Current visual question answering datasets do not consider the rich semantic information conveyed by text within an image. In this work, we present a new dataset, ST-VQA, that aims to highlight the importance of exploiting high-level semantic information present in images as textual cues in the VQA process. We use this dataset to define a series of tasks of increasing difficulty for which reading the scene text in the context provided by the visual information is necessary to reason and generate an appropriate answer. We propose a new evaluation metric for these tasks to account both for reasoning errors as well as shortcomings of the text recognition module. In addition we put forward a series of baseline methods, which provide further insight to the newly released dataset, and set the scene for further research.
Images with visual and scene text content are ubiquitous in everyday life. However current image interpretation systems are mostly limited to using only the visual features, neglecting to leverage the scene text content. In this paper we propose to jointly use scene text and visual channels for robust semantic interpretation of images. We undertake the task of matching Advertisement images against their human generated statements that describe the action that the ad prompts and the rationale it provides for taking this action. We extract the scene text and generate semantic and lexical text representations, which are used in the interpretation of the Ad Image. To deal with irrelevant or erroneous detection of scene text, we use a text attention scheme. We also learn an embedding of the visual channel,\ie visual features based on detected symbolism and objects, into a semantic embedding space, leveraging text semantics obtained from scene text. We show how the multi channel approach, involving visual semantics and scene text, improves upon the current state of the art.
We propose a framework for automated classification of Advertisement Images, using not just Visual features but also Textual cues extracted from embedded text. Our approach takes inspiration from the assumption that Ad images contain meaningful textual content, that can provide discriminative semantic interpretetion, and can thus aid in classifcation tasks. To this end, we develop a framework using off-the-shelf components, and demonstrate the effectiveness of Textual cues in semantic Classfication tasks.
In this work we introduce a cross modal image retrieval system that allows both text and sketch as input modalities for the query. A cross-modal deep network architecture is formulated to jointly model the sketch and text input modalities as well as the the image output modality, learning a common embedding between text and images and between sketches and images. In addition, an attention model is used to selectively focus the attention on the different objects of the image, allowing for retrieval with multiple objects in the query. Experiments show that the proposed method performs the best in both single and multiple object image retrieval in standard datasets.
This paper proposes a region based convolutional neural network for segmentation-free word spotting. Our net- work takes as input an image and a set of word candidate bound- ing boxes and embeds all bounding boxes into an embedding space, where word spotting can be casted as a simple nearest neighbour search between the query representation and each of the candidate bounding boxes. We make use of PHOC embedding as it has previously achieved significant success in segmentation- based word spotting. Word candidates are generated using a simple procedure based on grouping connected components using some spatial constraints. Experiments show that R-PHOC which operates on images directly can improve the current state-of- the-art in the standard GW dataset and performs as good as PHOCNET in some cases designed for segmentation based word spotting.
In this paper we propose an approach to lexicon-free recognition of text in scene images. Our approach relies on a LSTM-based soft visual attention model learned from convolutional features. A set of feature vectors are derived from an intermediate convolutional layer corresponding to different areas of the image. This permits encoding of spatial information into the image representation. In this way, the framework is able to learn how to selectively focus on different parts of the image. At every time step the recognizer emits one character using a weighted combination of the convolutional feature vectors according to the learned attention model. Training can be done end-to-end using only word level annotations. In addition, we show that modifying the beam search algorithm by integrating an explicit language model leads to significantly better recognition results. We validate the performance of our approach on standard SVT and ICDAR'03 scene text datasets, showing state-of-the-art performance in unconstrained text recognition.
In this paper we propose a segmentation-free query by string word spotting method. Both the documents and query strings are encoded using a recently proposed word representa- tion that projects images and strings into a common atribute space based on a pyramidal histogram of characters(PHOC). These attribute models are learned using linear SVMs over the Fisher Vector representation of the images along with the PHOC labels of the corresponding strings. In order to search through the whole page, document regions are indexed per character bi- gram using a similar attribute representation. On top of that, we propose an integral image representation of the document using a simplified version of the attribute model for efficient computation. Finally we introduce a re-ranking step in order to boost retrieval performance. We show state-of-the-art results for segmentation-free query by string word spotting in single-writer and multi-writer standard datasets