Abstract: Pedestrian detection is of paramount interest for many applications. Most promising detectors rely on discriminatively learnt classifiers, i.e., trained with annotated samples. However, the annotation step is a human intensive and subjective task worth to be minimized. By using virtual worlds we can automatically obtain precise and rich annotations. Thus, we face the question: can a pedestrian appearance model learnt in realistic virtual worlds work successfully for pedestrian detection in realworld images?. Conducted experiments show that virtual-world based training can provide excellent testing accuracy in real world, but it can also suffer the dataset shift problem as real-world based training does. Accordingly, we have designed a domain adaptation framework, V-AYLA, in which we have tested different techniques to collect a few pedestrian samples from the target domain (real world) and combine them with the many examples of the source domain (virtual world) in order to train a domain adapted pedestrian classifier that will operate in the target domain. V-AYLA reports the same detection accuracy than when training with many human-provided pedestrian annotations and testing with real-world images of the same domain. To the best of our knowledge, this is the first work demonstrating adaptation of virtual and real worlds for developing an object detector.

Abstract: The combination of the output of classifiers has been one of the strategies used to improve classification rates in general purpose classification systems. Some of the most common approaches can be explained using the Bayes' formula. In this paper, we tackle the problem of the combination of classifiers using a non-Bayesian probabilistic framework. This approach permits us to derive two linear combination rules that minimize misclassification rates under some constraints on the distribution of classifiers. In order to show the validity of this approach we have compared it with other popular combination rules from a theoretical viewpoint using a synthetic data set, and experimentally using two standard databases: the MNIST handwritten digit database and the GREC symbol database. Results on the synthetic data set show the validity of the theoretical approach. Indeed, results on real data show that the proposed methods outperform other common combination schemes.

Abstract: Handwritten Text Recognition has achieved an impressive performance in public benchmarks. However, due to the high inter- and intra-class variability between handwriting styles, such recognizers need to be trained using huge volumes of manually labeled training data. To alleviate this labor-consuming problem, synthetic data produced with TrueType fonts has been often used in the training loop to gain volume and augment the handwriting style variability. However, there is a significant style bias between synthetic and real data which hinders the improvement of recognition performance. To deal with such limitations, we propose a generative method for handwritten text-line images, which is conditioned on both visual appearance and textual content. Our method is able to produce long text-line samples with diverse handwriting styles. Once properly trained, our method can also be adapted to new target data by only accessing unlabeled text-line images to mimic handwritten styles and produce images with any textual content. Extensive experiments have been done on making use of the generated samples to boost Handwritten Text Recognition performance. Both qualitative and quantitative results demonstrate that the proposed approach outperforms the current state of the art.

Abstract: The recognition of symbols in graphic documents is an intensive research activity in the community of pattern recognition and document analysis. A key issue in the interpretation of maps, engineering drawings, diagrams, etc. is the recognition of domain dependent symbols according to a symbol database. In this work we first review the most outstanding symbol recognition methods from two different points of view: application domains and pattern recognition methods. In the second part of the paper, open and unaddressed problems involved in symbol recognition are described, analyzing their current state of art and discussing future research challenges. Thus, issues such as symbol representation, matching, segmentation, learning, scalability of recognition methods and performance evaluation are addressed in this work. Finally, we discuss the perspectives of symbol recognition concerning to new paradigms such as user interfaces in handheld computers or document database and WWW indexing by graphical content.

Abstract: Error Correcting Output Codes (ECOC) is a successful technique in multi-class classification, which is a core problem in Pattern Recognition and Machine Learning. A major advantage of ECOC over other methods is that the multi- class problem is decoupled into a set of binary problems that are solved independently. However, literature defines a general error-correcting capability for ECOCs without analyzing how it distributes among classes, hindering a deeper analysis of pair-wise error-correction. To address these limitations this paper proposes an Error-Correcting Factorization (ECF) method, our contribution is three fold: (I) We propose a novel representation of the error-correction capability, called the design matrix, that enables us to build an ECOC on the basis of allocating correction to pairs of classes. (II) We derive the optimal code length of an ECOC using rank properties of the design matrix. (III) ECF is formulated as a discrete optimization problem, and a relaxed solution is found using an efficient constrained block coordinate descent approach. (IV) Enabled by the flexibility introduced with the design matrix we propose to allocate the error-correction on classes that are prone to confusion. Experimental results in several databases show that when allocating the error-correction to confusable classes ECF outperforms state-of-the-art approaches.

Abstract: Transformer models have shown great success handling long-range interactions, making them a promising tool for modeling video. However, they lack inductive biases and scale quadratically with input length. These limitations are further exacerbated when dealing with the high dimensionality introduced by the temporal dimension. While there are surveys analyzing the advances of Transformers for vision, none focus on an in-depth analysis of video-specific designs. In this survey, we analyze the main contributions and trends of works leveraging Transformers to model video. Specifically, we delve into how videos are handled at the input level first. Then, we study the architectural changes made to deal with video more efficiently, reduce redundancy, re-introduce useful inductive biases, and capture long-term temporal dynamics. In addition, we provide an overview of different training regimes and explore effective self-supervised learning strategies for video. Finally, we conduct a performance comparison on the most common benchmark for Video Transformers (i.e., action classification), finding them to outperform 3D ConvNets even with less computational complexity.

Abstract: We present EgoACO, a deep neural architecture for video action recognition that learns to pool action-context-object descriptors from frame level features by leveraging the verb-noun structure of action labels in egocentric video datasets. The core component of EgoACO is class activation pooling (CAP), a differentiable pooling operation that combines ideas from bilinear pooling for fine-grained recognition and from feature learning for discriminative localization. CAP uses self-attention with a dictionary of learnable weights to pool from the most relevant feature regions. Through CAP, EgoACO learns to decode object and scene context descriptors from video frame features. For temporal modeling in EgoACO, we design a recurrent version of class activation pooling termed Long Short-Term Attention (LSTA). LSTA extends convolutional gated LSTM with built-in spatial attention and a re-designed output gate. Action, object and context descriptors are fused by a multi-head prediction that accounts for the inter-dependencies between noun-verb-action structured labels in egocentric video datasets. EgoACO features built-in visual explanations, helping learning and interpretation. Results on the two largest egocentric action recognition datasets currently available, EPIC-KITCHENS and EGTEA, show that by explicitly decoding action-context-object descriptors, EgoACO achieves state-of-the-art recognition performance.

Abstract: Existing color constancy methods are all based on specific assumptions such as the spatial and spectral characteristics of images. As a consequence, no algorithm can be considered as universal. However, with the large variety of available methods, the question is how to select the method that performs best for a specific image. To achieve selection and combining of color constancy algorithms, in this paper natural image statistics are used to identify the most important characteristics of color images. Then, based on these image characteristics, the proper color constancy algorithm (or best combination of algorithms) is selected for a specific image. To capture the image characteristics, the Weibull parameterization (e.g., grain size and contrast) is used. It is shown that the Weibull parameterization is related to the image attributes to which the used color constancy methods are sensitive. An MoG-classifier is used to learn the correlation and weighting between the Weibull-parameters and the image attributes (number of edges, amount of texture, and SNR). The output of the classifier is the selection of the best performing color constancy method for a certain image. Experimental results show a large improvement over state-of-the-art single algorithms. On a data set consisting of more than 11,000 images, an increase in color constancy performance up to 20 percent (median angular error) can be obtained compared to the best-performing single algorithm. Further, it is shown that for certain scene categories, one specific color constancy algorithm can be used instead of the classifier considering several algorithms.