Abstract: This note introduces a visual attention model of text localization in real-world scenes. The core of the model built upon the proto-object concept is discussed. It is shown how such dynamic mid-level representation of the scene can be derived in the framework of an action-perception loop engaging salience, text information value computation, and eye guidance mechanisms.
Preliminary results that compare model generated scanpaths with those eye-tracked from human subjects are presented.

Abstract: This work aims at the automatic polyp detection by using a model of polyp appearance in the context of the analysis of colonoscopy videos. Our method consists of three stages: region segmentation, region description and region classification. The performance of our region segmentation method guarantees that if a polyp is present in the image, it will be exclusively and totally contained in a single region. The output of the algorithm also defines which regions can be considered as non-informative. We define as our region descriptor the novel Sector Accumulation-Depth of Valleys Accumulation (SA-DOVA), which provides a necessary but not sufficient condition for the polyp presence. Finally, we classify our segmented regions according to the maximal values of the SA-DOVA descriptor. Our preliminary classification results are promising, especially when classifying those parts of the image that do not contain a polyp inside.

Abstract: Pedestrian classifiers decide which image windows contain a pedestrian. In practice, such classifiers provide a relatively high response at neighbor windows overlapping a pedestrian, while the responses around potential false positives are expected to be lower. An analogous reasoning applies for image sequences. If there is a pedestrian located within a frame, the same pedestrian is expected to appear close to the same location in neighbor frames. Therefore, such a location has chances of receiving high classification scores during several frames, while false positives are expected to be more spurious. In this paper we propose to exploit such correlations for improving the accuracy of base pedestrian classifiers. In particular, we propose to use two-stage classifiers which not only rely on the image descriptors required by the base classifiers but also on the response of such base classifiers in a given spatiotemporal neighborhood. More specifically, we train pedestrian classifiers using a stacked sequential learning (SSL) paradigm. We use a new pedestrian dataset we have acquired from a car to evaluate our proposal at different frame rates. We also test on a well known dataset: Caltech. The obtained results show that our SSL proposal boosts detection accuracy significantly with a minimal impact on the computational cost. Interestingly, SSL improves more the accuracy at the most dangerous situations, i.e. when a pedestrian is close to the camera.

Abstract: Lifelogging devices based on photo/video are spreading faster everyday. This growth can represent great benefits to develop methods for extraction of meaningful information about the user wearing the device and his/her environment. In this paper, we propose a semi-supervised strategy for easily discovering objects relevant to the person wearing a first-person camera. The egocentric video sequence acquired by the camera, uses both the appearance extracted by means of a deep convolutional neural network and an object refill methodology that allow to discover objects even in case of small amount of object appearance in the collection of images. We validate our method on a sequence of 1000 egocentric daily images and obtain results with an F-measure of 0.5, 0.17 better than the state of the art approach.

Abstract: We present an eye tracking system that works with regular webcams. We base our work on open source CVC Eye Tracker [7] and we propose a number of improvements and a novel gaze estimation method. The new method uses features extracted from iris segmentation and it does not fall into the traditional categorization of appearance–based/model–based methods. Our experiments show that our approach reduces the gaze estimation errors by 34 % in the horizontal direction and by 12 % in the vertical direction compared to the baseline system.

Abstract: Historical records of daily activities provide intriguing insights into the life of our ancestors, useful for demographic and genealogical research. For example, marriage license books have been used for centuries by ecclesiastical and secular institutions to register marriages. These books follow a simple structure of the text in the records with a evolutionary vocabulary, mainly composed of proper names that change along the time. This distinct vocabulary makes automatic transcription and semantic information extraction difficult tasks. In previous works we studied the use of category-based language models and how a Grammatical Inference technique known as MGGI could improve the accuracy of these tasks. In this work we analyze the main causes of the semantic errors observed in previous results and apply a better implementation of the MGGI technique to solve these problems. Using the resulting language model, transcription and information extraction experiments have been carried out, and the results support our proposed approach.

Abstract: We propose a new Graph Embedding (GEM) method that takes advantages of structural pattern representation. It models an Attributed Graph (AG) as a Probabilistic Graphical Model (PGM). Then, it learns the parameters of this PGM presented by a vector. This vector is a signature of AG in a lower dimensional vectorial space. We apply Structured Support Vector Machines (SSVM) to process classification task. As first tentative, results on the GREC dataset are encouraging enough to go further on this direction.

Abstract: It is commonly known the natural tendency of artificial neural networks to completely and abruptly forget previously known information when learning new information. We explore this behaviour in the context of Face Verification on the recently proposed Disguised Faces in the Wild dataset (DFW). We empirically evaluate several commonly used DCNN architectures on Face Recognition and distill some insights about the effect of sequential learning on distinct identities from different datasets, showing that the catastrophic forgetness phenomenon is present even in feature embeddings fine-tuned on different tasks from the original domain.