Search Results for author: Yongping Xiong

Found 7 papers, 5 papers with code

VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval

1 code implementation6 Jun 2024 Junjie Zhou, Zheng Liu, Shitao Xiao, Bo Zhao, Yongping Xiong

Thirdly, we introduce a multi-stage training algorithm, which first aligns the visual token embedding with the text encoder using massive weakly labeled data, and then develops multi-modal representation capability using the generated composed image-text data.

Retrieval

MLVU: A Comprehensive Benchmark for Multi-Task Long Video Understanding

1 code implementation6 Jun 2024 Junjie Zhou, Yan Shu, Bo Zhao, Boya Wu, Shitao Xiao, Xi Yang, Yongping Xiong, Bo Zhang, Tiejun Huang, Zheng Liu

To address the above problems, we propose a new benchmark, called MLVU (Multi-task Long Video Understanding Benchmark), for the comprehensive and in-depth evaluation of LVU.

Video Understanding

TextDiff: Mask-Guided Residual Diffusion Models for Scene Text Image Super-Resolution

1 code implementation13 Aug 2023 Baolin Liu, Zongyuan Yang, Pengfei Wang, Junjie Zhou, Ziqi Liu, Ziyi Song, Yan Liu, Yongping Xiong

Moreover, our proposed MRD module is plug-and-play that effectively sharpens the text edges produced by SOTA methods.

Image Super-Resolution

DocDiff: Document Enhancement via Residual Diffusion Models

2 code implementations6 May 2023 Zongyuan Yang, Baolin Liu, Yongping Xiong, Lan Yi, Guibin Wu, Xiaojun Tang, Ziqi Liu, Junjie Zhou, Xing Zhang

Removing degradation from document images not only improves their visual quality and readability, but also enhances the performance of numerous automated document analysis and recognition tasks.

Deblurring Denoising +1

GDB: Gated convolutions-based Document Binarization

1 code implementation4 Feb 2023 Zongyuan Yang, Yongping Xiong, Guibin Wu

However, existing methods can not extract stroke edges finely, mainly due to the fair-treatment nature of vanilla convolutions and the extraction of stroke edges without adequate supervision by boundary-related information.

Binarization Image Enhancement +1

SAT: Size-Aware Transformer for 3D Point Cloud Semantic Segmentation

no code implementations17 Jan 2023 Junjie Zhou, Yongping Xiong, Chinwai Chiu, Fangyu Liu, Xiangyang Gong

In this paper, we propose the Size-Aware Transformer (SAT) that can tailor effective receptive fields for objects of different sizes.

Point Cloud Segmentation Semantic Segmentation

Transmission Dynamics of COVID-19 Pandemic Non-pharmaceutical Interventions and Vaccination

no code implementations7 Jul 2021 Bin-Guo Wang, Shunxiang Huang, Yongping Xiong, Ming-Zhen Xin, Jing Li, Jiangqian Zhang, Zhihui Ma

By simulating the relation ships of the basic reproduction number $\mathscr{R}_{0}$, the vaccination rate and the efficiency of vaccine, we find that it is impossible to achieve the herd immunity without NPIs when the efficiency of vaccine is lower than $76. 9\%$.

Cannot find the paper you are looking for? You can Submit a new open access paper.