Activity

The experiments demonstrate the state-of-the-art results obtaining a relative gain of up to 114% on Pascal-VOC 2012 and 8.5% on the more challenging ADE20K compared to previous state-of-the-art methods.Neural architecture search (NAS) has attracted much attention in recent years. It automates the neural network construction for different tasks, which is traditionally addressed manually. KYA1797K datasheet In the literature, evolutionary optimization (EO) has been proposed for NAS due to its strong global search capability. However, despite the success enjoyed by EO, it is worth noting that existing EO algorithms for NAS are often very computationally expensive, which makes these algorithms unpractical in reality. Keeping this in mind, in this article, we propose an efficient memetic algorithm (MA) for automated convolutional neural network (CNN) architecture search. In contrast to existing EO algorithms for CNN architecture design, a new cell-based architecture search space, and new global and local search operators are proposed for CNN architecture search. To further improve the efficiency of our proposed algorithm, we develop a one-epoch-based performance estimation strategy without any pretrained models to evaluate each found architecture on the training datasets. To investigate the performance of the proposed method, comprehensive empirical studies are conducted against 34 state-of-the-art peer algorithms, including manual algorithms, reinforcement learning (RL) algorithms, gradient-based algorithms, and evolutionary algorithms (EAs), on widely used CIFAR10 and CIFAR100 datasets. The obtained results confirmed the efficacy of the proposed approach for automated CNN architecture design.Aligning human parts automatically is one of the most challenging problems for person re-identification (re-ID). Recently, the stripe-based methods, which equally partition the person images into the fixed stripes for aligned representation learning, have achieved great success. However, the stripes with fixed height and position cannot well handle the misalignment problems caused by inaccurate detection and occlusion and may introduce much background noise. In this article, we aim at learning adaptive stripes with foreground refinement to achieve pixel-level part alignment by only using person identity labels for person re-ID and make two contributions. 1) A semantics-consistent stripe learning method (SCS). Given an image, SCS partitions it into adaptive horizontal stripes and each stripe is corresponding to a specific semantic part. Specifically, SCS iterates between two processes i) clustering the rows to human parts or background to generate the pseudo-part labels of rows and ii) learning a row classifier to partition a person image, which is supervised by the latest pseudo-labels. This iterative scheme guarantees the accuracy of the learned image partition. 2) A self-refinement method (SCS+) to remove the background noise in stripes. We employ the above row classifier to generate the probabilities of pixels belonging to human parts (foreground) or background, which is called the class activation map (CAM). Only the most confident areas from the CAM are assigned with foreground/background labels to guide the human part refinement. Finally, by intersecting the semantics-consistent stripes with the foreground areas, SCS+ locates the human parts at pixel-level, obtaining a more robust part-aligned representation. Extensive experiments validate that SCS+ sets the new state-of-the-art performance on three widely used datasets including Market-1501, DukeMTMC-reID, and CUHK03-NP.This paper investigates the predefined-time hierarchical coordinated adaptive control on the hypersonic reentry vehicle in presence of low actuator efficiency. In order to compensate for the deficiency of rudder deflection in advantage of channel coupling, the hierarchical design is proposed for coordination of the elevator deflection and aileron deflection. Under the control scheme, the equivalent control law and switching control law are constructed with the predefined-time technology. For the dynamics uncertainty approximation, the composite learning using the tracking error and the prediction error is constructed by designing the serial-parallel estimation model. The closed-loop system stability is analyzed via the Lyapunov approach and the tracking errors are guaranteed to be uniformly ultimately bounded in a predefined time. The tracking performance and the learning accuracy of the proposed algorithm are verified via simulation tests.Deep generative models for graphs have recently achieved great successes in modeling and generating graphs for studying networks in biology, engineering, and social sciences. However, they are typically unconditioned generative models that have no control over the target graphs given a source graph. In this article, we propose a novel graph-translation-generative-adversarial-nets (GT-GAN) model that transforms the source graphs into their target output graphs. GT-GAN consists of a graph translator equipped with innovative graph convolution and deconvolution layers to learn the translation mapping considering both global and local features. A new conditional graph discriminator is proposed to classify the target graphs by conditioning on source graphs while training. Extensive experiments on multiple synthetic and real-world datasets in the domain of cybernetworks, the Internet of Things, and neuroscience demonstrate that the proposed GT-GAN model significantly outperforms other baseline methods in terms of both effectiveness and scalability. For instance, GT-GAN outperforms the classical state-of-the-art (SOTA) methods in functional connectivity (FC) prediction of brain networks by at least 32.5%.Unmanned Aerial Vehicles (UAVs) exhibit great agility but usually require