In this paper, we introduce a novel cooperative target tracking algorithm, namely the quantum-inspired belief propagation, aimed at rectifying the limitations observed in existing localization algorithms employed in multi-target cooperative tracking scenarios. Leveraging the principles of quantum superposition, our algorithm seeks to alleviate the uncertainty inherent in message fusion within belief propagation frameworks, thereby enhancing the accuracy and stability of multi-target cooperative localization. The utilization of the quantum Monte Carlo method facilitates the simulation of the message distribution process, with quantum particles embodying the superposition of multiple states concurrently. This approach effectively addresses the intractable integrations encountered in message updating on factor graphs, rendering the algorithm agnostic to the number of particles involved. Moreover, quantum unitary transformations and quantum black-box operations are deployed to encode factor graph function nodes for the propagation of quantum messages. This innovation surmounts the challenge posed by traditional factor graph function nodes’ inability to process quantum messages. Experimental findings corroborated the superiority of the proposed algorithm in terms of accuracy and robustness.

Abrupt-motion tracking is challenging due to the target’s unpredictable action. Although particle filter is suitable for target tracking of nonlinear non-Gaussian systems, it suffers from the problems of particle impoverishment and sample-size dependency. Inspired by quantum mechanics that one quantum bit could represent a superposition of two states, this paper proposes a diversity-preserving quantum-enhanced particle filter (DQPF). Firstly, we quantized the motion modes of particles into a superposition of several modes of motion, resulting in a quantum particle set that retains diversity. Aiming for the abruption of target motion, we propagate the quantum particles during the prediction stage. The quantum particles will already be in these possible positions even if abruption occurs, which addresses the abrupt-motion issue and reduces the tracking delay. Benefitting from quantum mechanics, the proposed particle filter has better precision and stability with fewer particles than the general particle filter. Compared to state-of-the-art, numerical experimental results demonstrate that the proposed DQPF has higher accuracy and stability under the same conditions, displaying superior performance to traditional modified particle filter methods.

Rice leaf disease (RLD) is one of the major factors that cause the decline in production, and the automatic recognition of such diseases under natural field conditions is of great significance for timely targeted rice management. Although many machine learning approaches have been proposed for RLD recognition, scale variation is still a challenging problem that affects prediction accuracy, especially in uncontrolled environments, such as natural fields. Also, the existing RLD data sets are collected in laboratory environments or with a constant scale, which cannot be used to develop the RLD classification algorithms under natural field conditions. To tackle these particular challenges, we propose a multiscale voting mechanism for RLD recognition under natural field conditions. First, data from 26 rice fields were collected to build a data set containing 6046 images of RLD. Afterwards, a feature pyramid was embedded into a mainstream classification architecture (EfficientNet) with a bottom-up and top-down pathway for feature fusion at different scales. To further reduce the inconsistency among multiscaled features, a multiscale voting strategy with regard to probability distribution was proposed to integrate the decisions from various scales. Each proposed module was carefully validated through an ablation study to demonstrate its effectiveness, and the proposed method was compared with a few state-of-the-art algorithms, including the Single Shot MultiBox Detector, Feature Pyramid Networks, Path Aggregation Network, and Bidirectional Feature Pyramid Network. Experimental results have shown that the classification accuracy of our model can reach 90.24%, which is 4.48% higher than that of the original EfficientNet-b0 model and 1.08% higher than that of existing multiscale networks. Finally, we exploit and demonstrate a visualized explanation for the boosted performance from the proposed model. As an extra outcome, our data set and codes are available at http://github.com/huanghsheng/multiscale-voting-mechanism to benefit the whole research community.

Color calibration is a critical step for Unmanned Aerial Vehicles (UAV) remote sensing, especially in precision agriculture, which relies mainly on correlating color changes to specific quality attributes, e.g., plant health, disease, and pest stresses. In UAV remote sensing, the exemplar-based color transfer is popularly used for color calibration, where the automatic search for the semantic correspondences is the key to ensuring the color transfer accuracy. However, the existing attention mechanisms encounter difficulties in building the precise semantic correspondences between the reference image and the target one, in which the normalized cross correlation is often computed for feature reassembling. As a result, the color transfer accuracy is inevitably decreased by the disturbance from the semantically unrelated pixels, leading to semantic mismatch due to the absence of semantic correspondences. In this paper, we proposed an unsupervised object-based attention mechanism (OBAM) to suppress the disturbance of the semantically unrelated pixels, along with a further introduced weight-adjusted AdaIN (WAA) method to tackle the challenges caused by the absence of semantic correspondences. By embedding the proposed modules into a photorealistic style transfer method with progressive stylization, the color transfer accuracy can be improved while better preserving the structural details. We evaluated our approach on the UAV data of different crop types including rice, beans, and cotton. Extensive experiments demonstrate that our proposed method outperforms several state-of-the-art methods. As our approach requires no annotated labels, it can be easily embedded into the off-the-shelf color transfer approaches. Relevant codes and configurations will be available at http://github.com/huanghsheng/object-based-attention-mechanism.

