Abstract: Language models are used in automatic transcription system to resolve ambiguities. This is done by limiting the vocabulary of words that can be recognized as well as estimating the n-gram probability of the words in the given text. In the context of historical documents, a non-unified spelling and the limited amount of written text pose a substantial problem for the selection of the recognizable vocabulary as well as the computation of the word probabilities. In this paper we propose for the transcription of historical Spanish text to keep the corpus for the n-gram limited to a sample of the target text, but expand the vocabulary with words gathered from external resources. We analyze the performance of such a transcription system with different sizes of external vocabularies and demonstrate the applicability and the significant increase in recognition accuracy of using up to 300 thousand external words.

Abstract: This paper presents a preliminary study on the registration and fusion of cross-spectral imaging. The objective is to evaluate the validity of widely used computer vision approaches when they are applied at different
spectral bands. In particular, we are interested in merging images from the infrared (both long wave infrared: LWIR and near infrared: NIR) and visible spectrum (VS). Experimental results with different data sets are presented.

Abstract: In this paper we present some conclusions about the advantages of having an efficient task formulation when a crowdsourcing platform is used. In particular we show how the task atomization and distribution can help to obtain results in an efficient way. Our proposal is based on a recursive splitting of the original task into a set of smaller and simpler tasks. As a result both more accurate and faster solutions are obtained. Our evaluation is performed on a set of ancient documents that need to be digitized.

Abstract: Dominance is referred to the level of influence a person has in a conversation. Dominance is an important research area in social psychology, but the problem of its automatic estimation is a very recent topic in the contexts of social and wearable computing. In this paper, we focus on dominance detection from visual cues. We estimate the correlation among observers by categorizing the dominant people in a set of face-to-face conversations. Different dominance indicators from gestural communication are defined, manually annotated, and compared to the observers opinion. Moreover, the considered indicators are automatically extracted from video sequences and learnt by using binary classifiers. Results from the three analysis shows a high correlation and allows the categorization of dominant people in public discussion video sequences.

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: This paper deals with the recognition of symbols and struc- tural textures in architectural plans using string matching techniques. A plan is represented by an attributed graph whose nodes represent characteristic points and whose edges represent segments. Symbols and textures can be seen as a set of regions, i.e. closed loops in the graph, with a particular arrangement. The search for a symbol involves a graph matching between the regions of a model graph and the regions of the graph representing the document. Discriminating a texture means a clus- tering of neighbouring regions of this graph. Both procedures involve a similarity measure between graph regions. A string codification is used to represent the sequence of outlining edges of a region. Thus, the simila- rity between two regions is defined in terms of the string edit distance between their boundary strings. The use of string matching allows the recognition method to work also under presence of distortion.

Abstract: Neural networks are very effective when trained on large datasets for a large number of iterations. However, when they are trained on non-stationary streams of data and in an online fashion, their performance is reduced (1) by the online setup, which limits the availability of data, (2) due to catastrophic forgetting because of the non-stationary nature of the data. Furthermore, several recent works (Caccia et al., 2022; Lange et al., 2023) arXiv:2205.13452 showed that replay methods used in continual learning suffer from the stability gap, encountered when evaluating the model continually (rather than only on task boundaries). In this article, we study the effect of model ensembling as a way to improve performance and stability in online continual learning. We notice that naively ensembling models coming from a variety of training tasks increases the performance in online continual learning considerably. Starting from this observation, and drawing inspirations from semi-supervised learning ensembling methods, we use a lightweight temporal ensemble that computes the exponential moving average of the weights (EMA) at test time, and show that it can drastically increase the performance and stability when used in combination with several methods from the literature.