Semantic segmentation of remote sensing images based on deep neural networks has gained wide attention recently. Although many methods have achieved amazing performance, they need large amounts of labeled images to distinguish the differences in angle, color, size, and other aspects for small targets in remote sensing data sets. However, with a few labeled images, it is difficult to extract the key features of small targets. We propose a semisupervised multiscale generative adversarial network (GAN), which not only utilizes the multipath input and atrous spatial pyramid pooling (ASPP) module but leverages unlabeled images and semisupervised learning strategy to improve the performance of small target segmentation in semantic segmentation when labeled data amount is small. Experimental results show that our model outperforms state-of-the-art methods with insufficient labeled data.

In the mid‐sixties, Rothaus introduced the notion of bent function and later presented a secondary construction of bent functions (building new bent functions from already defined ones), called Rothaus’ construction. In Zhang et al. 2017 (‘Constructing bent functions outside the Maiorana–Mcfarland class using a general form of Rothaus,’ IEEE Transactions on Information Theory , 2017, vol. 63, no. 8, pp. 5336–5349.’) provided two constructions of bent functions using a general form of Rothaus and showed that the obtained classes lie outside the completed Maiorana–McFarland ( ) class. In this study, the authors propose two similar methods for constructing bent functions outside the completed class but with significantly simplified sufficient conditions compared to those in Zhang et al. 2017. These simplified conditions do not induce any serious restrictions on the choice of permutations used in the construction apart from a simple requirement on their algebraic degree and the request that the component functions of one permutation do not admit linear structures. This enables us to generate a huge class of bent functions lying outside the completed class. Even more importantly, they prove that the new classes of bent functions are affine inequivalent to the bent functions in Zhang et al. 2017.

Object segmentation and object tracking are fundamental research areas in the computer vision community. These two topics are difficult to handle some common challenges, such as occlusion, deformation, motion blur, scale variation, and more. The former contains heterogeneous object, interacting object, edge ambiguity, and shape complexity; the latter suffers from difficulties in handling fast motion, out-of-view, and real-time processing. Combining the two problems of Video Object Segmentation and Tracking (VOST) can overcome their respective difficulties and improve their performance. VOST can be widely applied to many practical applications such as video summarization, high definition video compression, human computer interaction, and autonomous vehicles. This survey aims to provide a comprehensive review of the state-of-the-art VOST methods, classify these methods into different categories, and identify new trends. First, we broadly categorize VOST methods into Video Object Segmentation (VOS) and Segmentation-based Object Tracking (SOT). Each category is further classified into various types based on the segmentation and tracking mechanism. Moreover, we present some representative VOS and SOT methods of each time node. Second, we provide a detailed discussion and overview of the technical characteristics of the different methods. Third, we summarize the characteristics of the related video dataset and provide a variety of evaluation metrics. Finally, we point out a set of interesting future works and draw our own conclusions.

The ever‐developing Internet of Things (IoT) drives the prosperity of ubiquitous connections among heterogeneous wireless devices (e.g. WiFi, ZigBee and Bluetooth) that follow different standards. Wireless devices share unlicensed industrial, scientific and medical bands, offering an opportunity for cross‐technology communication (CTC), where coexistence and cooperation mechanisms of wireless technologies incur the problem of coexistence. This study is purposed to present a rounded state‐of‐the‐art survey on CTC from the hardware perspective, CTC techniques are roughly divided into two types: hardware based and hardware free. In hardware‐based strategies, a dedicated hardware is required to send information to wireless devices for enabling direct communication. The hardware‐free schemes, by contrast, enable heterogeneous wireless devices to communicate directly by exchanging information or data without the dedicated hardware. Recent advances in CTC are reviewed in both types by expatiating on how heterogeneous wireless devices are achieving direct communication. The authors compare some CTCs with respect to throughput, communication range, energy efficiency and cost, in addition, they present open research issues of two types.

In this paper, we give an efficient method for constructing a large set of disjoint spectra functions without linear structures, which are not equivalent to partially linear functions. This positively answers the open problem [“how to construct a large set of disjoint spectra functions which are not (linearly equivalent to) partially linear functions” raised by Zhang and Xiao]. At the same time, this significantly extends a recent result of Zhang, where a method of specifying four disjoint spectra functions was given. It is demonstrated that such sets can be utilized in the design of highly nonlinear resilient functions. In the second part, based on a generalization of the indirect sum method, we give an alternative approach for designing sets of disjoint spectra functions of even larger cardinality than already given ones, but these functions then admit linear structures. In addition, it is shown that using suitable initial functions in the generalized indirect sum method we can specify highly nonlinear resilient Boolean functions (in odd number of input variables n) whose nonlinearity in many cases exceeds the current best known values. Moreover, we design some balanced functions (for odd n) that also achieve the highest nonlinearity known.

