Search

The finite inverted beta mixture model (IBMM) has been proven to be efficient in modeling positive vectors. Under the traditional variational inference framework, the critical challenge in Bayesian estimation of the IBMM is that the computational cost of performing inference with large datasets is prohibitively expensive, which often limits the use of Bayesian approaches to small datasets. An efficient alternative provided by the recently proposed stochastic variational inference (SVI) framework allows for efficient inference on large datasets. Nevertheless, when using the SVI framework to address the non-Gaussian statistical models, the evidence lower bound (ELBO) cannot be explicitly calculated due to the intractable moment computation. Therefore, the algorithm under the SVI framework cannot directly use stochastic optimization to optimize the ELBO, and an analytically tractable solution cannot be derived. To address this problem, we propose an extended version of the SVI framework with more flexibility, namely, the extended SVI (ESVI) framework. This framework can be used in many non-Gaussian statistical models. First, some approximation strategies are applied to further lower the ELBO to avoid intractable moment calculations. Then, stochastic optimization with noisy natural gradients is used to optimize the lower bound. The excellent performance and effectiveness of the proposed method are verified in real data evaluation.

© 2021 The Authors. Many biomedical applications require accurate non-rigid image registration that can cope with complex deformations. However, popular diffeomorphic Demons registration algorithms suffer from difficulties for complex and serious distortions since they only use image greyscale and gradient information. To address these difficulties, a new diffeomorphic Demons registration algorithm is proposed using hierarchical neighbourhood spectral features namely HNSF Log-Demons in this paper. In view of three important properties of hierarchical neighbourhood spectral features based on line graph such as rotation invariance, invariance of linear changes of brightness, and robustness to noise, the hierarchical neighbourhood spectral features of a reference image and a moving image is first extracted and these novel spectral features are incorporated into the energy function of the diffeomorphic registration framework to improve the capability of capturing complex distortions. Secondly, the Nystr ö o ̈ m approximation based on random singular value decomposition is employed to effectively enhance the computational efficiency of HNSF Log-Demons. Finally, the hybrid multi-resolution strategy based on wavelet decomposition in the registration process is utilised to further improve the registration accuracy and efficiency. Experimental results show that the proposed HNSF Log-Demons not only effectively ensures the generation of smooth and reversible deformation field, but also achieves better performance than state-of-the-art algorithms. National Natural Science Foundation of China. Grant Numbers: 61762058, 61861024, 61871259; Natural Science Foundation of Gansu Province of China. Grant Number: 20JR5RA404; Natural Science Basic Research Program of Shaanxi. Grant Number: 2021JC-47.

Cosparse analysis model (CAM) provides a new signal processing paradigm for recovering cosparse signals with respect to a given analysis operator from the undersampled linear measurements in the context of emerging theory of compressed sensing (CS). The sparse analysis recovery/cosparse recovery is a key one brought up by this new paradigm. In this paper, we propose a new family of analysis pursuit algorithms for the sparse analysis recovery problem when the signals obey the cosparse analysis model, termed as iterative cosupport detection estimation (ICDE). ICDE is an algorithmic framework, which alternates between detecting a cosupport set of the unknown true signal and estimating the underlying signal by solving a truncated analysis pursuit problem on the detected cosupport. Further, we propose effective implementations of ICDE equipped with an efficient thresholding strategy for cosupport detection. Empirical performance comparisons show that ICDE is favorable in comparison with the state-of-the-art sparse analysis recovery algorithms. Source code of ICDE has been made publicly available on Github: https://github.com/songhp/ICDE. Beijing Natural Science Foundation (BNSF) under Grant No. 4194076, the Natural Science Foundation of Jiangsu Province under Grant No. BK20170558 and the China Scholarship Council (CSC, No. 202008320094).

