Recognizing irregular text in natural scene images is challenging due to the large variance in text appearance, such as curvature, orientation and distortion. Most existing approaches rely heavily on sophisticated model designs and/or extra fine-grained annotations, which, to some extent, increase the difficulty in algorithm implementation and data collection. In this work, we propose an easy-to-implement strong baseline for irregular scene text recognition, using offthe-shelf neural network components and only word-level annotations. It is composed of a 31-layer ResNet, an LSTMbased encoder-decoder framework and a 2-dimensional attention module. Despite its simplicity, the proposed method is robust. It achieves state-of-the-art performance on irregular text recognition benchmarks and comparable results on regular text datasets. Code is available at: https : //tinyurl.com/ShowAttendRead

Multiobjective evolutionary algorithms (MOEAs) have progressed significantly in recent decades, but most of them are designed to solve unconstrained multiobjective optimization problems. In fact, many real-world multiobjective problems contain a number of constraints. To promote research on constrained multiobjective optimization, we first propose a problem classification scheme with three primary types of difficulty, which reflect various types of challenges presented by real-world optimization problems, in order to characterize the constraint functions in constrained multiobjective optimization problems (CMOPs). These are feasibility-hardness, convergence-hardness, and diversity-hardness. We then develop a general toolkit to construct difficulty adjustable and scalable CMOPs (DAS-CMOPs, or DAS-CMaOPs when the number of objectives is greater than three) with three types of parameterized constraint functions developed to capture the three proposed types of difficulty. In fact, the combination of the three primary constraint functions with different parameters allows the construction of a large variety of CMOPs, with difficulty that can be defined by a triplet, with each of its parameters specifying the level of one of the types of primary difficulty. Furthermore, the number of objectives in this toolkit can be scaled beyond three. Based on this toolkit, we suggest nine difficulty adjustable and scalable CMOPs and nine CMaOPs, to be called DAS-CMOP1-9 and DAS-CMaOP1-9, respectively. To evaluate the proposed test problems, two popular CMOEAs—MOEA/D-CDP (MOEA/D with constraint dominance principle) and NSGA-II-CDP (NSGA-II with constraint dominance principle) and two popular constrained many-objective evolutionary algorithms (CMaOEAs)—C-MOEA/DD and C-NSGA-III—are used to compare performance on DAS-CMOP1-9 and DAS-CMaOP1-9 with a variety of difficulty triplets, respectively. The experimental results reveal that mechanisms in MOEA/D-CDP may be more effective in solving convergence-hard DAS-CMOPs, while mechanisms of NSGA-II-CDP may be more effective in solving DAS-CMOPs with simultaneous diversity-, feasibility-, and convergence-hardness. Mechanisms in C-NSGA-III may be more effective in solving feasibility-hard CMaOPs, while mechanisms of C-MOEA/DD may be more effective in solving CMaOPs with convergence-hardness. In addition, none of them can solve these problems efficiently, which stimulates us to continue to develop new CMOEAs and CMaOEAs to solve the suggested DAS-CMOPs and DAS-CMaOPs.

In the highly competitive environment, capturing and disseminating of tacit knowledge are significant to an organization’s success with the development of knowledge-based systems. However, in practical knowledge acquisition process, domain experts tend to express their judgments using multigranularity linguistic term sets, and there usually exists uncertain and incomplete information since expert knowledge is experience-based and tacit. In addition, although the technical capabilities of expert systems based on fuzzy Petri nets (FPNs) are expanding, they still fall short of meeting the increasingly complex knowledge demands. Therefore, this paper develops a theoretical model based on linguistic interval 2-tuples and interval-valued intuitionistic FPNs (IVIFPNs) for acquiring and representing tacit knowledge to increase and sustain the competitive advantages of knowledge intensive organizations. An empirical case study in medical practice is provided to demonstrate the application and feasibility of the proposed model, and the results show that it can well capture experts’ tacit knowledge and reuse the acquired knowledge productively.

No abstract

The present study employs a word association test to investigate the nature of Chinese English learners' mental lexicon by comparing the association responses of native speakers and Chinese English learners. The result shows that there are significant differences in the structure of mental lexicons between Chinese English learners and native speakers. With regard to L1 mental lexicons, Chinese English learners have poorer concentricity of association and weaker association strength. Their association is more dependent on forms. They have no established systematic and stable networks between words. The semantic network in their mental lexicon is underdeveloped. The results of the experiments have some implications for L2 vocabulary teaching and learning.