With the development of location-based services, more moving objects can be traced and a great deal of trajectory data can be collected. Periodicity is very commonly used to analyse the habits of moving objects, so finding objects’ periodic patterns can aid in understanding their behaviour. However, objects’ periodic patterns are always unknown previously, and describing their periods with different granularities will create some surprised findings. This article proposes a multi-granularity periodic activity discovery (MPAD) approach for moving objects. First, a multi-granularity model is introduced to describe the spatial and temporal information of an object’s activities. Then, two algorithms, namely, spatial first and temporal first multi-granularity activity discovery algorithms, are provided to transfer objects’ activities into different granularities. Finally, a novel periodic discovery algorithm is described to find the periodicities of objects’ activities. Experiments on both synthetic and real datasets demonstrate both the efficiency and effectiveness of the proposed work and its notably improved running performance compared to the same algorithms. Additionally, the discovered periodic patterns are more practically significant.

The minimum degree (resp. algebraic degree ) of a Boolean permutation is the minimum (resp. maximum) algebraic degree of all the non‐zero linear combinations of its coordinate functions. In this study, the authors concentrate on the design of Boolean permutations with optimal minimum degree . First, they present a novel method for optimising the minimum degrees of known Boolean permutations. Second, they show that the Boolean permutations, which are obtained by optimising Boolean permutations without optimal algebraic degree , have optimal minimum degree. At last, it is shown that their method generates an infinite class of involutions with optimal minimum degree.

Patch-based models that combine local image features or regions into loose geometric assemblies are a powerful paradigm for visual object tracking, and they present favorable properties such as robustness to partial occlusion, deformation, and the ability to address viewpoint changes. However, effectively exploiting the spatial-temporal confidence scores of each patch to construct a robust tracker while ensuring a low computational cost with dense discrete search remains a challenging problem. In this paper, we propose a unified Markov random field (MRF) model that can effectively capture spatio-temporal intrapatch relations and occlusion priors to enhance the tracking performance, and we derive a highly efficient dense belief propagation for inference of the proposed MRF model. We propose a tracker that models the tracking object with a constellation topology (i.e., a global object and several local patches), where the graph structure model describes the pairwise spatial structure and the image observation model corresponding to the correlation filter with occlusion handling measuring the appearance similarity. Furthermore, these two models are updated online by exploiting the flexibility of local patches. Extensive experimental results on single- and multiple-object tracking show that the proposed algorithm performs favorably against state-of-the-art methods and runs in real time.

Carpooling is becoming a more and more significant traffic choice, because it can provide additional service options, ease traffic congestion, and reduce total vehicle exhaust emissions. Although some recommendation systems have proposed taxicab carpooling services recently, they cannot fully utilize and understand the known information and essence of carpooling. This study proposes a novel recommendation algorithm, which provides either a vacant or an occupied taxicab in response to a passenger’s request, called VOT. VOT recommends the closest vacant taxicab to passengers. Otherwise, VOT infers destinations of occupied taxicabs by similarity comparison and clustering algorithms and then recommends the occupied taxicab heading to a close destination to passengers. Using an efficient large data-processing framework, Spark, we greatly improve the efficiency of large data processing. This study evaluates VOT with a real-world dataset that contains 14747 taxicabs’ GPS data. Results show that the ratio of range (between forecasted and actual destinations) of less than 900 M can reach 90.29%. The total mileage to deliver all passengers is significantly reduced (47.84% on average). Specifically, the reduced total mileage of nonrush hours outperforms other systems by 35%. VOT and others have similar performances in actual detour ratio, even better in rush hours.

Decomposing target into several parts may improve the capability of tracking algorithm to deal with appearance variations such as occlusion and deformation. In this letter, we propose a part-based appearance model by exploiting spatial structure from parts. The model minimizes appearance and deformation cost simultaneously to predict the new position of object. Then, the optimization problem is divided into two parts. Kernelized correlation filter (KCF) is used for tracking the appearance of parts separately to speed up the proposed tracker. Meanwhile, the deformation cost is minimized by structural learning schema, which can reduce the label noise that caused by inaccuracy bounding box. Finally, minimum spanning tree and dynamic programming are employed to combine the score map of the appearance and deformation of parts, and to detect best new position of target. Experimental results on several challenge sequences show the efficiency and effectiveness of the proposed tracking algorithm.