Xingye Tian — accepted AI-conference papers

2025

VFRTok: Variable Frame Rates Video Tokenizer with Duration-Proportional Information Assumption

Tianxiong Zhong, Xingye Tian, Boyuan Jiang, Xuebo Wang, Xin Tao, Pengfei Wan +1

NeurIPS 2025poster

Modern video generation frameworks based on Latent Diffusion Models suffer from inefficiencies in tokenization due to the Frame-Proportional Information Assumption. Existing tokenizers provide fixed temporal compression rates, causing the computational cost of the diffusion model to scale linearly w…

Cited by 0 Source ↗Scholar ↗

2023

DVIS: Decoupled Video Instance Segmentation Framework

Tao Zhang, Xingye Tian, Yu Wu, Shunping Ji, Xuebo Wang, Yuan Zhang +1

ICCV 2023poster

Video instance segmentation (VIS) is a critical task with diverse applications, including autonomous driving and video editing. Existing methods often underperform on complex and long videos in real world, primarily due to two factors. Firstly, offline methods are limited by the tightly-coupled mode…

Cited by 59 PDF ↗code ↗Scholar ↗