Abstract: The immense success of deep learning based methods in computer vision heavily relies on large scale training datasets. These richly annotated datasets help the network learn discriminative visual features. Collecting and annotating such datasets requires a tremendous amount of human effort and annotations are limited to popular set of classes. As an alternative, learning visual features by designing auxiliary tasks which make use of freely available self-supervision has become increasingly popular in the computer vision community.
In this paper, we put forward an idea to take advantage of multi-modal context to provide self-supervision for the training of computer vision algorithms. We show that adequate visual features can be learned efficiently by training a CNN to predict the semantic textual context in which a particular image is more probable to appear as an illustration. More specifically we use popular text embedding techniques to provide the self-supervision for the training of deep CNN.

Abstract: With the ongoing progress in digitization, huge document collections and archives have become available to a broad audience. Scanned document images can be transmitted electronically and studied simultaneously throughout the world. While this is very beneficial, it is often impossible to perform automated searches on these document collections. Optical character recognition usually fails when it comes to handwritten or historic documents. In order to address the need for exploring document collections rapidly, researchers are working on word spotting. In query-by-example word spotting scenarios, the user selects an exemplary occurrence of the query word in a document image. The word spotting system then retrieves all regions in the collection that are visually similar to the given example of the query word. The best matching regions are presented to the user and no actual transcription is required.
An important property of a word spotting system is the computational speed with which queries can be executed. In our previous work, we presented a relatively slow but high-precision method. In the present work, we will extend this baseline system to an integrated two-stage approach. In a coarse-grained first stage, we will filter document images efficiently in order to identify regions that are likely to contain the query word. In the fine-grained second stage, these regions will be analyzed with our previously presented high-precision method. Finally, we will report recognition results and query times for the well-known George Washington
benchmark in our evaluation. We achieve state-of-the-art recognition results while the query times can be reduced to 50% in comparison with our baseline.

Abstract: Optical Music Recognition refers to the task of transcribing the image of a music score into a machine-readable format. Many music scores are written in a single staff, and therefore, they could be treated as a sequence. Therefore, this work explores the use of Long Short-Term Memory (LSTM) Recurrent Neural Networks for reading the music score sequentially, where the LSTM helps in keeping the context. For training, we have used a synthetic dataset of more than 40000 images, labeled at primitive level. The experimental results are promising, showing the benefits of our approach.

Abstract: In this paper, we present a sparse-based denoising algorithm for scanned documents. This method can be applied to any kind of scanned documents with satisfactory results. Unlike other approaches, the proposed approach encodes noise documents through sparse representation and visual dictionary learning techniques without any prior noise model. Moreover, we propose a precision parameter estimator. Experiments on several datasets demonstrate the robustness of the proposed approach compared to the state-of-the-art methods on document denoising.