Abstract: 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 do not only extract and encode visual and scene text cues, but also model their interplay to generate a contextual joint embedding with richer semantics. The contextual embedding thus generated is applied to retrieval and classification tasks on multimedia images, with scene text content, to demonstrate its effectiveness. In the retrieval framework, we augment our learned text-visual semantic representation with scene text cues, to mitigate vocabulary misses that may have occurred during the semantic embedding. To deal with irrelevant or erroneous recognition of scene text, we also apply query-based attention to our text channel. We show how the multi-channel approach, involving visual semantics and scene text, improves upon state of the art.

Abstract: Nowadays, it is common in Historical Demography the use of individual-level data as a consequence of a predominant life-course approach for the understanding of the demographic behaviour, family transition, mobility, etc. Advanced record linkage is key since it allows increasing the data complexity and its volume to be analyzed. However, current methods are constrained to link data from the same kind of sources. Knowledge graph are flexible semantic representations, which allow to encode data variability and semantic relations in a structured manner.
In this paper we propose the use of knowledge graph methods to tackle record linkage tasks. The proposed method, named WERL, takes advantage of the main knowledge graph properties and learns embedding vectors to encode census information. These embeddings are properly weighted to maximize the record linkage performance. We have evaluated this method on benchmark data sets and we have compared it to related methods with stimulating and satisfactory results.

Abstract: This paper presents a new model for the task of scene text visual question answering. In this task questions about a given image can only be answered by reading and understanding scene text. Current state of the art models for this task make use of a dual attention mechanism in which one attention module attends to visual features while the other attends to textual features. A possible issue with this is that it makes difficult for the model to reason jointly about both modalities. To fix this problem we propose a new model that is based on an single attention mechanism that attends to multi-modal features conditioned to the question. The output weights of this attention module over a grid of multi-modal spatial features are interpreted as the probability that a certain spatial location of the image contains the answer text to the given question. Our experiments demonstrate competitive performance in two standard datasets with a model that is faster than previous methods at inference time. Furthermore, we also provide a novel analysis of the ST-VQA dataset based on a human performance study. Supplementary material, code, and data is made available through this link.

Abstract: This paper presents a novel method extracting biometric measures using depth sensors. Given a multi-part labeled training data, a new subject is aligned to the best model of the dataset, and soft biometrics such as lengths or circumference sizes of limbs and body are computed. The process is performed by training relevant pose clusters, defining a representative model, and fitting a 3D shape context descriptor within an iterative matching procedure. We show robust measures by applying orthogonal plates to body hull. We test our approach in a novel full-body RGB-Depth data set, showing accurate estimation of soft biometrics and better segmentation accuracy in comparison with random forest approach without requiring large training data.

Abstract: We present the results of recent challenges in Automated Computer Vision (AutoCV, renamed here for clarity AutoCV1 and AutoCV2, 2019), which are part of a series of challenge on Automated Deep Learning (AutoDL). These two competitions aim at searching for fully automated solutions for classification tasks in computer vision, with an emphasis on any-time performance. The first competition was limited to image classification while the second one included both images and videos. Our design imposed to the participants to submit their code on a challenge platform for blind testing on five datasets, both for training and testing, without any human intervention whatsoever. Winning solutions adopted deep learning techniques based on already published architectures, such as AutoAugment, MobileNet and ResNet, to reach state-of-the-art performance in the time budget of the challenge (only 20 minutes of GPU time). The novel contributions include strategies to deliver good preliminary results at any time during the learning process, such that a method can be stopped early and still deliver good performance. This feature is key for the adoption of such techniques by data analysts desiring to obtain rapidly preliminary results on large datasets and to speed up the development process. The soundness of our design was verified in several aspects: (1) Little overfitting of the on-line leaderboard providing feedback on 5 development datasets was observed, compared to the final blind testing on the 5 (separate) final test datasets, suggesting that winning solutions might generalize to other computer vision classification tasks; (2) Error bars on the winners’ performance allow us to say with confident that they performed significantly better than the baseline solutions we provided; (3) The ranking of participants according to the any-time metric we designed, namely the Area under the Learning Curve, was different from that of the fixed-time metric, i.e. AUC at the end of the fixed time budget. We released all winning solutions under open-source licenses. At the end of the AutoDL challenge series, all data of the challenge will be made publicly available, thus providing a collection of uniformly formatted datasets, which can serve to conduct further research, particularly on meta-learning.

Abstract: In this paper we present a study on the use of Action Units as mid-level features for automatically recognizing basic and subtle emotions. We propose a representation model based on mid-level facial muscular movement features. We encode these movements dynamically using the Facial Action Coding System, and propose to use these intermediate features based on Action Units (AUs) to classify emotions. AUs activations are detected fusing a set of spatiotemporal geometric and appearance features. The algorithm is validated in two applications: (i) the recognition of 7 basic emotions using the publicly available Cohn-Kanade database, and (ii) the inference of subtle emotional cues in the Newscast database. In this second scenario, we consider emotions that are perceived cumulatively in longer periods of time. In particular, we Automatically classify whether video shoots from public News TV channels refer to Good or Bad news. To deal with the different video lengths we propose a Histogram of Action Units and compute it using a sliding window strategy on the frame sequences. Our approach achieves accuracies close to human perception.

Abstract: By definition, local image features provide a compact representation of the image in which most of the image information is preserved. This capability offered by local features has been overlooked, despite being relevant in many application scenarios. In this paper, we analyze and discuss the performance of feature-driven Maximally Stable Extremal Regions (MSER) in terms of the coverage of informative image parts (completeness). This type of features results from an MSER extraction on saliency maps in which features related to objects boundaries or even symmetry axes are highlighted. These maps are intended to be suitable domains for MSER detection, allowing this detector to provide a better coverage of informative image parts. Our experimental results, which were based on a large-scale evaluation, show that feature-driven MSER have relatively high completeness values and provide more complete sets than a traditional MSER detection even when sets of similar cardinality are considered.

Abstract: IF JCR CCIA 1.303 2009 54/103
The classification of large number of object categories is a challenging trend in the pattern recognition field. In literature, this is often addressed using an ensemble of classifiers. In this scope, the Error-correcting output codes framework has demonstrated to be a powerful tool for combining classifiers. However, most state-of-the-art ECOC approaches use a linear or exponential number of classifiers, making the discrimination of a large number of classes unfeasible. In this paper, we explore and propose a minimal design of ECOC in terms of the number of classifiers. Evolutionary computation is used for tuning the parameters of the classifiers and looking for the best minimal ECOC code configuration. The results over several public UCI datasets and different multi-class computer vision problems show that the proposed methodology obtains comparable (even better) results than state-of-the-art ECOC methodologies with far less number of dichotomizers.