Abstract: Many successful models for predicting attention in a scene involve three main steps: convolution with a set of filters, a center-surround mechanism and spatial pooling to construct a saliency map. However, integrating spatial information and justifying the choice of various parameter values remain open problems. In this paper we show that an efficient model of color appearance in human vision, which contains a principled selection of parameters as well as an innate spatial pooling mechanism, can be generalized to obtain a saliency model that outperforms state-of-the-art models. Scale integration is achieved by an inverse wavelet transform over the set of scale-weighted center-surround responses. The scale-weighting function (termed ECSF) has been optimized to better replicate psychophysical data on color appearance, and the appropriate sizes of the center-surround inhibition windows have been determined by training a Gaussian Mixture Model on eye-fixation data, thus avoiding ad-hoc parameter selection. Additionally, we conclude that the extension of a color appearance model to saliency estimation adds to the evidence for a common low-level visual front-end for different visual tasks.

Abstract: In this article, a form of the so-called word spotting-method is used on a large set of handwritten documents in order to identify those that contain script of similar execution. The point of departure for the investigation is the mediaeval Swedish manuscript Cod. Holm. D 3. The main scribe of this manuscript has yet not been identified in other documents. The current attempt aims at localising other documents that display a large degree of similarity in the characteristics of the script, these being possible candidates for being executed by the same hand. For this purpose, the method of word spotting has been employed, focusing on individual letters, and therefore the process is referred to as letter spotting in the article. In this process, a set of ‘g’:s, ‘h’:s and ‘k’:s have been selected as templates, and then a search has been made for close matches among the mediaeval Swedish charters. The search resulted in a number of charters that displayed great similarities with the manuscript D 3. The used letter spotting method thus proofed to be a very efficient sorting tool localising similar script samples.

Abstract: In Part 1 of the thesis, we hypothesize that salient and non-salient image regions can be estimated to be the regions which are enhanced or assimilated in standard low-level color image representations. We prove this hypothesis by adapting a low-level model of color perception into a saliency estimation model. This model shares the three main steps found in many successful models for predicting attention in a scene: convolution with a set of filters, a center-surround mechanism and spatial pooling to construct a saliency map. For such models, integrating spatial information and justifying the choice of various parameter values remain open problems. Our saliency model inherits a principled selection of parameters as well as an innate spatial pooling mechanism from the perception model on which it is based. This pooling mechanism has been fitted using psychophysical data acquired in color-luminance setting experiments. The proposed model outperforms the state-of-the-art at the task of predicting eye-fixations from two datasets. After demonstrating the effectiveness of our basic saliency model, we introduce an improved image representation, based on geometrical grouplets, that enhances complex low-level visual features such as corners and terminations, and suppresses relatively simpler features such as edges. With this improved image representation, the performance of our saliency model in predicting eye-fixations increases for both datasets.
In Part 2 of the thesis, we investigate the problem of aesthetic visual analysis. While a great deal of research has been conducted on hand-crafting image descriptors for aesthetics, little attention so far has been dedicated to the collection, annotation and distribution of ground truth data. Because image aesthetics is complex and subjective, existing datasets, which have few images and few annotations, have significant limitations. To address these limitations, we have introduced a new large-scale database for conducting Aesthetic Visual Analysis, which we call AVA. AVA contains more than 250,000 images, along with a rich variety of annotations. We investigate how the wealth of data in AVA can be used to tackle the challenge of understanding and assessing visual aesthetics by looking into several problems relevant for aesthetic analysis. We demonstrate that by leveraging the data in AVA, and using generic low-level features such as SIFT and color histograms, we can exceed state-of-the-art performance in aesthetic quality prediction tasks.
Finally, we entertain the hypothesis that low-level visual information in our saliency model can also be used to predict visual aesthetics by capturing local image characteristics such as feature contrast, grouping and isolation, characteristics thought to be related to universal aesthetic laws. We use the weighted center-surround responses that form the basis of our saliency model to create a feature vector that describes aesthetics. We also introduce a novel color space for fine-grained color representation. We then demonstrate that the resultant features achieve state-of-the-art performance on aesthetic quality classification.
As such, a promising contribution of this thesis is to show that several vision experiences – low-level color perception, visual saliency and visual aesthetics estimation – may be successfully modeled using a unified framework. This suggests a similar architecture in area V1 for both color perception and saliency and adds evidence to the hypothesis that visual aesthetics appreciation is driven in part by low-level cues.

Abstract: We propose an approach without any forgetting to continual learning for the task-aware regime, where at inference the task-label is known. By using ternary masks we can upgrade a model to new tasks, reusing knowledge from previous tasks while not forgetting anything about them. Using masks prevents both catastrophic forgetting and backward transfer. We argue -- and show experimentally -- that avoiding the former largely compensates for the lack of the latter, which is rarely observed in practice. In contrast to earlier works, our masks are applied to the features (activations) of each layer instead of the weights. This considerably reduces the number of mask parameters for each new task; with more than three orders of magnitude for most networks. The encoding of the ternary masks into two bits per feature creates very little overhead to the network, avoiding scalability issues. To allow already learned features to adapt to the current task without changing the behavior of these features for previous tasks, we introduce task-specific feature normalization. Extensive experiments on several finegrained datasets and ImageNet show that our method outperforms current state-of-the-art while reducing memory overhead in comparison to weight-based approaches.

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: Nonverbal communication is an intrinsic part in daily face-to-face meetings. A frequently observed behavior during social interactions is mirroring, in which one person tends to mimic the attitude of the counterpart. This paper shows that a computer vision system could be used to predict the perception of competence in dyadic interactions through the automatic detection of mirroring
events. To prove our hypothesis, we developed: (1) A social assistant for mirroring detection, using a wearable device which includes a video camera and (2) an automatic classifier for the perception of competence, using the number of nodding gestures and mirroring events as predictors. For our study, we used a mixed-method approach in an experimental design where 48 participants acting as customers interacted with a confederated psychologist. We found that the number of nods or mirroring events has a significant influence on the perception of competence. Our results suggest that: (1) Customer mirroring is a better predictor than psychologist mirroring; (2) the number of psychologist’s nods is a better predictor than the number of customer’s nods; (3) except for the psychologist mirroring, the computer vision algorithm we used worked about equally well whether it was acquiring images from wearable smartglasses or fixed cameras.

Abstract: This paper presents results of Document Visual Question Answering Challenge organized as part of “Text and Documents in the Deep Learning Era” workshop, in CVPR 2020. The challenge introduces a new problem – Visual Question Answering on document images. The challenge comprised two tasks. The first task concerns with asking questions on a single document image. On the other hand, the second task is set as a retrieval task where the question is posed over a collection of images. For the task 1 a new dataset is introduced comprising 50,000 questions-answer(s) pairs defined over 12,767 document images. For task 2 another dataset has been created comprising 20 questions over 14,362 document images which share the same document template.

Abstract: One interesting publicity application for Smart City environments is recognizing brand information contained in urban advertising panels. For such a purpose, a previous stage is to accurately detect and locate the position of these panels in images. This work presents an effective solution to this problem using a Single Shot Detector (SSD) based on a deep neural network architecture that minimizes the number of false detections under multiple variable conditions regarding the panels and the scene. Achieved experimental results using the Intersection over Union (IoU) accuracy metric make this proposal applicable in real complex urban images.