In view of the problem that the traditional learning service recommendation does not fully consider the distinct differences between individuals, it is easy to lead to the contradiction between unchanging learning resources and learners’ personalized learning needs that are constantly improving, so an adaptive learning service recommendation improvement algorithm based on big data is proposed. Idea is based on adaptive learning platform and function modules. We consider the individual differences between students, to students as the center, collect students’ personalized learning demand data, and according to the data information to build student demand model. On the basis of using data mining methods for clustering recommendation service resources in learning, the adaptive recommend according to students’ individual need is proposed. The experimental results show that the adaptive learning service recommendation algorithm based on big data has high recommendation accuracy, coverage rate and recall rate, which is of great significance in the actual learning service recommendation.

Scene text detection is attracting more and more attention and has become an important topic in machine vision research. With the development of mobile IoT (Internet of things) and deep learning technology, text detection research has made significant progress. This survey aims to summarize and analyze the main challenges and significant progress in scene text detection research. In this paper, we first introduce the history and progress of scene text detection and classify the traditional methods and deep learning-based methods in detail, pointing out the corresponding key issues and techniques. Then, we introduce commonly used benchmark datasets and evaluation protocols and identify state-of-the-art algorithms by comparison. Finally, we summarize and predict potential future research directions.

The task of multi-hop question generation (QG) seeks to generate questions that require a complex reasoning process that spans multiple sentences and answers. Beyond the conventional challenges of what to ask and how to ask, multi-hop QG necessitates sophisticated reasoning from dispersed evidence across multiple sentences. To address these challenges, a knowledge graph-enhanced language model (KGEL) has been developed to imitate human reasoning for multi-hop questions.The initial step in KGEL involves encoding the input sentence with a pre-trained GPT-2 language model to obtain a comprehensive semantic context representation. Next, a knowledge graph is constructed using the entities identified within the context. The critical information in the graph that is related to the answer is then utilized to update the context representations through an answer-aware graph attention network (GAT). Finally, the multi-head attention generation module (MHAG) is performed over the updated latent representations of the context to generate coherent questions. Human evaluations demonstrate that KGEL generates more logical and fluent multi-hop questions compared to GPT-2. Furthermore, KGEL outperforms five prominent baselines in automatic evaluations, with a BLEU-4 score that is 27% higher than that of GPT-2.

Scene text detection, this task of detecting text from real images, is a hot research topic in the machine vision community. Most of the current research is based on an anchor box. These methods are complex in model design and time-consuming to train. In this paper, we propose a new Fully Convolutional One-Stage Object Detection (FCOS)-based text detection method that can robustly detect multioriented and multilingual text from natural scene images in a per pixel prediction approach. Our proposed text detector employs an anchor-free approach, unlike state-of-the-art text detectors that do not rely on a predefined anchor box. In order to enhance the feature representation ability of FCOS for text detection tasks, we apply the Bidirectional Feature Pyramid Network (BiFPN) as the backbone network, enhancing the model learning capacity and increasing the receptive field. We demonstrate the superior performance of our method on multioriented (ICDAR-2015, ICDAR-2017 MLT) and horizontal (ICDAR-2013) text detection benchmark tasks. Moreover, our method has an f-measure of 88.65 and 86.32 for the benchmark datasets ICDAR 2013 and ICDAR 2015, respectively, and 80.75 for the ICDAR-2017 MLT dataset.

As the core component of video analysis, Temporal Action Localization (TAL) has experienced remarkable success. However, some issues are not well addressed. First, most of the existing methods process the local context individually, without explicitly exploiting the relations between features in an action instance as a whole. Second, the duration of different actions varies widely; thus, it is difficult to choose the proper temporal receptive field. To address these issues, this paper proposes a novel network, GLFormer, which can aggregate short, medium, and long temporal contexts. Our method consists of three independent branches with different ranges of attention, and these features are then concatenated along the temporal dimension to obtain richer features. One is multi-scale local convolution (MLC), which consists of multiple 1D convolutions with varying kernel sizes to capture the multi-scale context information. Another is window self-attention (WSA), which tries to explore the relationship between features within the window range. The last is global attention (GA), which is used to establish long-range dependencies across the full sequence. Moreover, we design a feature pyramid structure to be compatible with action instances of various durations. GLFormer achieves state-of-the-art performance on two challenging video benchmarks, THUMOS14 and ActivityNet 1.3. Our performance is 67.2% and 54.5% AP@0.5 on the datasets THUMOS14 and ActivityNet 1.3, respectively.

Purpose: This paper aims to investigate a novel shape from focus (SFF) algorithm based on maximum correntropy Kalman filtering (SFF-MCKF) for solving the problem that traditional SFF methods are weak in de-noising and spatial continuity. Design/methodology/approach: To be specific, it was first assumed that the predicted depth of next pixel is equal to the depth of the current pixel according to spatial continuity. Besides, the observing data are derived from the estimation of traditional SFF and the corresponding covariance of noise is adaptively calculated by the entropy along the optical axis. Finally, to enhance robustness, we systematically conduct MCKF iteratively in four transfer directions that are 0°, 90°, 45° and −45°, respectively. Findings: The experimental results indicate that the robustness of SFF-MCKF facing noises as well as the spatial continuity is better than that of the existing representative ones. Research limitations/implications: As the proposed method is aimed at precision objects, high demand is for experimental device. Unstable device unregister the source images, which is unfavorable for observing data. Originality/value: SFF-MCKF can be applied to many precision object measurements without significant drifts, such as the surface reconstruction of metal objects and electronic components. Besides, the computation cost is low, and SFF-MCKF has a wide range of real-time industrial applications.