Search

In the field of object detection, deep learning models have achieved great success in recent years. Despite these advances, detecting small objects remains difficult. Most objects in aerial images have features that are a challenge for traditional object detection techniques, including small size, high density, high variability, and varying orientation. Previous approaches have used slicing methods on high-resolution images or feature maps to improve performance. However, existing slicing methods inevitably lead to redundant computation. Therefore, in this article we present a novel adaptive slicing method named ASAHI (Adaptive Slicing Aided Hyper Inference), which can dramatically reduce redundant computation using an adaptive slicing size. Specifically, ASAHI focuses on the number of slices rather than the slicing size, that is, it adaptively adjusts the slicing size to control the number of slices according to the image resolution. Additionally, we replace the standard non-maximum suppression technique with Cluster-DIoU-NMS due to its improved accuracy and inference speed in the post-processing stage. In extensive experiments, ASAHI achieves competitive performance on the VisDrone and xView datasets. The results show that the mAP50 is increased by 0.9% and the computation time is reduced by 20–25% compared with state-of-the-art slicing methods on the TPH-YOLOV5 pretrained model. On the VisDrone2019-DET-val dataset, our mAP50 result is 56.4% higher, demonstrating the superiority of our approach. [ABSTRACT FROM AUTHOR]

Personalized learning paths aim to save learning time and improve learning achievements by providing the most appropriate learning sequence for heterogeneous students. Most existing methods that construct personalized learning paths focus on students' characteristics or knowledge structure, while ignoring the critical roles of learning states. This study describes a dynamic personalized learning path planning algorithm to recommend appropriate knowledge points for online students based on their learning states and the difficulty of each knowledge point. The proposed method first calculates the difficulty of knowledge points automatically and constructs a knowledge difficulty model. Then, a dynamic knowledge mastery model is built based on learning behavior and normalized test scores. Finally, a path that satisfies students' personalized changing states is generated. To achieve the aforementioned goal, a novel method that calculates the difficulty of knowledge points automatically is proposed. Moreover, the personalized learning path planning method proposed in this research is not limited to a particular course. To evaluate the method, we use a series of approaches to verify the impact of the personalized path on student learning. The experimental results demonstrate that the proposed algorithm can effectively generate personalized learning paths. Results demonstrate that the personalized path proposed by the algorithm can improve effective behavior rates, course completion rates and learning efficiency. Results also show that the personalized learning paths based on student states would help students to master knowledge. [ABSTRACT FROM AUTHOR]

Example-based texture synthesis plays a significant role in many fields, including computer graphics, computer vision, multimedia, and image and video editing and processing. However, it is not easy for all textures to synthesize high-quality outputs of any size from a small input example. Hence, the assessment of the synthesizability of the example textures deserves more attention. Inspired by the broad studies in image quality assessment, we propose a texture synthesizability assessment approach based on a deep Siamese-type network. To our best knowledge, this is the first attempt to evaluate the synthesizability of sample textures through end-to-end training. We first train a Siamese-type network to compare the example texture and the synthesized texture in terms of their similarity and then transfer the experience knowledge obtained in the Siamese-type network to a traditional CNN by fine-tuning, so that to give an absolute score to a single example texture, representing its synthesizability. Not relying on laborious human selection and annotation, these synthesized textures can be generated automatically by example-based synthesis algorithms. We demonstrate that our approach is completely data-driven without hand-crafted features and/or prior knowledge in the field of expertise. Experiments show that our approach improves the accuracy of texture synthesizability assessment qualitatively and quantitatively and outperforms the manual feature-based method. [ABSTRACT FROM AUTHOR]

In this work, we present a supervised object segmentation algorithm for unconstrained video. Instead of arbitrarily picking a few frames for manual labeling, as in many existing supervised methods, the proposed method selects frames in a more reasonable manner, called supervision optimization. For this, we formulate a principled objective function by inferring the propagation error from appearance and motion clues. After this, we construct a multilevel segmentation model, which consists of low-level and high-level features. On the low level, image pixels are used for a more accurate estimation of motion and segmentation. On the high level, image segments are considered for a more semantic classification of the foreground and background. By integrating these in one segmentation graph, the result can be further improved by leveraging the knowledge from both levels. In experiments, the proposed approach is evaluated by different measures, and the results on a benchmark demonstrate the effectiveness in comparison with other state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

