Qiuyi Xin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Qiuyi Xin has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Chu Zhang
School of Information Engineering, Huzhou Normal University, Huzhou 313000, China
2 shared publications - Hengnian Qi
School of Information Engineering, Huzhou Normal University, Huzhou 313000, China
2 shared publications - Chuanhao Fan
School of Information Engineering, Huzhou University, Huzhou 313000, China
1 shared publication - Hao Yang
School of Information Engineering, Huzhou University, Huzhou 313000, China
1 shared publication - Jiabin Ye
School of Information Engineering, Huzhou University, Huzhou 313000, China
1 shared publication - Qing Lang
Library, Huzhou University, Huzhou 313000, China
1 shared publication
Latest Publications
- Open Access
- 13 January 2026
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 10 (1) , 31
TRACE: Topical Reasoning with Adaptive Contextual Experts
Retrieval-Augmented Generation (RAG) is widely used for long-text summarization due to its efficiency and scalability. However, standard RAG methods flatten documents into independent chunks, disrupting sequential flow and thematic structure, resulting in significant loss of contextual information. This paper presents MOEGAT, a novel graph-enhanced retrieval framework that addresses this limitation by explicitly modeling document structure. MOEGAT constructs an Orthogonal Context Graph to capture sequential discourse and global semantic relationships—long-range dependencies between non-adjacent text spans that reflect topical similarity and logical associations beyond local context. It then employs a query-aware Mixture-of-Experts Graph Attention Network to dynamically activate specialized reasoning pathways. Experiments conducted on three public long-text summarization datasets demonstrate that MOEGAT achieves state-of-the-art performance. Notably, on the WCEP dataset, it outperforms the previous state-of-the-art Graph of Records (GOR) baseline by 14.9%, 18.1%, and 18.4% on ROUGE-L, ROUGE-1, and ROUGE-2, respectively. These substantial gains, especially the 14.9% improvement in ROUGE-L, reflect significantly better capture of long-range coherence and thematic integrity in summaries. Ablation studies confirm the effectiveness of the orthogonal graph and Mixture-of-Experts components. Overall, this work introduces a novel structure-aware approach to RAG that explicitly models and leverages document structure through an orthogonal graph representation and query-aware Mixture-of-Experts reasoning.
- 13 January 2026
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 10 (1) , 31
Open AccessTRACE: Topical Reasoning with Adaptive Contextual Experts
Retrieval-Augmented Generation (RAG) is widely used for long-text summarization due to its efficiency and scalability. However, standard RAG methods flatten documents into independent chunks, disrupting sequential flow and thematic structure, resulting in significant loss of contextual information. This paper presents MOEGAT, a novel graph-enhanced retrieval framework that addresses this limitation by explicitly modeling document structure. MOEGAT constructs an Orthogonal Context Graph to capture sequential discourse and global semantic relationships—long-range dependencies between non-adjacent text spans that reflect topical similarity and logical associations beyond local context. It then employs a query-aware Mixture-of-Experts Graph Attention Network to dynamically activate specialized reasoning pathways. Experiments conducted on three public long-text summarization datasets demonstrate that MOEGAT achieves state-of-the-art performance. Notably, on the WCEP dataset, it outperforms the previous state-of-the-art Graph of Records (GOR) baseline by 14.9%, 18.1%, and 18.4% on ROUGE-L, ROUGE-1, and ROUGE-2, respectively. These substantial gains, especially the 14.9% improvement in ROUGE-L, reflect significantly better capture of long-range coherence and thematic integrity in summaries. Ablation studies confirm the effectiveness of the orthogonal graph and Mixture-of-Experts components. Overall, this work introduces a novel structure-aware approach to RAG that explicitly models and leverages document structure through an orthogonal graph representation and query-aware Mixture-of-Experts reasoning.
- Top Cited PapersOpen Access
- 21 August 2025
- Published by MDPI AG in Electronics
- Vol. 14 (16) , 3324
DRA-Net: Dynamic Feature Fusion Upsampling and Text-Region Focus for Ancient Chinese Scene Text Detection
Ancient Chinese scene text detection, as an emerging interdisciplinary topic between computer vision and cultural heritage preservation, presents unique technical challenges. Compared with modern scene text, ancient Chinese text is characterized by complex backgrounds, diverse fonts, extreme aspect ratios, and a scarcity of annotated data. Existing detection methods often perform poorly under these conditions. To address these challenges, this paper proposes a novel detection network based on dynamic feature fusion upsampling and text-region focus, named DRA-Net. The core innovations of the proposed method include (1) a dynamic fusion upsampling module, which adaptively assigns weights to effectively fuse multi-scale features while preserving critical information during feature propagation; (2) an adaptive text-region focus module that incorporates axial attention mechanisms to enhance the model’s ability to locate text regions and suppress background interference; and (3) the integration of deformable convolution, which improves the network’s capacity to model irregular text shapes and extreme aspect ratios. To tackle the issue of data scarcity, we construct a dataset named ACST, specifically for ancient Chinese text detection. This dataset includes a wide range of scene types, such as stone inscriptions, calligraphy works, couplets, and other historical media, covering various font styles from different historical periods, thus offering strong data support for related research. Experimental results demonstrate that DRA-Net achieves significantly higher detection accuracy on the ACST dataset compared to existing methods and performs robustly in scenarios with complex backgrounds and extreme text aspect ratios. It achieves an F1-score of 72.9%, a precision of 82.8%, and a recall of 77.5%. This study provides an effective technical solution for the digitization of ancient documents and the intelligent preservation of cultural heritage, with strong theoretical significance and practical potential.
- 21 August 2025
- Published by MDPI AG in Electronics
- Vol. 14 (16) , 3324
Top Cited PapersOpen AccessDRA-Net: Dynamic Feature Fusion Upsampling and Text-Region Focus for Ancient Chinese Scene Text Detection
Ancient Chinese scene text detection, as an emerging interdisciplinary topic between computer vision and cultural heritage preservation, presents unique technical challenges. Compared with modern scene text, ancient Chinese text is characterized by complex backgrounds, diverse fonts, extreme aspect ratios, and a scarcity of annotated data. Existing detection methods often perform poorly under these conditions. To address these challenges, this paper proposes a novel detection network based on dynamic feature fusion upsampling and text-region focus, named DRA-Net. The core innovations of the proposed method include (1) a dynamic fusion upsampling module, which adaptively assigns weights to effectively fuse multi-scale features while preserving critical information during feature propagation; (2) an adaptive text-region focus module that incorporates axial attention mechanisms to enhance the model’s ability to locate text regions and suppress background interference; and (3) the integration of deformable convolution, which improves the network’s capacity to model irregular text shapes and extreme aspect ratios. To tackle the issue of data scarcity, we construct a dataset named ACST, specifically for ancient Chinese text detection. This dataset includes a wide range of scene types, such as stone inscriptions, calligraphy works, couplets, and other historical media, covering various font styles from different historical periods, thus offering strong data support for related research. Experimental results demonstrate that DRA-Net achieves significantly higher detection accuracy on the ACST dataset compared to existing methods and performs robustly in scenarios with complex backgrounds and extreme text aspect ratios. It achieves an F1-score of 72.9%, a precision of 82.8%, and a recall of 77.5%. This study provides an effective technical solution for the digitization of ancient documents and the intelligent preservation of cultural heritage, with strong theoretical significance and practical potential.