Yongqin Xian

papers

1,241

total citations

papers (19)

I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification

CVPR 2023arXiv

citations

CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution

CVPR 2023arXiv

citations

SILC: Improving Vision Language Pretraining with Self-Distillation

ECCV 2024arXiv

citations

VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning

CVPR 2022arXiv

citations

I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification

NEURIPS 2022arXiv

citations

Text-Conditioned Resampler For Long Form Video Understanding

ECCV 2024arXiv

citations

PALM: Predicting Actions through Language Models

ECCV 2024arXiv

citations

3D Compositional Zero-Shot Learning with DeCompositional Consensus

ECCV 2022arXiv

citations

Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos

CVPR 2025arXiv

citations

Active Data Curation Effectively Distills Large-Scale Multimodal Models

CVPR 2025arXiv

citations

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

ICLR 2025arXiv

citations

UIP2P: Unsupervised Instruction-based Image Editing via Edit Reversibility Constraint

ICCV 2025arXiv

citations

Weakly-Supervised Domain Adaptive Semantic Segmentation With Prototypical Contrastive Learning

CVPR 2023

citations

LOGICZSL: Exploring Logic-induced Representation for Compositional Zero-shot Learning

CVPR 2025

citations

MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning

ICCV 2025arXiv

citations

Yongqin Xian

papers (19)

Attribute Prototype Network for Zero-Shot Learning

Learning Graph Embeddings for Compositional Zero-Shot Learning

Open World Compositional Zero-Shot Learning

Distilling Audio-Visual Knowledge by Compositional Contrastive Learning

I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification

CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution

SILC: Improving Vision Language Pretraining with Self-Distillation

VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning

I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification

Text-Conditioned Resampler For Long Form Video Understanding

PALM: Predicting Actions through Language Models

3D Compositional Zero-Shot Learning with DeCompositional Consensus

Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos

Active Data Curation Effectively Distills Large-Scale Multimodal Models

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

UIP2P: Unsupervised Instruction-based Image Editing via Edit Reversibility Constraint

Weakly-Supervised Domain Adaptive Semantic Segmentation With Prototypical Contrastive Learning

LOGICZSL: Exploring Logic-induced Representation for Compositional Zero-shot Learning

MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning

papers (19)

Attribute Prototype Network for Zero-Shot Learning

Learning Graph Embeddings for Compositional Zero-Shot Learning

Open World Compositional Zero-Shot Learning

Distilling Audio-Visual Knowledge by Compositional Contrastive Learning

I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification

CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution

SILC: Improving Vision Language Pretraining with Self-Distillation

VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning

I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification

Text-Conditioned Resampler For Long Form Video Understanding

PALM: Predicting Actions through Language Models

3D Compositional Zero-Shot Learning with DeCompositional Consensus

Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos

Active Data Curation Effectively Distills Large-Scale Multimodal Models

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

UIP2P: Unsupervised Instruction-based Image Editing via Edit Reversibility Constraint

Weakly-Supervised Domain Adaptive Semantic Segmentation With Prototypical Contrastive Learning

LOGICZSL: Exploring Logic-induced Representation for Compositional Zero-shot Learning

MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning