Related papers: Don't only Feel Read: Using Scene text to understa…

Automatically determining whether a text and a corresponding image are semantically aligned is a significant challenge for vision-language models, with applications in generative text-to-image and image-to-text tasks. In this work, we study…

Vision-language models can assess visual context in an image and generate descriptive text. While the generated text may be accurate and syntactically correct, it is often overly general. To address this, recent work has used optical…

Incorporating linguistic knowledge can improve scene text recognition, but it is questionable whether the same holds for scene text spotting, which typically involves text detection and recognition. This paper proposes a method that…

Text Spotting in the wild consists of detecting and recognizing text appearing in images (e.g. signboards, traffic signals or brands in clothing or objects). This is a challenging problem due to the complexity of the context where texts…

Scene text retrieval aims to localize and search all text instances from an image gallery, which are the same or similar to a given query text. Such a task is usually realized by matching a query text to the recognized words, outputted by…

Current text classification methods typically require a good number of human-labeled documents as training data, which can be costly and difficult to obtain in real applications. Humans can perform classification without seeing any labeled…

A popular approach to semantic image understanding is to manually tag images with keywords and then learn a mapping from vi- sual features to keywords. Manually tagging images is a subjective pro- cess and the same or very similar visual…

In this paper we propose a new document classification method, bridging discrepancies (so-called semantic gap) between the training set and the application sets of textual data. We demonstrate its superiority over classical text…

In order to convey the most content in their limited space, advertisements embed references to outside knowledge via symbolism. For example, a motorcycle stands for adventure (a positive property the ad wants associated with the product…

The detection of allusive text reuse is particularly challenging due to the sparse evidence on which allusive references rely---commonly based on none or very few shared words. Arguably, lexical semantics can be resorted to since uncovering…

We consider a document classification problem where document labels are absent but only relevant keywords of a target class and unlabeled documents are given. Although heuristic methods based on pseudo-labeling have been considered,…

Scene text detection methods based on neural networks have emerged recently and have shown promising results. Previous methods trained with rigid word-level bounding boxes exhibit limitations in representing the text region in an arbitrary…

The ability to identify sentiment in text, referred to as sentiment analysis, is one which is natural to adult humans. This task is, however, not one which a computer can perform by default. Identifying sentiments in an automated,…

We study the problem of extracting text instance contour information from images and use it to assist scene text detection. We propose a novel and effective framework for this and experimentally demonstrate that: (1) A CNN that can be…

This work presents a new and simple approach for fine-tuning pretrained word embeddings for text classification tasks. In this approach, the class in which a term appears, acts as an additional contextual variable during the fine tuning…

Text segmentation, the task of dividing a document into sections, is often a prerequisite for performing additional natural language processing tasks. Existing text segmentation methods have typically been developed and tested using clean,…

As the amount of online text increases, the demand for text categorization to aid the analysis and management of text is increasing. Text is cheap, but information, in the form of knowing what classes a text belongs to, is expensive.…

Social media is daily creating massive multimedia content with paired image and text, presenting the pressing need to automate the vision and language understanding for various multimodal classification tasks. Compared to the commonly…

Representing structured text from complex documents typically calls for different machine learning techniques, such as language models for paragraphs and convolutional neural networks (CNNs) for table extraction, which prohibits drawing…

The result listing from search engines includes a link and a snippet from the web page for each result item. The snippet in the result listing plays a vital role in assisting the user to click on it. This paper proposes a novel approach to…