Author name cluster

Zhi Yu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

EAAI Journal 2025 Journal Article

A Multi-Domain Patch-Differentiated Transformer for vehicle re-identification

Zhi Yu
Zhiyong Huang
Mingyang Hou
Yan Yan
Yushi Liu
Daming Sun
Hans Gregersen

Vehicle re-identification aims to identify the specific vehicles in cross-camera systems, which is a crucial applied engineering task in intelligent transportation Recently, transformer-based architectures have gained prominence in this field due to the robust feature modeling capabilities. However, most transformer-based approaches apply uniform consideration to all patches, disregarding the heterogeneous contributions of diverse patches to the final representation. To this end, this work proposes a Multi-Domain Patch-Differentiated Transformer (MDPDTrans) built upon the transformer architecture for vehicle re-identification applied engineering. Specifically, a Multi-Domain Patch Differentiation Module (MDPDM) is designed to evaluate the importance of diverse patches adaptively by integrating the domains of attention response, information entropy, and feature energy, enabling differential adjustment for diverse patches. The MDPDM is then embedded within the vision transformer to construct the MDPDTrans, enhancing the transformer’s ability to handle diverse patch contributions and distinguish the heterogeneous importance. Finally, to ensure alignment across these domains, this work designs a Multi-Domain Alignment (MDA) loss. This constrains both direction and distribution to align the patch importance obtained from different domains. By integrating multi-domain patch differentiation and alignment into the transformer, MDPDTrans demonstrates strong performance under challenging conditions. Simultaneously, the experiments verify engineering advancement and practical value of MDPDTrans in vehicle re-identification applied engineering.

Details DOI

JBHI Journal 2025 Journal Article

MSCD-VM-UNet: A Vision Mamba Combining Multi-Scale Global and Local Feature Extraction With Cross-Domain Feature Fusion for Medical Image Segmentation

Zhiyong Huang
Shuxin Wang
Mingyang Hou
Zhi Yu
Shiwei Wang
Xiaoyu Li
Yan Yan
Yushi Liu

Accurate segmentation of tissues and lesions is essential for diagnosis and treatment. State Space Models (SSMs) have gained attention for their linear complexity and ability to model long-range dependencies. However, the existing Mamba architecture relies on direct skip connections, which limits its ability to integrate multi-scale and multi-level features and handle boundary details effectively. To address these limitations, we propose the MSCD-VM-UNet architecture, which incorporates three novel modules: the Spatial Group Multi-Scale Attention Module (SGMAM), the Cross-Domain Feature Fusion Module (CDFFM), and the Attention-Based Feature Injection Module (ABFIM). The SGMAM captures multi-scale global and local information and adaptively adjusts feature importance to highlight key regions while suppressing noise. The CDFFM enhances boundary and detail handling by aligning semantic features from both the frequency and spatial domains. The ABFIM utilizes attention mechanisms to adaptively fuse and weigh features from different scales and semantics, promoting feature collaboration and improving the model’s robustness in complex tasks. Experiments on multiple datasets show that these modules significantly enhance the accuracy of MSCD-VM-UNet, setting a new benchmark for medical image segmentation.

Details DOI

AAAI Conference 2025 Conference Paper

ProcTag: Process Tagging for Assessing the Efficacy of Document Instruction Data

Yufan Shen
Chuwei Luo
Zhaoqing Zhu
Yang Chen
Qi Zheng
Zhi Yu
Jiajun Bu
Cong Yao

Recently, large language models (LLMs) and multimodal large language models (MLLMs) have demonstrated promising results on document visual question answering (VQA) task, particularly after training on document instruction datasets. An effective evaluation method for document instruction data is crucial in constructing instruction data with high efficacy, which, in turn, facilitates the training of LLMs and MLLMs for document VQA. However, most existing evaluation methods for instruction data are limited to the textual content of the instructions themselves, thereby hindering the effective assessment of document instruction datasets and constraining their construction. In this paper, we propose ProcTag, a data-oriented method that assesses the efficacy of document instruction data. ProcTag innovatively performs tagging on the execution process of instructions rather than the instruction text itself. By leveraging the diversity and complexity of these tags to assess the efficacy of the given dataset, ProcTag enables selective sampling or filtering of document instructions. Furthermore, DocLayPrompt, a novel semi-structured layout-aware document prompting strategy, is proposed for effectively representing documents. Experiments demonstrate that sampling existing open-sourced and generated document VQA/instruction datasets with ProcTag significantly outperforms current methods for evaluating instruction data. Impressively, with ProcTag-based sampling in the generated document datasets, only 30.5 percent of the document instructions are required to achieve 100 percent efficacy compared to the complete dataset.

PDF Details DOI

AAAI Conference 2023 Conference Paper

LORE: Logical Location Regression Network for Table Structure Recognition

Hangdi Xing
Feiyu Gao
Rujiao Long
Jiajun Bu
Qi Zheng
Liangcheng Li
Cong Yao
Zhi Yu

Table structure recognition (TSR) aims at extracting tables in images into machine-understandable formats. Recent methods solve this problem by predicting the adjacency relations of detected cell boxes, or learning to generate the corresponding markup sequences from the table images. However, they either count on additional heuristic rules to recover the table structures, or require a huge amount of training data and time-consuming sequential decoders. In this paper, we propose an alternative paradigm. We model TSR as a logical location regression problem and propose a new TSR framework called LORE, standing for LOgical location REgression network, which for the first time combines logical location regression together with spatial location regression of table cells. Our proposed LORE is conceptually simpler, easier to train and more accurate than previous TSR models of other paradigms. Experiments on standard benchmarks demonstrate that LORE consistently outperforms prior arts. Code is available at https:// github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/DocumentUnderstanding/LORE-TSR.

PDF Details DOI