Abstract: This paper presents a new technique to the instantaneous 3D motion estimation. The main contributions are as follows. First, we show that the 3D camera or scene velocity can be retrieved from image derivatives only assuming that the scene contains a dominant plane. Second, we propose a new robust algorithm that simultaneously provides the Least Trimmed Square solution and the percentage of inliers-the non-contaminated data. Experiments on both synthetic and real image sequences demonstrated the effectiveness of the developed method. Those experiments show that the new robust approach can outperform classical robust schemes.

Abstract: Corners and junctions are landmarks characterized by the lack of differentiability in the unit tangent to the image level curve. Detectors based on differential operators are not, by their own definition, the best posed as they require a higher degree of differentiability to yield a reliable response. We argue that a corner detector should be based on the degree of continuity of the tangent vector to the image level sets, work on the image domain and need no assumptions on neither the image local structure nor the particular geometry of the corner/junction. An operator measuring the degree of differentiability of the projection matrix on the image gradient fulfills the above requirements. Because using smoothing kernels leads to corner misplacement, we suggest an alternative fake response remover based on the receptive field inhibition of spurious details. The combination of both orientation discontinuity detection and noise inhibition produce our inhibition orientation energy (IOE) landmark locator.

Abstract: Document Visual Question Answering (DocVQA) refers to the task of answering questions from document images. Existing work on DocVQA only considers single-page documents. However, in real scenarios documents are mostly composed of multiple pages that should be processed altogether. In this work we extend DocVQA to the multi-page scenario. For that, we first create a new dataset, MP-DocVQA, where questions are posed over multi-page documents instead of single pages. Second, we propose a new hierarchical method, Hi-VT5, based on the T5 architecture, that overcomes the limitations of current methods to process long multi-page documents. The proposed method is based on a hierarchical transformer architecture where the encoder summarizes the most relevant information of every page and then, the decoder takes this summarized information to generate the final answer. Through extensive experimentation, we demonstrate that our method is able, in a single stage, to answer the questions and provide the page that contains the relevant information to find the answer, which can be used as a kind of explainability measure.

Abstract: Tabular structures in business documents offer a complementary dimension to the raw textual data. For instance, there is information about the relationships among pieces of information. Nowadays, digital mailroom applications have become a key service for workflow automation. Therefore, the detection and interpretation of tables is crucial. With the recent advances in information extraction, table detection and recognition has gained interest in document image analysis, in particular, with the absence of rule lines and unknown information about rows and columns. However, business documents usually contain sensitive contents limiting the amount of public benchmarking datasets. In this paper, we propose a graph-based approach for detecting tables in document images which do not require the raw content of the document. Hence, the sensitive content can be previously removed and, instead of using the raw image or textual content, we propose a purely structural approach to keep sensitive data anonymous. Our framework uses graph neural networks (GNNs) to describe the local repetitive structures that constitute a table. In particular, our main application domain are business documents. We have carefully validated our approach in two invoice datasets and a modern document benchmark. Our experiments demonstrate that tables can be detected by purely structural approaches.

Abstract: Change detection is the most important task for video surveillance analytics such as foreground and anomaly detection. Current foreground detectors learn models from annotated images since the goal is to generate a robust foreground model able to detect changes in all possible scenarios. Unfortunately, manual labelling is very expensive. Most advanced supervised learning techniques based on generic object detection datasets currently exhibit very poor performance when applied to surveillance datasets because of the unconstrained nature of such environments in terms of types and appearances of objects. In this paper, we take advantage of change detection for training multiple foreground detectors in an unsupervised manner. We use statistical learning techniques which exploit the use of latent parameters for selecting the best foreground model parameters for a given scenario. In essence, the main novelty of our proposed approach is to combine the where (motion segmentation) and what (learning procedure) in change detection in an unsupervised way for improving the specificity and generalization power of foreground detectors at the same time. We propose a framework based on latent support vector machines that, given a noisy initialization based on motion cues, learns the correct position, aspect ratio, and appearance of all moving objects in a particular scene. Specificity is achieved by learning the particular change detections of a given scenario, and generalization is guaranteed since our method can be applied to any possible scene and foreground object, as demonstrated in the experimental results outperforming the state-of-the-art.