Classifying a visual concept merely from its associated online textual source, such as a Wikipedia article, is an attractive research topic in zero-shot learning because it alleviates the burden of manually collecting semantic attributes. Several recent works have pursued this approach by exploring various ways of connecting the visual and text domains. This paper revisits this idea by stepping further to consider one important factor: the textual representation is usually too noisy for the zero-shot learning application. This consideration motivates us to design a simple-but-effective zero-shot learning method capable of suppressing noise in the text.
More specifically, we propose an $l_{2,1}$-norm based objective function which can simultaneously suppress the noisy signal in the text and learn a function to match the text document and visual features. We also develop an optimization algorithm to efficiently solve the resulting problem. By conducting experiments on two large datasets, we demonstrate that the proposed method significantly outperforms the competing methods which rely on online information sources but without explicit noise suppression. We further make an in-depth analysis of the proposed method and provide insight as to what kind of information in documents is useful for zero-shot learning.
Unveil: Unified Visual-Textual Integration and Distillation for Multi-modal Document Retrieval
State Key Laboratory of General Artificial Intelligence, Peking University（北京理工大学通用人工智能国家重点实验室）；School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院）；Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院航空航天信息研究所）；Key Laboratory of Target Cognition and Application Technology（目标认知与应用技术重点实验室）；Beijing Institute of Technology（北京理工大学）；Ucap Cloud（Ucap云）
SenseTime Research（商汤科技研究院）；School of Cyber Science and Engineering, Xi’an Jiaotong University（西安交通大学网络空间安全学院）
Key information extraction from document images is of paramount importance in office automation. Conventional template matching based approaches fail to generalize well to document images of unseen templates, and are not robust against text recognition errors. In this paper, we propose an end-to-end Spatial Dual-Modality Graph Reasoning method (SDMG-R) to extract key information from unstructured document images. We model document images as dual-modality graphs, nodes of which encode both the visual and textual features of detected text regions, and edges of which represent the spatial relatio…
In this paper, we present StrucTexTv2, an effective document image pre-training framework, by performing masked visual-textual prediction. It consists of two self-supervised pre-training tasks: masked image modeling and masked language modeling, based on text region-level image masking. The proposed method randomly masks some image regions according to the bounding box coordinates of text words. The objectives of our pre-training tasks are reconstructing the pixels of masked image regions and the corresponding masked tokens simultaneously. Hence the pre-trained encoder can capture more textual…
Optical Character Recognition (OCR), the task of extracting textual information from scanned documents is a vital and broadly used technology for digitizing and indexing physical documents. Existing technologies perform well for clean documents, but when the document is visually degraded, or when there are non-textual elements, OCR quality can be greatly impacted, specifically due to erroneous detections. In this paper we present an improved detection network with a masking system to improve the quality of OCR performed on documents. By filtering non-textual elements from the image we can util…
Amazon Web Services（亚马逊网络服务）；Harvard University（哈佛大学）；Cornell University（康奈尔大学）
Nowadays, as cameras are rapidly adopted in our daily routine, images of documents are becoming both abundant and prevalent. Unlike natural images that capture physical objects, document-images contain a significant amount of text with critical semantics and complicated layouts. In this work, we devise a generic unsupervised technique to learn multimodal affinities between textual entities in a document-image, considering their visual style, the content of their underlying text and their geometric context within the image. We then use these learned affinities to automatically cluster the textu…
Xuzhou Medical University（徐州医科大学）；Ping An Property & Casualty Insurance Company（平安产险公司）
Computer vision with state-of-the-art deep learning models has achieved huge success in the field of Optical Character Recognition (OCR) including text detection and recognition tasks recently. However, Key Information Extraction (KIE) from documents as the downstream task of OCR, having a large number of use scenarios in real-world, remains a challenge because documents not only have textual features extracting from OCR systems but also have semantic visual features that are not fully exploited and play a critical role in KIE. Too little work has been devoted to efficiently make full use of b…
International Institute of Information Technology - Hyderabad（海得拉巴国际信息技术学院）；Universitat Autónoma de Barcelona（巴塞罗那自治大学）；Computer Vision Centre（计算机视觉中心）
This work addresses the problem of Question Answering (QA) on handwritten document collections. Unlike typical QA and Visual Question Answering (VQA) formulations where the answer is a short text, we aim to locate a document snippet where the answer lies. The proposed approach works without recognizing the text in the documents. We argue that the recognition-free approach is suitable for handwritten documents and historical collections where robust text recognition is often difficult. At the same time, for human users, document image snippets containing answers act as a valid alternative to te…
Cornell University（康奈尔大学）；Allen Institute for AI（艾伦人工智能研究所）
Images can give us insights into the contextual meanings of words, but current image-text grounding approaches require detailed annotations. Such granular annotation is rare, expensive, and unavailable in most domain-specific contexts. In contrast, unlabeled multi-image, multi-sentence documents are abundant. Can lexical grounding be learned from such documents, even though they have significant lexical and visual overlap? Working with a case study dataset of real estate listings, we demonstrate the challenge of distinguishing highly correlated grounded terms, such as "kitchen" and "bedroom", …
The segmentation of complex images into semantic regions has seen a growing interest these last years with the advent of Deep Learning. Until recently, most existing methods for Historical Document Analysis focused on the visual appearance of documents, ignoring the rich information that textual content can offer. However, the segmentation of complex documents into semantic regions is sometimes impossible relying only on visual features and recent models embed both visual and textual information. In this paper, we focus on the use of both visual and textual information for segmenting historica…
As textual attributes like font are core design elements of document format and page style, automatic attributes recognition favor comprehensive practical applications. Existing approaches already yield satisfactory performance in differentiating disparate attributes, but they still suffer in distinguishing similar attributes with only subtle difference. Moreover, their performance drop severely in real-world scenarios where unexpected and obvious imaging distortions appear. In this paper, we aim to tackle these problems by proposing TaCo, a contrastive framework for textual attribute recognit…
Page layout analysis is a fundamental step in document processing which enables to segment a page into regions of interest. With highly complex layouts and mixed scripts, scholarly commentaries are text-heavy documents which remain challenging for state-of-the-art models. Their layout considerably varies across editions and their most important regions are mainly defined by semantic rather than graphical characteristics such as position or appearance. This setting calls for a comparison between textual, visual and hybrid approaches. We therefore assess the performances of two transformers (Lay…
AnnoPage Dataset: Dataset of Non-Textual Elements in Documents with Fine-Grained Categorization
Faculty of Information Technology, Brno University of Technology（布拉格技术学院）；Moravian Library（摩拉维亚图书馆）；National Library of the Czech Republic（捷克国家图书馆）；Library of the Czech Academy of Sciences（捷克科学院图书馆）
IBM Research - Haifa（IBM研究院（海法））；IBM Research - Zurich（IBM研究院（苏黎世））
For digitizing or indexing physical documents, Optical Character Recognition (OCR), the process of extracting textual information from scanned documents, is a vital technology. When a document is visually damaged or contains non-textual elements, existing technologies can yield poor results, as erroneous detection results can greatly affect the quality of OCR. In this paper we present a detection network dubbed BusiNet aimed at OCR of business documents. Business documents often include sensitive information and as such they cannot be uploaded to a cloud service for OCR. BusiNet was designed t…
Active consumption of digital documents has yielded scope for research in various applications, including search. Traditionally, searching within a document has been cast as a text matching problem ignoring the rich layout and visual cues commonly present in structured documents, forms, etc. To that end, we ask a mostly unexplored question: "Can we search for other similar snippets present in a target document page given a single query instance of a document snippet?". We propose MONOMER to solve this as a one-shot snippet detection task. MONOMER fuses context from visual, textual, and spatial…
We introduce a novel approach for scanned document representation to perform field extraction. It allows the simultaneous encoding of the textual, visual and layout information in a 3-axis tensor used as an input to a segmentation model. We improve the recent Chargrid and Wordgrid \cite{chargrid} models in several ways, first by taking into account the visual modality, then by boosting its robustness in regards to small datasets while keeping the inference time low. Our approach is tested on public and private document-image datasets, showing higher performances compared to the recent state-of…
IIIT Hyderabad（海得拉巴国际信息技术学院）；IISER Pune（浦那印度科学教育与研究院）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）
Infographics are documents designed to effectively communicate information using a combination of textual, graphical and visual elements. In this work, we explore the automatic understanding of infographic images by using Visual Question Answering technique.To this end, we present InfographicVQA, a new dataset that comprises a diverse collection of infographics along with natural language questions and answers annotations. The collected questions require methods to jointly reason over the document layout, textual content, graphical elements, and data visualizations. We curate the dataset with …
Visually rich documents (VRDs) are ubiquitous in daily business and life. Examples are purchase receipts, insurance policy documents, custom declaration forms and so on. In VRDs, visual and layout information is critical for document understanding, and texts in such documents cannot be serialized into the one-dimensional sequence without losing information. Classic information extraction models such as BiLSTM-CRF typically operate on text sequences and do not incorporate visual features. In this paper, we introduce a graph convolution based model to combine textual and visual information prese…