ABSTRACT We present a method to make an accurate and dense reconstruction from the input of video captured by a free moving handheld camera in real time. By the method firstly, the positions of the camera and sparse 3D points are estimated by simultaneous localization mapping. Then the depth maps of selected reference frames are computed from corresponding camera bundles. Lastly a novel linear algorithm is also proposed to integrate all the depth maps into dense meshes partially. The main contributions of this paper are in the following points: the reference frames and corresponding camera bundles are able to be selected automatically, then accurate and smooth depth maps are generated in real time, and the depth maps are merged into a dense mesh by using a linear algorithm based on the error clouds optimization. Our algorithm is implemented on dual CPU and graphics processing unit in a parallel framework for improving the performance. Copyright © 2013 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Recently, deep learning has enabled a huge leap forward in image inpainting. However, due to the memory and computational limitation, most existing methods are able to handle only low-resolution inputs, typically less than 1 K. With the improvement of Internet transmission capacity and mobile device cameras, the resolution of image and video sources available to users via the cloud or locally is increasing. For high-resolution images, the common inpainting methods simply upsample the inpainted result of the shrinked image to yield a blurry result. In recent years, there is an urgent need to reconstruct the missing high-frequency information in high-resolution images and generate sharp texture details. Hence, we propose a general deep learning framework for high-resolution image inpainting, which first hallucinates a semantically continuous blurred result using low-resolution inpainting and suppresses computational overhead. Then the sharp high-frequency details with original resolution are reconstructed using super-resolution refinement. Experimentally, our method achieves inspiring inpainting quality on 2K and 4K resolution images, ahead of the state-of-the-art high-resolution inpainting technique. This framework is expected to be popularized for high-resolution image editing tasks on personal computers and mobile devices in the future. [ABSTRACT FROM AUTHOR]

Subtitles are crucial for video content understanding. However, a large amount of videos have only burned-in, hardcoded subtitles that prevent video re-editing, translation, etc. In this paper, we construct a deep-learning-based system for the inverse conversion of a burned-in subtitle video to a subtitle file and an inpainted video, by coupling three deep neural networks (CTPN, CRNN, and EdgeConnect). We evaluated the performance of the proposed method and found that the deep learning method achieved high-precision separation of the subtitles and video frames and significantly improved the video inpainting results compared to the existing methods. This research fills a gap in the application of deep learning to burned-in subtitle video reconstruction and is expected to be widely applied in the reconstruction and re-editing of videos with subtitles, advertisements, logos, and other occlusions. [ABSTRACT FROM AUTHOR]

In the information age, MOOCs (Massive Open Online Courses), micro-classes, flipping classroom, and other blended teaching scenes have improved students learning outcomes. However, incorporating technologies into experimental courses, especially electronic and electrical experiments, has its own characteristics and difficulties. The focus of this paper is to introduce virtual technology into an electronic circuit experiment course and to explore its teaching strategy, thereby realizing the informatization of experiment teaching. First, this paper explores the design concepts and implementation details of the digital circuit virtual laboratory, which is then developed based on previous literature and a prequestionnaire to users. Second, the informatization process of the experiment learning model based on traditional custom lab benches is shown through a blended learning scheme that integrates the online virtual laboratory. Finally, the experiment information system is verified and analyzed with a control group experiment and questionnaires. The blended program turned out to be an effective teaching model to complement the deficiencies in existing physical laboratories. The research conclusions show that the virtual experiment system provides students with a rich, efficient, and expansive experimental experience, in particular, the flexibility, repeatability, and visual appeal of a virtual platform could promote the development of students' abilities in active learning, reflective thinking, and creativity. [ABSTRACT FROM AUTHOR]

Although online learning platforms are gradually becoming commonplace in modern society, learners' high dropout rates and serious academic performance require more attention within the virtual learning environment (VLE). This study aims to predict students' performance in a specific course as it is continuously running, using the statistic personal biographical information and sequential behavior data with VLE. To achieve this goal, a novel recurrent neural network (RNN)-gated recurrent unit (GRU) joint neural network is proposed to fit both static and sequential data, where the data completion mechanism is also adopted to fill the missing stream data. To incorporate the sequential relationship of learning data, three kinds of time-series deep neural network algorithms: simple RNN, GRU, and LSTM are first taken into consideration as baseline models. Their performances are compared in identifying at-risk students. Experimental results on Open University Learning Analytics Dataset (OULAD) show that simple methods like GRU and simple RNN have better results than the relatively complex LSTM model. The results also reveal that different models have different peak performance time, which results in the proposed joint model that achieves over 80% prediction accuracy of at-risk students at the end of the semester. [ABSTRACT FROM AUTHOR]

Learning data feedback and analysis have been widely investigated in all aspects of education, especially for large scale remote learning scenario like Massive Open Online Courses (MOOCs) data analysis. On-site teaching and learning still remains the mainstream form for most teachers and students, and learning data analysis for such small scale scenario is rarely studied. In this work, we first develop a novel user interface to progressively collect students' feedback after each class of a course with WeChat mini program inspired by the evaluation mechanism of most popular shopping website. Collected data are then visualized to teachers and pre-processed. We also propose a novel artificial neural network model to conduct a progressive study performance prediction. These prediction results are reported to teachers for next-class and further teaching improvement. Experimental results show that the proposed neural network model outperforms other state-of-the-art machine learning methods and reaches a precision value of 74.05% on a 3-class classifying task at the end of the term. [ABSTRACT FROM AUTHOR]