Locality constraints in nominal evaluation times

The temporal arguments of VPs and adverbs must be locally coindexed with the nearest time abstraction above them (Percus 2000). In contrast, nouns, which also have time arguments, have been noted to have multiple available evaluation times (Enç 1981), often coinciding with the topic time (e.g. Musan 1995, Tonhauser 2002, Keshet 2008) or utterance time (O’Leary 2017, O’Leary & Brasoveanu 2018). I argue that we can explain the possible temporal interpretations of nouns in a way that makes their behavior consistent with that of VPs and adverbs by positing an analogous locality constraint and making a simple appeal to quantifier raising. I additionally propose that the need for a locality constraint on the coindexing of temporal arguments extends to all predicates introducing novel referents.

ГЕНЕРАТОРЫ КОНЦЕПТОВ И ПРОБЛЕМА ЛОКАЛЬНОСТИ В СЕМАНТИКЕ ВЫСКАЗЫВАНИЙ ОБ УСТАНОВКАХ DE RE

This paper presents a design for an experimentum crucis as to the particular type of locality found with the binding of variables ranging over so-called concept generators in the compositional semantics of de re readings of attitude reports (Percus, Sauerland 2003). The outcome of the experiment would show whether Santorio’s (2014) formulation of the locality constraint is adequate. If it is not, this will affect his technical proposal. This paper presents an alternative proposal couched in terms of agreement and thus capable of capturing a more flexible, relative kind of locality. Статья посвящена формальному семантическому анализу высказываний о пропозициональных установках, интерпретируемых de re. Уже ставший традиционным анализ, использующий переменные по генераторам концептов (Percus, Sauerland 2003), перепорождает (Santorio 2014); мы описываем способ, каким можно проверить, адекватно ли требование локальности означивания этих переменных, сформулированное П. Санторио. В случае отрицательного результата альтернативная формализация, предложенная Санторио, окажется неадекватной. Мы предлагаем ещё одно решение, основанное на комбинации согласования (в смысле генеративистской теории признаков) и семантики альтернатив и предсказывающее относительную, а не абсолютную локальность.

A Dictionary Learning Algorithm Based on Dictionary Reconstruction and Its Application in Face Recognition

In recent years, dictionary learning has received more and more attention in the study of face recognition. However, most dictionary learning algorithms directly use the original training samples to learn the dictionary, ignoring noise existing in the training samples. For example, there are differences between different images of the same subject due to changes in illumination, expression, etc. To address the above problems, this paper proposes the dictionary relearning algorithm (DRLA) based on locality constraint and label embedding, which can effectively reduce the influence of noise on the dictionary learning algorithm. In our proposed dictionary learning algorithm, first, the initial dictionary and coding coefficient matrix are directly obtained from the training samples, and then the original training samples are reconstructed by the product of the initial dictionary and coding coefficient matrix. Finally, the dictionary learning algorithm is reapplied to obtain a new dictionary and coding coefficient matrix, and the newly obtained dictionary and coding coefficient matrix are used for subsequent image classification. The dictionary reconstruction method can partially eliminate noise in the original training samples. Therefore, the proposed algorithm can obtain more robust classification results. The experimental results demonstrate that the proposed algorithm performs better in recognition accuracy than some state-of-the-art algorithms.

Blur Kernel Estimation by Structure Sparse Prior

Blind image deblurring tries to recover a sharp version from a blurred image, where blur kernel is usually unknown. Recently, sparse representation has been successfully applied to estimate the blur kernel. However, the sparse representation has not considered the structure relationships among original pixels. In this paper, a blur kernel estimation method is proposed by introducing the locality constraint into sparse representation framework. Both the sparsity regularization and the locality constraint are incorporated to exploit the structure relationships among pixels. The proposed method was evaluated on a real-world benchmark dataset. Experimental results demonstrate that the proposed method achieve comparable performance to the state-of-the-art methods.

A Joint Training Model for Face Sketch Synthesis

The exemplar-based method is most frequently used in face sketch synthesis because of its efficiency in representing the nonlinear mapping between face photos and sketches. However, the sketches synthesized by existing exemplar-based methods suffer from block artifacts and blur effects. In addition, most exemplar-based methods ignore the training sketches in the weight representation process. To improve synthesis performance, a novel joint training model is proposed in this paper, taking sketches into consideration. First, we construct the joint training photo and sketch by concatenating the original photo and its sketch with a high-pass filtered image of their corresponding sketch. Then, an offline random sampling strategy is adopted for each test photo patch to select the joint training photo and sketch patches in the neighboring region. Finally, a novel locality constraint is designed to calculate the reconstruction weight, allowing the synthesized sketches to have more detailed information. Extensive experimental results on public datasets show the superiority of the proposed joint training model, both from subjective perceptual and the FaceNet-based face recognition objective evaluation, compared to existing state-of-the-art sketch synthesis methods.