Yunhai Tong

papers

2,148

total citations

papers (20)

PolyphonicFormer: Unified Query Learning for Depth-Aware Video Panoptic Segmentation

ECCV 2022arXiv

citations

Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation

ICCV 2023arXiv

citations

Towards Language-Driven Video Inpainting via Multimodal Large Language Models

CVPR 2024arXiv

citations

MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning

AAAI 2025arXiv

citations

Explore In-Context Segmentation via Latent Diffusion Models

AAAI 2025arXiv

citations

DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation

CVPR 2025arXiv

citations

Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs

ICCV 2025arXiv

citations

DreamRelation: Bridging Customization and Relation Generation

CVPR 2025arXiv

citations

Decouple and Track: Benchmarking and Improving Video Diffusion Transformers For Motion Transfer

ICCV 2025arXiv

citations

Towards Scalable and Deep Graph Neural Networks via Noise Masking

AAAI 2025arXiv

citations

Conditional Panoramic Image Generation via Masked Autoregressive Modeling

NEURIPS 2025arXiv

citations

"Fashionformer: A Simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition"

ECCV 2022

citations

Yunhai Tong

papers (20)

Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting

Semantic Flow for Fast and Accurate Scene Parsing

Improving Semantic Segmentation via Decoupled Body and Edge Supervision

Boundary Content Graph Neural Network for Temporal Action Proposal Generation

Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation

Enhanced Boundary Learning for Glass-Like Object Segmentation

PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation

Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation

PolyphonicFormer: Unified Query Learning for Depth-Aware Video Panoptic Segmentation

Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation

Towards Language-Driven Video Inpainting via Multimodal Large Language Models

MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning

Explore In-Context Segmentation via Latent Diffusion Models

DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation

Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs

DreamRelation: Bridging Customization and Relation Generation

Decouple and Track: Benchmarking and Improving Video Diffusion Transformers For Motion Transfer

Towards Scalable and Deep Graph Neural Networks via Noise Masking

Conditional Panoramic Image Generation via Masked Autoregressive Modeling

"Fashionformer: A Simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition"

papers (20)

Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting

Semantic Flow for Fast and Accurate Scene Parsing

Improving Semantic Segmentation via Decoupled Body and Edge Supervision

Boundary Content Graph Neural Network for Temporal Action Proposal Generation

Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation

Enhanced Boundary Learning for Glass-Like Object Segmentation

PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation

Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation

PolyphonicFormer: Unified Query Learning for Depth-Aware Video Panoptic Segmentation

Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation

Towards Language-Driven Video Inpainting via Multimodal Large Language Models

MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning

Explore In-Context Segmentation via Latent Diffusion Models

DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation

Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs

DreamRelation: Bridging Customization and Relation Generation

Decouple and Track: Benchmarking and Improving Video Diffusion Transformers For Motion Transfer

Towards Scalable and Deep Graph Neural Networks via Noise Masking

Conditional Panoramic Image Generation via Masked Autoregressive Modeling

"Fashionformer: A Simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition"