Abstract: Document Visual Question Answering (DocVQA) is a fast growing branch of document understanding. Despite the fact that documents contain sensitive or copyrighted information, none of the current DocVQA methods offers strong privacy guarantees.
In this work, we explore privacy in the domain of DocVQA for the first time. We highlight privacy issues in state of the art multi-modal LLM models used for DocVQA, and explore possible solutions.
Specifically, we focus on the invoice processing use case as a realistic, widely used scenario for document understanding, and propose a large scale DocVQA dataset comprising invoice documents and associated questions and answers. We employ a federated learning scheme, that reflects the real-life distribution of documents in different businesses, and we explore the use case where the ID of the invoice issuer is the sensitive information to be protected.
We demonstrate that non-private models tend to memorise, behaviour that can lead to exposing private information. We then evaluate baseline training schemes employing federated learning and differential privacy in this multi-modal scenario, where the sensitive information might be exposed through any of the two input modalities: vision (document image) or language (OCR tokens).
Finally, we design an attack exploiting the memorisation effect of the model, and demonstrate its effectiveness in probing different DocVQA models.

Abstract: In some Thai documents, a single text line of a printed document page may contain words of both Thai and Roman scripts. For the Optical Character Recognition (OCR) of such a document page it is better to identify, at first, Thai and Roman script portions and then to use individual OCR systems of the respective scripts on these identified portions. In this article, an SVM-based method is proposed for identification of word-wise printed Roman and Thai scripts from a single line of a document page. Here, at first, the document is segmented into lines and then lines are segmented into character groups (words). In the proposed scheme, we identify the script of a character group combining different character features obtained from structural shape, profile behavior, component overlapping information, topological properties, and water reservoir concept, etc. Based on the experiment on 10,000 data (words) we obtained 99.62% script identification accuracy from the proposed scheme.

Abstract: Cross-modal retrieval methods have been significantly improved in last years with the use of deep neural networks and large-scale annotated datasets such as ImageNet and Places. However, collecting and annotating such datasets requires a tremendous amount of human effort and, besides, their annotations are limited to discrete sets of popular visual classes that may not be representative of the richer semantics found on large-scale cross-modal retrieval datasets. In this paper, we present a self-supervised cross-modal retrieval framework that leverages as training data the correlations between images and text on the entire set of Wikipedia articles. Our method consists in training a CNN to predict: (1) the semantic context of the article in which an image is more probable to appear as an illustration, and (2) the semantic context of its caption. Our experiments demonstrate that the proposed method is not only capable of learning discriminative visual representations for solving vision tasks like classification, but that the learned representations are better for cross-modal retrieval when compared to supervised pre-training of the network on the ImageNet dataset.