Abstract: Although current image generation methods have reached impressive quality levels, they are still unable to produce plausible yet diverse images of handwritten words. On the contrary, when writing by hand, a great variability is observed across different writers, and even when analyzing words scribbled by the same individual, involuntary variations are conspicuous. In this work, we take a step closer to producing realistic and varied artificially rendered handwritten words. We propose a novel method that is able to produce credible handwritten word images by conditioning the generative process with both calligraphic style features and textual content. Our generator is guided by three complementary learning objectives: to produce realistic images, to imitate a certain handwriting style and to convey a specific textual content. Our model is unconstrained to any predefined vocabulary, being able to render whatever input word. Given a sample writer, it is also able to mimic its calligraphic features in a few-shot setup. We significantly advance over prior art and demonstrate with qualitative, quantitative and human-based evaluations the realistic aspect of our synthetically produced images.

Abstract: Pretraining has proven successful in Document Intelligence tasks where deluge of documents are used to pretrain the models only later to be finetuned on downstream tasks. One of the problems of the pretraining approaches is the inconsistent usage of pretraining data with different OCR engines leading to incomparable results between models. In other words, it is not obvious whether the performance gain is coming from diverse usage of amount of data and distinct OCR engines or from the proposed models. To remedy the problem, we make public the OCR annotations for IDL documents using commercial OCR engine given their superior performance over open source OCR models. The contributed dataset (OCR-IDL) has an estimated monetary value over 20K US$. It is our hope that OCR-IDL can be a starting point for future works on Document Intelligence. All of our data and its collection process with the annotations can be found in this https URL.

Abstract: Geometric Deep Learning has recently attracted significant interest in a wide range of machine learning fields, including document analysis. The application of Graph Neural Networks (GNNs) has become crucial in various document-related tasks since they can unravel important structural patterns, fundamental in key information extraction processes. Previous works in the literature propose task-driven models and do not take into account the full power of graphs. We propose Doc2Graph, a task-agnostic document understanding framework based on a GNN model, to solve different tasks given different types of documents. We evaluated our approach on two challenging datasets for key information extraction in form understanding, invoice layout analysis and table detection.

Abstract: Facial trait judgments are an important information cue for people. Recent works in the Psychology field have stated the basis of face evaluation, defining a set of traits that we evaluate from faces (e.g. dominance, trustworthiness, aggressiveness, attractiveness, threatening or intelligence among others). We rapidly infer information from others faces, usually after a short period of time (< 1000ms) we perceive a certain degree of dominance or trustworthiness of another person from the face. Although these perceptions are not necessarily accurate, they influence many important social outcomes (such as the results of the elections or the court decisions). This topic has also attracted the attention of Computer Vision scientists, and recently a computational model to automatically predict trait evaluations from faces has been proposed. These systems try to mimic the human perception by means of applying machine learning classifiers to a set of labeled data. In this paper we perform an experimental study on the specific facial features that trigger the social inferences. Using previous results from the literature, we propose to use simple similarity maps to evaluate which regions of the face influence the most the trait inferences. The correlation analysis is performed using only appearance, and the results from the experiments suggest that each trait is correlated with specific facial characteristics.

Abstract: Semantic segmentation refers to the process of assigning an object label (e.g., building, road, sidewalk, car, pedestrian) to every pixel in an image. Common approaches formulate the task as a random field labeling problem modeling the interactions between labels by combining local and contextual features such as color, depth, edges, SIFT or HoG. These models are trained to maximize the likelihood of the correct classification given a training set. However, these approaches rely on hand–designed features (e.g., texture, SIFT or HoG) and a higher computational time required in the inference process.
Therefore, in this paper, we focus on estimating the unary potentials of a conditional random field via ensembles of learned features. We propose an algorithm based on convolutional neural networks to learn local features from training data at different scales and resolutions. Then, diversification between these features is exploited using a weighted linear combination. Experiments on a publicly available database show the effectiveness of the proposed method to perform semantic road scene segmentation in still images. The algorithm outperforms appearance based methods and its performance is similar compared to state–of–the–art methods using other sources of information such as depth, motion or stereo.

Abstract: Procrustes Analysis (PA) has been a popular technique to align and build 2-D statistical models of shapes. Given a set of 2-D shapes PA is applied to remove rigid transformations. Then, a non-rigid 2-D model is computed by modeling (e.g., PCA) the residual. Although PA has been widely used, it has several limitations for modeling 2-D shapes: occluded landmarks and missing data can result in local minima solutions, and there is no guarantee that the 2-D shapes provide a uniform sampling of the 3-D space of rotations for the object. To address previous issues, this paper proposes Subspace PA (SPA). Given several instances of a 3-D object, SPA computes the mean and a 2-D subspace that can simultaneously model all rigid and non-rigid deformations of the 3-D object. We propose a discrete (DSPA) and continuous (CSPA) formulation for SPA, assuming that 3-D samples of an object are provided. DSPA extends the traditional PA, and produces unbiased 2-D models by uniformly sampling dierent views of the 3-D object. CSPA provides a continuous approach to uniformly sample the space of 3-D rotations, being more ecient in space and time. Experiments using SPA to learn 2-D models of bodies from motion capture data illustrate the benets of our approach.

Abstract: Many scene text understanding methods approach the endtoend recognition problem from a word-spotting perspective and take huge benet from using small per-image lexicons. Such customized lexicons are normally assumed as given and their source is rarely discussed.
In this paper we propose a method that generates contextualized lexicons
for scene images using only visual information. For this, we exploit
the correlation between visual and textual information in a dataset consisting
of images and textual content associated with them. Using the topic modeling framework to discover a set of latent topics in such a dataset allows us to re-rank a xed dictionary in a way that prioritizes the words that are more likely to appear in a given image. Moreover, we train a CNN that is able to reproduce those word rankings but using only the image raw pixels as input. We demonstrate that the quality of the automatically obtained custom lexicons is superior to a generic frequency-based baseline.