an experienced pilot to operate them in certain applications such as inspection for disaster scenarios or buildings. The reduction of cognitive overload when driving this kind of aerial robot becomes a challenge and several solutions can be found in the literature. A new virtual control scheme for reducing this cognitive overload when controlling an aerial robot is proposed in this paper. The architecture is based on a novel interaction Drone Exocentric Advanced Metaphor (DrEAM) located in a Cave Automated Virtual Environment (CAVE) and a real robot containing an embedded controller based on quaternion formulation. The testing room, where real robots are evolving, is located away from the CAVE and they are connected via UDP in a ground station. The user controls manually a virtual drone through the DrEAM interaction metaphor, and the real robot imitates autonomously in real time the trajectory imposed by the user in the virtual environment. Experimental results illustrate the easy implementation and feasibility of the proposed scheme in two different scenarios. Results from these tests show that the mental effort when controlling a drone using the proposed virtual control scheme is lower than when controlling it in direct view. Moreover, the easy maneuverability and controllability of the real drone is also demonstrated in real time experiments.We present an efficient locomotion technique that can reduce cybersickness through aligning the visual and vestibular induced self-motion illusion. Our locomotion technique stimulates proprioception consistent with the visual sense by intentional head motion, which includes both the head’s translational movement and yaw rotation. A locomotion event is triggered by the hand-held controller together with an intended physical head motion simultaneously. Based on our method, we further explore the connections between the level of cybersickness and the velocity of self motion through a series of experiments. We first conduct Experiment 1 to investigate the cybersickness induced by different translation velocities using our method and then conduct Experiment 2 to investigate the cybersickness induced by different angular velocities. Our user studies from these two experiments reveal a new finding on the correlation between translation/angular velocities and the level of cybersickness. The cybersickness is greatest at the lowest velocity using our method, and the statistical analysis also indicates a possible U-shaped relation between the translation/angular velocity and cybersickness degree. Finally, we conduct Experiment 3 to evaluate the performances of our method and other commonly-used locomotion approaches, i.e., joystick-based steering and teleportation. The results show that our method can significantly reduce cybersickness compared with the joystick-based steering and obtain a higher presence compared with the teleportation. These advantages demonstrate that our method can be an optional locomotion solution for immersive VR applications using commercially available HMD suites only.Applications like physics, medicine, earth sciences, mechanical engineering, geo-engineering, bio-engineering use tensorial data. For example, tensors are used in formulating the balance equations of charge, mass, momentum, or energy as well as the constitutive relations that complement them. Some of these tensors (i.e. stiffness tensor, strain gradient, photo-elastic tensor) are of order higher than two. Currently, there are nearly no visualization techniques for such data beyond glyphs. An important reason for this is the limit of currently used tensor decomposition techniques. In this article, we propose to use the deviatoric decomposition to draw lines describing tensors of arbitrary order in three dimensions. The deviatoric decomposition splits a three-dimensional tensor of any order with any type of index symmetry into totally symmetric, traceless tensors. These tensors, called deviators, can be described by a unique set of directions (called multipoles by J. C. Maxwell) and scalars. These multipoles allow the definition of multipole lines which can be computed in a similar fashion to tensor lines and allow a line-based visualization of three-dimensional tensors of any order. We give examples for the visualization of symmetric, second-order tensor fields as well as fourth-order tensor fields. To allow an interpretation of the multipole lines, we analyze the connection between the multipoles and the eigenvectors/eigenvalues in the second-order case. For the fourth-order stiffness tensor, we prove relations between multipoles and the eigenvectors of the second-order right Cauchy-Green tensor and present different interpretations of the multipole lines.Piezoelectric materials have been developed since early 1900s and many research had been conducted on the composition and process to obtain higher piezoelectric constants (d33). Within composition research, lead perovskite relaxor piezoelectric single crystals (SCs) of Pb(Mg1/3Nb2/3)O3 – lead titanate PbTiO3 type have been actively studied since 1990s because of their outstanding d33>1,500 pC/N compared to those of conventional Pb(Zr,Ti)O3 ceramics. A major driving force of these SC research has been promoted by mass-production of ultrasound transducers and arrays probes for medical diagnostic systems since early 2000s. However, the higher d33 material and process research for these ultrasound devices are almost saturated. In this review article, we present a brief overview of the history, current situation, and future perspective of piezoelectric SCs. Authors believe that main research in the next century is high d33 SCs with a high composition uniformity and low-energy SC growth methods, such as solid-state-SC growth, low-loss SC transducer manufacturing technique, and improved poling process.