Abstract: The main objective of this thesis is to highlight the salient object in an image or in a video sequence. We address three important—but in our opinion
insufficiently investigated—aspects of saliency detection. Firstly, we start
by extending previous research on saliency which explicitly models the information provided from the context. Then, we show the importance of
explicit context modelling for saliency estimation. Several important works
in saliency are based on the usage of object proposals. However, these methods
focus on the saliency of the object proposal itself and ignore the context.
To introduce context in such saliency approaches, we couple every object
proposal with its direct context. This allows us to evaluate the importance
of the immediate surround (context) for its saliency. We propose several
saliency features which are computed from the context proposals including
features based on omni-directional and horizontal context continuity. Secondly,
we investigate the usage of top-downmethods (high-level semantic
information) for the task of saliency prediction since most computational
methods are bottom-up or only include few semantic classes. We propose
to consider a wider group of object classes. These objects represent important
semantic information which we will exploit in our saliency prediction
approach. Thirdly, we develop a method to detect video saliency by computing
saliency from supervoxels and optical flow. In addition, we apply the
context features developed in this thesis for video saliency detection. The
method combines shape and motion features with our proposed context
features. To summarize, we prove that extending object proposals with their
direct context improves the task of saliency detection in both image and
video data. Also the importance of the semantic information in saliency
estimation is evaluated. Finally, we propose a newmotion feature to detect
saliency in video data. The three proposed novelties are evaluated on standard
saliency benchmark datasets and are shown to improve with respect to
state-of-the-art.

Abstract: In this dissertation, we explore different ways to perform human action recognition in video clips. We focus on data efficiency, proposing new approaches that alleviate the need for laborious and time-consuming manual data annotation. In the first part of this dissertation, we start by analyzing previous state-of-the-art models, comparing their differences and similarities in order to pinpoint where their real strengths come from. Leveraging this information, we then proceed to boost the classification accuracy of shallow models to levels that rival deep neural networks. We introduce hybrid video classification architectures based on carefully designed unsupervised representations of handcrafted spatiotemporal features classified by supervised deep networks. We show in our experiments that our hybrid model combine the best of both worlds: it is data efficient (trained on 150 to 10,000 short clips) and yet improved significantly on the state of the art, including deep models trained on millions of manually labeled images and videos. In the second part of this research, we investigate the generation of synthetic training data for action recognition, as it has recently shown promising results for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation and other computer graphics techniques of modern game engines. We generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for “Procedural Human Action Videos”. It contains a total of 39,982 videos, with more than 1,000 examples for each action of 35 categories. Our approach is not limited to existing motion capture sequences, and we procedurally define 14 synthetic actions. We then introduce deep multi-task representation learning architectures to mix synthetic and real videos, even if the action categories differ. Our experiments on the UCF-101 and HMDB-51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance, outperforming fine-tuning state-of-the-art unsupervised generative models of videos.

Abstract: Automatic analyzing humans in photographs or videos has great potential applications in computer vision, including medical diagnosis, sports, entertainment, movie editing and surveillance, just to name a few. Body, face and hand are the most studied components of humans. Body has many variabilities in shape and clothing along with high degrees of freedom in pose. Face has many muscles causing many visible deformity, beside variable shape and hair style. Hand is a small object, moving fast and has high degrees of freedom. Adding human characteristics to all aforementioned variabilities makes human analysis quite a challenging task.
In this thesis, we developed human segmentation in different modalities. In a first scenario, we segmented human body and hand in depth images using example-based shape warping. We developed a shape descriptor based on shape context and class probabilities of shape regions to extract nearest neighbors. We then considered rigid affine alignment vs. nonrigid iterative shape warping. In a second scenario, we segmented face in RGB images using convolutional neural networks (CNN). We modeled conditional random field with recurrent neural networks. In our model pair-wise kernels are not fixed and learned during training. We trained the network end-to-end using adversarial networks which improved hair segmentation by a high margin.
We also worked on 3D hand pose estimation in depth images. In a generative approach, we fitted a finger model separately for each finger based on our example-based rigid hand segmentation. We minimized an energy function based on overlapping area, depth discrepancy and finger collisions. We also applied linear models in joint trajectory space to refine occluded joints based on visible joints error and invisible joints trajectory smoothness. In a CNN-based approach, we developed a tree-structure network to train specific features for each finger and fused them for global pose consistency. We also formulated physical and appearance constraints as loss functions.
Finally, we developed a number of applications consisting of human soft biometrics measurement and garment retexturing. We also generated some datasets in this thesis consisting of human segmentation, synthetic hand pose, garment retexturing and Italian gestures.

Abstract: The original idea of this project was to study the role of colour in the challenging task of object recognition. We started by extending previous research on colour naming showing that it is feasible to capture colour terms through parsimonious ellipsoids. Although, the results of our model exceeded state-of-the-art in two benchmark datasets, we realised that the two phenomena of metameric lights and colour constancy must be addressed prior to any further colour processing. Our investigation of metameric pairs reached the conclusion that they are infrequent in real world scenarios. Contrary to that, the illumination of a scene often changes dramatically. We addressed this issue by proposing a colour constancy model inspired by the dynamical centre-surround adaptation of neurons in the visual cortex. This was implemented through two overlapping asymmetric Gaussians whose variances and heights are adjusted according to the local contrast of pixels. We complemented this model with a generic contrast-variant pooling mechanism that inversely connect the percentage of pooled signal to the local contrast of a region. The results of our experiments on four benchmark datasets were indeed promising: the proposed model, although simple, outperformed even learning-based approaches in many cases. Encouraged by the success of our contrast-variant surround modulation, we extended this approach to detect boundaries of objects. We proposed an edge detection model based on the first derivative of the Gaussian kernel. We incorporated four types of surround: full, far, iso- and orthogonal-orientation. Furthermore, we accounted for the pooling mechanism at higher cortical areas and the shape feedback sent to lower areas. Our results in three benchmark datasets showed significant improvement over non-learning algorithms.
To summarise, we demonstrated that biologically-inspired models offer promising solutions to computer vision problems, such as, colour naming, colour constancy and edge detection. We believe that the greatest contribution of this Ph.D dissertation is modelling the concept of dynamic surround modulation that shows the significance of contrast-variant surround integration. The models proposed here are grounded on only a portion of what we know about the human visual system. Therefore, it is only natural to complement them accordingly in future works.

Abstract: Visual recognition is one of the main problems in computer vision that attempts to solve image understanding by deciding what objects are in images. This problem can be computationally solved by using relevant sets of visual features, such as edges, corners, color or more complex object parts. This thesis contributes to how color features have to be represented for recognition tasks.
Image features can be extracted following two different approaches. A first approach is defining handcrafted descriptors of images which is then followed by a learning scheme to classify the content (named flat schemes in Kruger et al. (2013). In this approach, perceptual considerations are habitually used to define efficient color features. Here we propose a new flat color descriptor based on the extension of color channels to boost the representation of spatio-chromatic contrast that surpasses state-of-the-art approaches. However, flat schemes present a lack of generality far away from the capabilities of biological systems. A second approach proposes evolving these flat schemes into a hierarchical process, like in the visual cortex. This includes an automatic process to learn optimal features. These deep schemes, and more specifically Convolutional Neural Networks (CNNs), have shown an impressive performance to solve various vision problems. However, there is a lack of understanding about the internal representation obtained, as a result of automatic learning. In this thesis we propose a new methodology to explore the internal representation of trained CNNs by defining the Neuron Feature as a visualization of the intrinsic features encoded in each individual neuron. Additionally, and inspired by physiological techniques, we propose to compute different neuron selectivity indexes (e.g., color, class, orientation or symmetry, amongst others) to label and classify the full CNN neuron population to understand learned representations.
Finally, using the proposed methodology, we show an in-depth study on how color is represented on a specific CNN, trained for object recognition, that competes with primate representational abilities (Cadieu et al (2014)). We found several parallelisms with biological visual systems: (a) a significant number of color selectivity neurons throughout all the layers; (b) an opponent and low frequency representation of color oriented edges and a higher sampling of frequency selectivity in brightness than in color in 1st layer like in V1; (c) a higher sampling of color hue in the second layer aligned to observed hue maps in V2; (d) a strong color and shape entanglement in all layers from basic features in shallower layers (V1 and V2) to object and background shapes in deeper layers (V4 and IT); and (e) a strong correlation between neuron color selectivities and color dataset bias.

Abstract: Latest advances in digitization techniques have fostered the interest in creating digital copies of collections of documents. Digitized documents permit an easy maintenance, loss-less storage, and efficient ways for transmission and to perform information retrieval processes. This situation has opened a new market niche to develop systems able to automatically extract and analyze information contained in these collections, specially in the ambit of the business activity.
Due to the great variety of types of documents this is not a trivial task. For instance, the automatic extraction of numerical data from invoices differs substantially from a task of text recognition in historical documents. However, in order to extract the information of interest, is always necessary to identify the area of the document where it is located. In the area of Document Analysis we refer to this process as layout analysis, which aims at identifying and categorizing the different entities that compose the document, such as text regions, pictures, text lines, or tables, among others. To perform this task it is usually necessary to incorporate a prior knowledge about the task into the analysis process, which can be modeled by defining a set of contextual relations between the different entities of the document. The use of context has proven to be useful to reinforce the recognition process and improve the results on many computer vision tasks. It presents two fundamental questions: What kind of contextual information is appropriate for a given task, and how to incorporate this information into the models.
In this thesis we study several ways to incorporate contextual information to the task of document layout analysis, and to the particular case of handwritten text line segmentation. We focus on the study of Probabilistic Graphical Models and other mechanisms for this purpose, and propose several solutions to these problems. First, we present a method for layout analysis based on Conditional Random Fields. With this model we encode local contextual relations between variables, such as pair-wise constraints. Besides, we encode a set of structural relations between different classes of regions at feature level. Second, we present a method based on 2D-Probabilistic Context-free Grammars to encode structural and hierarchical relations. We perform a comparative study between Probabilistic Graphical Models and this syntactic approach. Third, we propose a method for structured documents based on Bayesian Networks to represent the document structure, and an algorithm based in the Expectation-Maximization to find the best configuration of the page. We perform a thorough evaluation of the proposed methods on two particular collections of documents: a historical collection composed of ancient structured documents, and a collection of contemporary documents. In addition, we present a general method for the task of handwritten text line segmentation. We define a probabilistic framework where we combine the EM algorithm with variational approaches for computing inference and parameter learning on a Markov Random Field. We evaluate our method on several collections of documents, including a general dataset of annotated administrative documents. Results demonstrate the applicability of our method to real problems, and the contribution of the use of contextual information to this kind of problems.

Abstract: In this work, we develop a generic framework that is able to handle the document retrieval problem in various scenarios such as searching for full page matches or retrieving the counterparts for specific document areas, focusing on their structural similarity or letting their visual resemblance to play a dominant role. Based on the spatial indexing technique, we propose to search for matches of local key-region pairs carrying both structural and visual information from the collection while a scheme allowing to adjust the relative contribution of structural and visual similarity is presented.
Based on the fact that the structure of documents is tightly linked with the distance among their elements, we firstly introduce an efficient detector named Distance Transform based Maximally Stable Extremal Regions (DTMSER). We illustrate that this detector is able to efficiently extract the structure of a document image as a dendrogram (hierarchical tree) of multi-scale key-regions that roughly correspond to letters, words and paragraphs. We demonstrate that, without benefiting from the structure information, the key-regions extracted by the DTMSER algorithm achieve better results comparing with state-of-the-art methods while much less amount of key-regions are employed.
We subsequently propose a pair-wise Bag of Words (BoW) framework to efficiently embed the explicit structure extracted by the DTMSER algorithm. We represent each document as a list of key-region pairs that correspond to the edges in the dendrogram where inclusion relationship is encoded. By employing those structural key-region pairs as the pooling elements for generating the histogram of features, the proposed method is able to encode the explicit inclusion relations into a BoW representation. The experimental results illustrate that the pair-wise BoW, powered by the embedded structural information, achieves remarkable improvement over the conventional BoW and spatial pyramidal BoW methods.
To handle various retrieval scenarios in one framework, we propose to directly query a series of key-region pairs, carrying both structure and visual information, from the collection. We introduce the spatial indexing techniques to the document retrieval community to speed up the structural relationship computation for key-region pairs. We firstly test the proposed framework in a full page retrieval scenario where structurally similar matches are expected. In this case, the pair-wise querying method achieves notable improvement over the BoW and spatial pyramidal BoW frameworks. Furthermore, we illustrate that the proposed method is also able to handle focused retrieval situations where the queries are defined as a specific interesting partial areas of the images. We examine our method on two types of focused queries: structure-focused and exact queries. The experimental results show that, the proposed generic framework obtains nearly perfect precision on both types of focused queries while it is the first framework able to tackle structure-focused queries, setting a new state of the art in the field.
Besides, we introduce a line verification method to check the spatial consistency among the matched key-region pairs. We propose a computationally efficient version of line verification through a two step implementation. We first compute tentative localizations of the query and subsequently employ them to divide the matched key-region pairs into several groups, then line verification is performed within each group while more precise bounding boxes are computed. We demonstrate that, comparing with the standard approach (based on RANSAC), the line verification proposed generally achieves much higher recall with slight loss on precision on specific queries.

Abstract: As any iterative technique, it is a necessary condition a stop criterion for terminating Evolutionary Algorithms (EA). In the case of optimization methods, the algorithm should stop at the time it has reached a steady state so it can not improve results anymore. Assessing the reliability of termination conditions for EAs is of prime importance. A wrong or weak stop criterion can negatively aect both the computational eort and the nal result.
In this Thesis, we introduce a statistical framework for assessing whether a termination condition is able to stop EA at its steady state. In one hand a numeric approximation to steady states to detect the point in which EA population has lost its diversity has been presented for EA termination. This approximation has been applied to dierent EA paradigms based on diversity and a selection of functions covering the properties most relevant for EA convergence. Experiments show that our condition works regardless of the search space dimension and function landscape and Dierential Evolution (DE) arises as the best paradigm. On the other hand, we use a regression model in order to determine the requirements ensuring that a measure derived from EA evolving population is related to the distance to the optimum in xspace.
Our theoretical framework is analyzed across several benchmark test functions
and two standard termination criteria based on function improvement in f-space and EA population x-space distribution for the DE paradigm. Results validate our statistical framework as a powerful tool for determining the capability of a measure for terminating EA and select the x-space distribution as the best-suited for accurately stopping DE in real-world applications.