Related papers: Benchmarking recognition results on word image dat…

In a world of digitization, optical character recognition holds the automation to written history. Optical character recognition system basically converts printed images into editable texts for better storage and usability. To be completely…

Assigning meaning to parts of image data is the goal of semantic image segmentation. Machine learning methods, specifically supervised learning is commonly used in a variety of tasks formulated as semantic segmentation. One of the major…

We propose an approach to semantic segmentation that achieves state-of-the-art supervised performance when applied in a zero-shot setting. It thus achieves results equivalent to those of the supervised methods, on each of the major semantic…

One of the ways blind people understand their surroundings is by clicking images and relying on descriptions generated by image captioning systems. Current work on captioning images for the visually impaired do not use the textual data…

Various methods have been proposed to detect objects while reducing the cost of data annotation. For instance, weakly supervised object detection (WSOD) methods rely only on image-level annotations during training. Unfortunately, data…

Image search and retrieval engines rely heavily on textual annotation in order to match word queries to a set of candidate images. A system that can automatically annotate images with meaningful text can be highly beneficial for such…

In recent years, convolutional neural networks (CNNs) took over the field of document analysis and they became the predominant model for word spotting. Especially attribute CNNs, which learn the mapping between a word image and an attribute…

Optical character recognition (OCR) is a widely used pattern recognition application in numerous domains. There are several feature-rich, general-purpose OCR solutions available for consumers, which can provide moderate to excellent…

Using deep learning, we now have the ability to create exceptionally good semantic segmentation systems; however, collecting the prerequisite pixel-wise annotations for training images remains expensive and time-consuming. Therefore, it…

While many image colorization algorithms have recently shown the capability of producing plausible color versions from gray-scale photographs, they still suffer from the problems of context confusion and edge color bleeding. To address…

Deep convolutional neural networks (CNNs) are state-of-the-art for semantic image segmentation, but typically require many labeled training samples. Obtaining 3D segmentations of medical images for supervised training is difficult and labor…

Models based on deep convolutional neural networks (CNN) have significantly improved the performance of semantic segmentation. However, learning these models requires a large amount of training images with pixel-level labels, which are very…

This paper presents a novel approach for automatically generating image descriptions: visual detectors, language models, and multimodal similarity models learnt directly from a dataset of image captions. We use multiple instance learning to…

Repositories of images with semantic and emotion content descriptions are valuable tools in many areas such as Affective Computing and Human-Computer Interaction, but they are also important in the development of multimodal searchable…

In this work, we for the first time present a method for detecting label errors in image datasets with semantic segmentation, i.e., pixel-wise class labels. Annotation acquisition for semantic segmentation datasets is time-consuming and…

Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, especially in the context of deep learning. For semantic urban…

Object recognition and detection are well-studied problems with a developed set of almost standard solutions. Identity documents recognition, classification, detection, and localization are the tasks required in a number of applications,…

Current state of the art methods for generating semantic segmentation rely heavily on a large set of images that have each pixel labeled with a class of interest label or background. Coming up with such labels, especially in domains that…

Each year, numerous segmentation and classification algorithms are invented or reused to solve problems where machine vision is needed. Generally, the efficiency of these algorithms is compared against the results given by one or many human…

Deep neural networks trained for classification have been found to learn powerful image representations, which are also often used for other tasks such as comparing images w.r.t. their visual similarity. However, visual similarity does not…