Yunhai Tong

20

Papers

91

Total Citations

Papers (20)

Towards Language-Driven Video Inpainting via Multimodal Large Language Models

Explore In-Context Segmentation via Latent Diffusion Models

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

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

Conditional Panoramic Image Generation via Masked Autoregressive Modeling

Towards Scalable and Deep Graph Neural Networks via Noise Masking

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

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

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

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

PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation

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

Enhanced Boundary Learning for Glass-Like Object Segmentation

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

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

Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting