Abstract: To cope with the tremendous variations of writing styles encountered between different individuals, unconstrained automatic handwriting recognition systems need to be trained on large sets of labeled data. Traditionally, the training data has to be labeled manually, which is a laborious and costly process. Semi-supervised learning techniques offer methods to utilize unlabeled data, which can be obtained cheaply in large amounts in order, to reduce the need for labeled data. In this paper, we propose the use of Co-Training for improving the recognition accuracy of two weakly trained handwriting recognition systems. The first one is based on Recurrent Neural Networks while the second one is based on Hidden Markov Models. On the IAM off-line handwriting database we demonstrate a significant increase of the recognition accuracy can be achieved with Co-Training for single word recognition.

Abstract: Video alignment consists of integrating multiple video sequences recorded independently into a single video sequence. This means to register both in time (synchronize
frames) and space (image registration) so that the two videos sequences can be fused
or compared pixel–wise. In spite of being relatively unknown, many applications today may benefit from the availability of robust and efficient video alignment methods.
For instance, video surveillance requires to integrate video sequences that are recorded
of the same scene at different times in order to detect changes. The problem of aligning videos has been addressed before, but in the relatively simple cases of fixed or rigidly attached cameras and simultaneous acquisition. In addition, most works rely
on restrictive assumptions which reduce its difficulty such as linear time correspondence or the knowledge of the complete trajectories of corresponding scene points on the images; to some extent, these assumptions limit the practical applicability of the solutions developed until now. In this thesis, we focus on the challenging problem of aligning sequences recorded at different times from independent moving cameras following similar but not coincident trajectories. More precisely, this thesis covers four studies that advance the state-of-the-art in video alignment. First, we focus on analyzing and developing a probabilistic framework for video alignment, that is, a principled way to integrate multiple observations and prior information. In this way, two different approaches are presented to exploit the combination of several purely visual features (image–intensities, visual words and dense motion field descriptor), and
global positioning system (GPS) information. Second, we focus on reformulating the
problem into a single alignment framework since previous works on video alignment
adopt a divide–and–conquer strategy, i.e., first solve the synchronization, and then
register corresponding frames. This also generalizes the ’classic’ case of fixed geometric transform and linear time mapping. Third, we focus on exploiting directly the
time domain of the video sequences in order to avoid exhaustive cross–frame search.
This provides relevant information used for learning the temporal mapping between
pairs of video sequences. Finally, we focus on adapting these methods to the on–line
setting for road detection and vehicle geolocation. The qualitative and quantitative
results presented in this thesis on a variety of real–world pairs of video sequences show that the proposed method is: robust to varying imaging conditions, different image
content (e.g., incoming and outgoing vehicles), variations on camera velocity, and
different scenarios (indoor and outdoor) going beyond the state–of–the–art. Moreover, the on–line video alignment has been successfully applied for road detection and
vehicle geolocation achieving promising results.

Abstract: Visual categorization is important to manage large collections of digital images and video, where textual meta-data is often incomplete or simply unavailable. The bag-of-words model has become the most powerful method for visual categorization of images and video. Despite its high accuracy, a severe drawback of this model is its high computational cost. As the trend to increase computational power in newer CPU and GPU architectures is to increase their level of parallelism, exploiting this parallelism becomes an important direction to handle the computational cost of the bag-of-words approach. When optimizing a system based on the bag-of-words approach, the goal is to minimize the time it takes to process batches of images. Additionally, we also consider power usage as an evaluation metric. In this paper, we analyze the bag-of-words model for visual categorization in terms of computational cost and identify two major bottlenecks: the quantization step and the classification step. We address these two bottlenecks by proposing two efficient algorithms for quantization and classification by exploiting the GPU hardware and the CUDA parallel programming model. The algorithms are designed to (1) keep categorization accuracy intact, (2) decompose the problem and (3) give the same numerical results. In the experiments on large scale datasets it is shown that, by using a parallel implementation on the Geforce GTX260 GPU, classifying unseen images is 4.8 times faster than a quad-core CPU version on the Core i7 920, while giving the exact same numerical results. In addition, we show how the algorithms can be generalized to other applications, such as text retrieval and video retrieval. Moreover, when the obtained speedup is used to process extra video frames in a video retrieval benchmark, the accuracy of visual categorization is improved by 29%.

Abstract: We address the task of estimating 3D human poses from monocular camera sequences. Many works make use of multiple consecutive frames for the estimation of a 3D pose in a frame. Although such an approach should ease the pose estimation task substantially since multiple consecutive frames allow to solve for 2D projection ambiguities in principle, it has not yet been investigated systematically how much we can improve the 3D pose estimates when using multiple consecutive frames opposed to single frame information. In this paper we analyze the difference in quality of 3D pose estimates based on different numbers of consecutive frames from which 2D pose estimates are available. We validate the use of temporal information on two major different approaches for human pose estimation – modeling and learning approaches. The results of our experiments show that both learning and modeling approaches benefit from using multiple frames opposed to single frame input but that the benefit is small when the 2D pose estimates show a high quality in terms of precision.

Abstract: We describe an equivalence of categories between the category of mixed Hodge structures and a category of equivariant vector bundles on a toric model of the complex projective plane which verify some semistability condition. We then apply this correspondence to define an invariant which generalizes the notion of R-split mixed Hodge structure and give calculations for the first group of cohomology of possibly non smooth or non-complete curves of genus 0 and 1. Finally, we describe some extension groups of mixed Hodge structures in terms of equivariant extensions of coherent sheaves. © 2011 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim

Abstract: We present a method for spotting a subgraph in a graph repository. Subgraph spotting is a very interesting research problem for various application domains where the use of a relational data structure is mandatory. Our proposed method accomplishes subgraph spotting through graph embedding. We achieve automatic indexation of a graph repository during off-line learning phase, where we (i) break the graphs into 2-node sub graphs (a.k.a. cliques of order 2), which are primitive building-blocks of a graph, (ii) embed the 2-node sub graphs into feature vectors by employing our recently proposed explicit graph embedding technique, (iii) cluster the feature vectors in classes by employing a classic agglomerative clustering technique, (iv) build an index for the graph repository and (v) learn a Bayesian network classifier. The subgraph spotting is achieved during the on-line querying phase, where we (i) break the query graph into 2-node sub graphs, (ii) embed them into feature vectors, (iii) employ the Bayesian network classifier for classifying the query 2-node sub graphs and (iv) retrieve the respective graphs by looking-up in the index of the graph repository. The graphs containing all query 2-node sub graphs form the set of result graphs for the query. Finally, we employ the adjacency matrix of each result graph along with a score function, for spotting the query graph in it. The proposed subgraph spotting method is equally applicable to a wide range of domains, offering ease of query by example (QBE) and granularity of focused retrieval. Experimental results are presented for graphs generated from two repositories of electronic and architectural document images.