Solder paste printing is the first part of the surface mount process flow; its postprinting defect inspection is particularly important. In this paper, we focus on studying the printing defects inspection algorithm for solder paste on PCB (Printed Circuit Board) images. +e work proposes a number of methods to enhance the defects inspection performance of solder paste printing: a regional multidirectional data fusion image interpolation method, which can achieve fast and high precision image interpolation; a method for detecting solder paste areas with better accuracy, efficiency, and robustness; an improved connected domain labeling method to reduce time complexity; and defects detection and types classification method, which extracts features and centroid of every solder paste region and completes the inspection by comparing with a standard image. +e experiments show that the defects inspection algorithm can detect the most common types of defects with low time consumption, high inspection accuracy, and classification accuracy. Key Project of Shaanxi Province Innovation Program, China (2017ZDCXL-GY-11-02-02)

Recently, Multi-Object Tracking (MOT) has attracted rising attention, and accordingly, remarkable progresses have been achieved. However, the existing methods tend to use various basic models (e.g, detector and embedding model), and different training or inference tricks, etc. As a result, the construction of a good baseline for a fair comparison is essential. In this paper, a classic tracker, i.e., DeepSORT, is first revisited, and then is significantly improved from multiple perspectives such as object detection, feature embedding, and trajectory association. The proposed tracker, named StrongSORT, contributes a strong and fair baseline for the MOT community. Moreover, two lightweight and plug-and-play algorithms are proposed to address two inherent "missing" problems of MOT: missing association and missing detection. Specifically, unlike most methods, which associate short tracklets into complete trajectories at high computation complexity, we propose an appearance-free link model (AFLink) to perform global association without appearance information, and achieve a good balance between speed and accuracy. Furthermore, we propose a Gaussian-smoothed interpolation (GSI) based on Gaussian process regression to relieve the missing detection. AFLink and GSI can be easily plugged into various trackers with a negligible extra computational cost (1.7 ms and 7.1 ms per image, respectively, on MOT17). Finally, by fusing StrongSORT with AFLink and GSI, the final tracker (StrongSORT++) achieves state-of-the-art results on multiple public benchmarks, i.e., MOT17, MOT20, DanceTrack and KITTI. Codes are available at https://github.com/dyhBUPT/StrongSORT and https://github.com/open-mmlab/mmtracking., Accepted by IEEE Transactions on Multimedia 2023

Clustering algorithms by minimizing an objective function share a clear drawback of having to set the number of clusters manually. Although density peak clustering is able to find the number of clusters, it suffers from memory overflow when it is used for image segmentation because a moderate-size image usually includes a large number of pixels leading to a huge similarity matrix. To address this issue, here we proposed an automatic fuzzy clustering framework (AFCF) for image segmentation. The proposed framework has threefold contributions. First, the idea of superpixel is used for the density peak (DP) algorithm, which efficiently reduces the size of the similarity matrix and thus improves the computational efficiency of the DP algorithm. Second, we employ a density balance algorithm to obtain a robust decision-graph that helps the DP algorithm achieve fully automatic clustering. Finally, a fuzzy c-means clustering based on prior entropy is used in the framework to improve image segmentation results. Because the spatial neighboring information of both the pixels and membership are considered, the final segmentation result is improved effectively. Experiments show that the proposed framework not only achieves automatic image segmentation, but also provides better segmentation results than state-of-the-art algorithms. 10.13039/501100001809-National Natural Science Foundation of China; 10.13039/501100002858-China Postdoctoral Science Foundation

Copyright: © 2021 Pereira, Meng and Hone. It is well recognised that social signals play an important role in communication effectiveness. Observation of videos to understand non-verbal behaviour is time-consuming and limits the potential to incorporate detailed and accurate feedback of this behaviour in practical applications such as communication skills training or performance evaluation. The aim of the current research is twofold: (1) to investigate whether off-the-shelf emotion recognition technology can detect social signals in media interviews and (2) to identify which combinations of social signals are most promising for evaluating trainees’ performance in a media interview. To investigate this, non-verbal signals were automatically recognised from practice on-camera media interviews conducted within a media training setting with a sample size of 34. Automated non-verbal signal detection consists of multimodal features including facial expression, hand gestures, vocal behaviour and ‘honest’ signals. The on-camera interviews were categorised into effective and poor communication exemplars based on communication skills ratings provided by trainers and neutral observers which served as a ground truth. A correlation-based feature selection method was used to select signals associated with performance. To assess the accuracy of the selected features, a number of machine learning classification techniques were used. Naive Bayes analysis produced the best results with an F-measure of 0.76 and prediction accuracy of 78%. Results revealed that a combination of body movements, hand movements and facial expression are relevant for establishing communication effectiveness in the context of media interviews. The results of the current study have implications for the automatic evaluation of media interviews with a number of potential application areas including enhancing communication training including current media skills training. UK Defence Science and Technology Laboratory; Engineering and Physical Sciences Research Council (DTP grant).

An autonomous vehicle navigates by perceiving the environment through the sensors and acting on the received data by making sense of the surroundings. In this paper, innovative holoscopic 3D scene classification based on the single aperture holoscopic 3D camera is proposed to recognise continuous 3D scene of environment. The deep learning network AlexNet is used to evaluate the proposed approach, and the outcome exhibits promising results compared to 2D images.

Simultaneous Localization and Mapping (SLAM) is a critical system for Unmanned Aerial Vehicles (UAV), Autonomous Navigation (AN), Augmented Reality (AR) and Virtual Reality (VR). However, due to volume and computation limitations, the current SLAM systems on mobile devices are not robust enough for practical applications. In this paper, a new SLAM system is proposed, which can be applied to AR or VR. With the RGB-D input data, this SLAM system can produce 3D scene reconstruction and camera pose estimation in almost real time. The parameters of the system are optimized for use on mobile devices. In addition, an adaptive keyframe selection method is proposed to balance trade-off between accuracy and speed of the system. Experimental results demonstrated its superior performance in comparison with the state-of-the-art methods in the same public benchmark dataset.

Emotion Artificial Intelligence (AI) is a novel technology for advanced human machine interaction in real-world applications. In interactive films, variant contents can be adjusted and displayed in the film based on audiences’ interaction such as voice, hand gesture or body movement, etc. In this paper, a specific emotion detection system is designed and implemented that can detect emotion continuously through the audience’s facial expression and give the feedback to the film immediately. Then the film can change its contents accordingly. In this system, A pre-trained convolutional neural network is used for feature extraction from video frames and then the emotion is predicted by a support vector regression model. The environmental noise is reduced in the pre-processing stage and the final prediction is smoothed in the post-processing. A database is recorded for this particular scene and the proposed system is trained on it. The experimental results demonstrate the effectiveness of the system and the built interactive film “RIOT” has been exhibited on several occasions with good performance.

As one of the most classic human inventions, music can be seen as another language, used to express the author’s thoughts and emotion. Music Emotion Recognition (MER) is an interesting research topic in artificial intelligence field for recognising emotions from music. The recognition methods and tools for music signals are growing fast recently. However the attentions are paid mainly on music signal feature extraction and machine learning methods. The theoretical knowledge of music on emotion is usually ignored. This paper propose a new method through important music units – chord to recognize emotion from music. We firstly build a new chord database with chord segments based on selected emotions. Then FFT and statistics (STAT) features are extracted from the music signals in the database. Then one-shot learning are used for chord identification and emotion recognition using Euclidean distance and correlation. The proposed method can recognise 6 emotions from music signals through chord identification with 76.6% accuracy of chord identification. This idea can be developed further using more advanced feature extraction and one-shot learning methods.

The popular deep convolutional networks used for image super-resolution (SR) reconstruction often increase the network depth and employ attention mechanism to improve image reconstruction effect. However, these networks suffer from two problems. The first is the deeper network easily causes higher computational cost and more GPU memory usage. The second is traditional attention mechanism often misses the spatial information of images leading the loss of image detail information. To address these issues, we propose a lightweight non-local network (LNLN) for image super resolution in this paper. The proposed network makes two contributions. First, we use non-local module instead of normal attention module to obtain larger receptive field and extract more comprehensive feature information, which is helpful for improving image SR reconstruction results. Secondly, we use the depthwise separable convolution (DSC) instead of the vanilla convolution to reconstruct the residual block, which greatly reduces the number of parameters and computational cost. The proposed LNLN and comparative networks are evaluated on five commonly public datasets, and experiments demonstrate that the proposed LNLN is superior to state-of-the-art networks in terms of reconstruction performance, the number of parameters and storage space.

