Unveil: Unified Visual-Textual Integration and Distillation for Multi-modal Document Retrieval

• URL: http://arxiv.org/abs/2605.24530v1
• Date: Sat, 23 May 2026 11:48:28 GMT
• Title: Unveil: Unified Visual-Textual Integration and Distillation for Multi-modal Document Retrieval
• Abstract summary: Document retrieval in real-world scenarios faces significant challenges due to diverse document formats and modalities.<n>Traditional text-based approaches rely on tailored parsing techniques that disregard layout information and are prone to errors.<n>Recent parsing-free visual methods often struggle to capture fine-grained textual semantics in text-rich scenarios.
• Score: 13.450276171264177
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Document retrieval in real-world scenarios faces significant challenges due to diverse document formats and modalities. Traditional text-based approaches rely on tailored parsing techniques that disregard layout information and are prone to errors, while recent parsing-free visual methods often struggle to capture fine-grained textual semantics in text-rich scenarios. To address these limitations, we propose \textbf{Unveil}, a novel visual-textual embedding framework that effectively integrates textual and visual features for robust document representation. Through knowledge distillation, we transfer the semantic understanding capabilities from the visual-textual embedding model to a purely visual model, enabling efficient parsing-free retrieval while preserving semantic fidelity. Experimental results demonstrate that our visual-textual embedding method surpasses existing approaches, while knowledge distillation successfully bridges the performance gap between visual-textual and visual-only methods, improving both retrieval accuracy and efficiency.

Related papers

• Informative Text-Image Alignment for Visual Affordance Learning with Foundation Models [13.874282137468517]
  We present a framework for text-guided affordance learning, which involves information-based constraints to achieve text-image alignment at feature level.<n>Specifically, we design an affordance mutual information constraint that helps learn appropriate textual prompts and task-oriented visual features simultaneously.<n>In addition, we propose an object-level information constraint that maximizes the mutual information between the visual features of a given object and the text features of the category it belongs to.
  arXiv  Detail & Related papers  (2025-09-21T13:21:16Z)
• SAViL-Det: Semantic-Aware Vision-Language Model for Multi-Script Text Detection [4.013156524547072]
  This paper introduces SAViL-Det, a novel semantic-aware vision-language model that enhances multi-script text detection.<n>The proposed framework adaptively propagates fine-grained semantic information from text prompts to visual features via cross-modal attention.<n>Experiments on challenging benchmarks demonstrate the effectiveness of the proposed approach.
  arXiv  Detail & Related papers  (2025-07-27T09:16:39Z)
• Visual Text Processing: A Comprehensive Review and Unified Evaluation [99.57846940547171]
  We present a comprehensive, multi-perspective analysis of recent advancements in visual text processing.<n>Our aim is to establish this work as a fundamental resource that fosters future exploration and innovation in the dynamic field of visual text processing.
  arXiv  Detail & Related papers  (2025-04-30T14:19:29Z)
• TextInVision: Text and Prompt Complexity Driven Visual Text Generation Benchmark [61.412934963260724]
  Existing diffusion-based text-to-image models often struggle to accurately embed text within images.<n>We introduce TextInVision, a large-scale, text and prompt complexity driven benchmark to evaluate the ability of diffusion models to integrate visual text into images.
  arXiv  Detail & Related papers  (2025-03-17T21:36:31Z)
• DoPTA: Improving Document Layout Analysis using Patch-Text Alignment [3.3181276611945267]
  We present a novel image-text alignment technique specially designed for leveraging the textual information in document images to improve performance on visual tasks.<n>Our document encoder model DoPTA - trained with this technique demonstrates strong performance on a wide range of document image understanding tasks, without requiring OCR during inference.<n>DoPTA also sets new state-of-the art results on D4LA, and FUNSD, two challenging document visual analysis benchmarks.
  arXiv  Detail & Related papers  (2024-12-17T13:26:31Z)
• Analogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Model [25.47573567479831]
  We propose a novel inference-based visual ICL approach that exploits both visual and textual prompting techniques. Our method is out-of-the-box and does not require fine-tuning or optimization.
  arXiv  Detail & Related papers  (2024-05-16T17:59:21Z)
• Seek for Incantations: Towards Accurate Text-to-Image Diffusion Synthesis through Prompt Engineering [118.53208190209517]
  We propose a framework to learn the proper textual descriptions for diffusion models through prompt learning. Our method can effectively learn the prompts to improve the matches between the input text and the generated images.
  arXiv  Detail & Related papers  (2024-01-12T03:46:29Z)
• Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs [96.54224331778195]
  We present a text-grounding document understanding model, termed TGDoc, which enhances MLLMs with the ability to discern the spatial positioning of text within images. We formulate instruction tuning tasks including text detection, recognition, and spotting to facilitate the cohesive alignment between the visual encoder and large language model. Our method achieves state-of-the-art performance across multiple text-rich benchmarks, validating the effectiveness of our method.
  arXiv  Detail & Related papers  (2023-11-22T06:46:37Z)
• Holistic Visual-Textual Sentiment Analysis with Prior Models [64.48229009396186]
  We propose a holistic method that achieves robust visual-textual sentiment analysis. The proposed method consists of four parts: (1) a visual-textual branch to learn features directly from data for sentiment analysis, (2) a visual expert branch with a set of pre-trained "expert" encoders to extract selected semantic visual features, (3) a CLIP branch to implicitly model visual-textual correspondence, and (4) a multimodal feature fusion network based on BERT to fuse multimodal features and make sentiment predictions.
  arXiv  Detail & Related papers  (2022-11-23T14:40:51Z)
• TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents [51.744527199305445]
  This paper proposes a unified end-to-end information extraction framework from visually rich documents. Text reading and information extraction can reinforce each other via a well-designed multi-modal context block. The framework can be trained in an end-to-end trainable manner, achieving global optimization.
  arXiv  Detail & Related papers  (2022-07-14T08:52:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.