation

Fashion Editing With Adversarial Parsing Learning

MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval

D-Attn: Decomposed Attention for Large Vision-and-Language Model

R2Former: Unified Retrieval and Reranking Transformer for Place Recognition

Video Object Detection via Object-level Temporal Aggregation

A Unified 3D Human Motion Synthesis Model via Conditional Variational Auto-Encoder

papers (17)

Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

Learning Progressive Joint Propagation for Human Motion Prediction

SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing

Randomized Autoregressive Visual Generation

MaskBit: Embedding-free Image Generation via Bit Tokens

Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses

Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation

ViTamin: Designing Scalable Vision Models in the Vision-Language Era

FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching

Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens

COCONut: Modernizing COCO Segmentation

Fashion Editing With Adversarial Parsing Learning

MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval

D-Attn: Decomposed Attention for Large Vision-and-Language Model

R2Former: Unified Retrieval and Reranking Transformer for Place Recognition

Video Object Detection via Object-level Temporal Aggregation

A Unified 3D Human Motion Synthesis Model via Conditional Variational Auto-Encoder