A great number of improved fuzzy c-means (FCM) clustering algorithms have been widely used for grayscale and color image segmentation. However, most of them are time-consuming and unable to provide desired segmentation results for color images due to two reasons. The first one is that the incorporation of local spatial information often causes a high computational complexity due to the repeated distance computation between clustering centers and pixels within a local neighboring window. The other one is that a regular neighboring window usually breaks up the real local spatial structure of images and thus leads to a poor segmentation. In this work, we propose a superpixel-based fast FCM clustering algorithm (SFFCM) that is significantly faster and more robust than state-of-the-art clustering algorithms for color image segmentation. To obtain better local spatial neighborhoods, we firstly define a multiscale morphological gradient reconstruction (MMGR) operation to obtain a superpixel image with accurate contour. In contrast to traditional neighboring window of fixed size and shape, the superpixel image provides better adaptive and irregular local spatial neighborhoods that are helpful for improving color image segmentation. Secondly, based on the obtained superpixel image, the original color image is simplified efficiently and its histogram is computed easily by counting the number of pixels in each region of the superpixel image. Finally, we implement FCM with histogram parameter on the superpixel image to obtain the final segmentation result. Experiments performed on synthetic images and real images demonstrate that the proposed algorithm provides better segmentation results and takes less time than state-of-the-art clustering algorithms for color image segmentation. China Postdoctoral Science Foundation; National Natural Science Foundation of China; National Science Foundation of Shanghai

As fuzzy c-means clustering (FCM) algorithm is sensitive to noise, local spatial information is often introduced to an objective function to improve the robustness of the FCM algorithm for image segmentation. However, the introduction of local spatial information often leads to a high computational complexity, arising out of an iterative calculation of the distance between pixels within local spatial neighbors and clustering centers. To address this issue, an improved FCM algorithm based on morphological reconstruction and membership filtering (FRFCM) that is significantly faster and more robust than FCM is proposed in this paper. First, the local spatial information of images is incorporated into FRFCM by introducing morphological reconstruction operation to guarantee noise-immunity and image detail-preservation. Second, the modification of membership partition, based on the distance between pixels within local spatial neighbors and clustering centers, is replaced by local membership filtering that depends only on the spatial neighbors of membership partition. Compared with state-of-the-art algorithms, the proposed FRFCM algorithm is simpler and significantly faster, since it is unnecessary to compute the distance between pixels within local spatial neighbors and clustering centers. In addition, it is efficient for noisy image segmentation because membership filtering are able to improve membership partition matrix efficiently. Experiments performed on synthetic and real-world images demonstrate that the proposed algorithm not only achieves better results, but also requires less time than the state-of-the-art algorithms for image segmentation.

This document describes the initial results obtained by the IoRL researchers in the proof trial results of the user equipment (UE) design including the VLC and mmWave links. The results were obtained during the development, integration and initial testing of the different modules that are part of the RRLH UE including: mmWave Tx/Rx with 60GHz mmWave Tx/Rx with 40GHz VLC Tx with Oledcomm Rx at Viavi testbed VLC Tx with TH Rx at Viavi testbed VLC Tx with Oledcomm Rx at REL DRAN+RRLH testbed VLC Tx with TH Rx at REL DRAN+RRLH testbed, Suggested readers: IoRL project members

The COVID-19 epidemic in 2020 posed a sudden and serious challenge to education where online teachings were adopted, and problems that people had not noticed before were exposed. Based on the experience of international online course and the study of online teaching, the paper focuses on the associated problems and puts forward some solutions. First, based on the performance of current software and hardware used in online teaching, the characteristics of commonly used teaching software have been analysed and compared. Then, efficient combinations of teaching software for complementary advantages are recommended to ensure a high-quality online teaching. Second, problems inside of class existing in online lecturing and learning are studied, and corresponding teaching methods have been explored including the aspects of class interaction design and implementation, alternative method for delivering essential video information, and online class management. Finally, some objective class evaluation criteria are studied in terms of coverage of class content, learning effect of specialized knowledge, and online class interaction. In the end, some feasible solutions are provided, and it can be served as a reference to improve the online teaching. [ABSTRACT FROM AUTHOR] Copyright of Scientific Programming is the property of Hindawi Limited and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)