Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911537218715648 |
|---|---|
| author | Yan, Yibo Huo, Jiahao Feng, Guanbo Ou, Mingdong Cao, Yi Zou, Xin Liu, Shuliang Lyu, Yuanhuiyi Huang, Yu Li, Jungang Zheng, Kening Zheng, Xu Yu, Philip S. Kwok, James Hu, Xuming |
| author_facet | Yan, Yibo Huo, Jiahao Feng, Guanbo Ou, Mingdong Cao, Yi Zou, Xin Liu, Shuliang Lyu, Yuanhuiyi Huang, Yu Li, Jungang Zheng, Kening Zheng, Xu Yu, Philip S. Kwok, James Hu, Xuming |
| contents | With the rapid proliferation of multimodal information, Visual Document Retrieval (VDR) has emerged as a critical frontier in bridging the gap between unstructured visually rich data and precise information acquisition. Unlike traditional natural image retrieval, visual documents exhibit unique characteristics defined by dense textual content, intricate layouts, and fine-grained semantic dependencies. This paper presents the first comprehensive survey of the VDR landscape, specifically through the lens of the Multimodal Large Language Model (MLLM) era. We begin by examining the benchmark landscape, and subsequently dive into the methodological evolution, categorizing approaches into three primary aspects: multimodal embedding models, multimodal reranker models, and the integration of Retrieval-Augmented Generation (RAG) and Agentic systems for complex document intelligence. Finally, we identify persistent challenges and outline promising future directions, aiming to provide a clear roadmap for future multimodal document intelligence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_19961 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval Yan, Yibo Huo, Jiahao Feng, Guanbo Ou, Mingdong Cao, Yi Zou, Xin Liu, Shuliang Lyu, Yuanhuiyi Huang, Yu Li, Jungang Zheng, Kening Zheng, Xu Yu, Philip S. Kwok, James Hu, Xuming Computation and Language Information Retrieval With the rapid proliferation of multimodal information, Visual Document Retrieval (VDR) has emerged as a critical frontier in bridging the gap between unstructured visually rich data and precise information acquisition. Unlike traditional natural image retrieval, visual documents exhibit unique characteristics defined by dense textual content, intricate layouts, and fine-grained semantic dependencies. This paper presents the first comprehensive survey of the VDR landscape, specifically through the lens of the Multimodal Large Language Model (MLLM) era. We begin by examining the benchmark landscape, and subsequently dive into the methodological evolution, categorizing approaches into three primary aspects: multimodal embedding models, multimodal reranker models, and the integration of Retrieval-Augmented Generation (RAG) and Agentic systems for complex document intelligence. Finally, we identify persistent challenges and outline promising future directions, aiming to provide a clear roadmap for future multimodal document intelligence. |
| title | Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2602.19961 |