Medical image classification and diagnosis is currently a hot topic in the field of deep learning. The ACM International Conference on Multimedia and Simula co-hosted the MutilMedia Grand Challenge, which aims to use artificial intelligence aiding detection and classification of gastrointestinal image. This competition is divided into four subtasks, including detection, efficient detection, efficient detection (the same hardware for all the participants) and report generation. We participate in the multi-label detection task and propose a new attention model, which can effectively improve the network's ability to classify different types of categories. Our approach also uses a series of different techniques including multi-epoch fusion, automatic data augmentation selection, and adaptive threshold selection. Combining these techniques, we are able to achieve good classification results on the given dataset. Finally, our f1 score is 0.907 and MCC is 0.952 with a high speed.

Video identification is an important task in the practical application and industry. Based on the iQIYI-VID-2019 dataset, ACM International Conference on Multimedia and iQIYI co-hosted the celebrity video identification challenge. We take part in the competition, propose a new feature fusion method and design a residual dense network which can improve video identification performance in the complex scenes. Only with face features, we achieve 0.9035 in mean Average Precision(mAP) which win the second place on the leadboard. At the same time, it is the best score only with official features. It is worth mention that the flops of our model is only 0.5G and the time required to predict the entire test dataset is only 2 sim 5 minutes. Our method takes accuracy and speed into account, which has a strong practical significance.

Dimensionality reduction is of high importance in hyperspectral data processing, which can effectively reduce the data redundancy and computation time for improved classification accuracy. Band selection and feature extraction methods are two widely used dimensionality reduction techniques. By integrating the advantages of the band selection and feature extraction, the authors propose a new method for reducing the dimension of hyperspectral image data. First, a new and fast band selection algorithm is proposed for hyperspectral images based on an improved determinantal point process (DPP). To reduce the amount of calculation, the dual‐DPP is used for fast sampling representative pixels, followed by k‐nearest neighbour‐based local processing to explore more spatial information. These representative pixel points are used to construct multiple adjacency matrices to describe the correlation between bands based on mutual information. To further improve the classification accuracy, two‐dimensional singular spectrum analysis is used for feature extraction from the selected bands. Experiments show that the proposed method can select a low‐redundancy and representative band subset, where both data dimension and computation time can be reduced. Furthermore, it also shows that the proposed dimensionality reduction algorithm outperforms a number of state‐of‐the‐art methods in terms of classification accuracy.

Although extreme learning machines (ELM) have been successfully applied for the classification of hyperspectral images (HSIs), they still suffer from three main drawbacks. These include: 1) ineffective feature extraction (FE) in HSIs due to a single hidden layer neuron network used; 2) ill-posed problems caused by the random input weights and biases; and 3) lack of spatial information for HSIs classification. To tackle the first problem, we construct a multilayer ELM for effective FE from HSIs. The sparse representation is adopted with the multilayer ELM to tackle the ill-posed problem of ELM, which can be solved by the alternative direction method of multipliers. This has resulted in the proposed multilayer sparse ELM (MSELM) model. Considering that the neighboring pixels are more likely from the same class, a local block extension is introduced for MSELM to extract the local spatial information, leading to the local block MSELM (LBMSELM). The loopy belief propagation is also applied to the proposed MSELM and LBMSELM approaches to further utilize the rich spectral and spatial information for improving the classification. Experimental results show that the proposed methods have outperformed the ELM and other state-of-the-art approaches.

Big data analytics frameworks (BDAFs) have been widely used for data processing applications. These frameworks provide a large number of configuration parameters to users, which leads to a tuning issue that overwhelms users. To address this issue, many automatic tuning approaches have been proposed. However, it remains a critical challenge to generate enough samples in a high-dimensional parameter space within a time constraint. In this paper, we present AutoTune-an automatic parameter tuning system that aims to optimize application execution time on BDAFs. AutoTune first constructs a smaller-scale testbed from the production system so that it can generate more samples, and thus train a better prediction model, under a given time constraint. Furthermore, the AutoTune algorithm produces a set of samples that can provide a wide coverage over the high-dimensional parameter space, and searches for more promising configurations using the trained prediction model. AutoTune is implemented and evaluated using the Spark framework and HiBench benchmark deployed on a public cloud. Extensive experimental results illustrate that AutoTune improves on default configurations by 63.70% on average, and on the five state-of-the-art tuning algorithms by 6%-23%.

Parallel computing combined with distributed data storage and management has been widely adopted by most big data analytics systems. Scheduling computing tasks to improve data locality is crucial to the performance of such systems. While existing schedulers target near-data scheduling on top of physical data blocks, these systems face a new scheduling problem where computing tasks process table-based datasets directly and access large physical blocks indirectly through their indices stored in associated small logical blocks. This new problem invalidates the basic assumption made by many existing algorithms on near-data scheduling. In this paper, we propose a Logical-block Affinity Scheduling (LAS) algorithm to coordinate the near-data scheduling of computing tasks and the placement of logical blocks for a desired balance between data-locality and load-balancing to maximize system throughput. The proposed algorithm is implemented and evaluated using a well-known big data benchmark and a practical production system deployed in public clouds. Extensive experimental results illustrate the performance superiority of LAS over three existing scheduling algorithms.