To date, liquid metals have been widely applied in many fields such as electronics, mechanical engineering and energy. In the last decade, with a better understanding of the physicochemical ...properties such as low viscosity, good fluidity, high thermal/electrical conductivity and good biocompatibility, gallium and gallium-based low-melting-point (near or below physiological temperature) alloys have attracted considerable attention in bio-related applications. This tutorial review introduces the common performances of liquid metals, highlights their featured properties, as well as summarizes various state-of-the-art bio-applications involving carriers for drug delivery, molecular imaging, cancer therapy and biomedical devices. Challenges for the clinical translation of liquid metals are also discussed.
Spatiotemporal and motion features are two complementary and crucial information for video action recognition. Recent state-of-the-art methods adopt a 3D CNN stream to learn spatiotemporal features ...and another flow stream to learn motion features. In this work, we aim to efficiently encode these two features in a unified 2D framework. To this end, we first propose a STM block, which contains a Channel-wise SpatioTemporal Module (CSTM) to present the spatiotemporal features and a Channel-wise Motion Module (CMM) to efficiently encode motion features. We then replace original residual blocks in the ResNet architecture with STM blcoks to form a simple yet effective STM network by introducing very limited extra computation cost. Extensive experiments demonstrate that the proposed STM network outperforms the state-of-the-art methods on both temporal-related datasets (i.e., Something-Something v1 & v2 and Jester) and scene-related datasets (i.e., Kinetics-400, UCF-101, and HMDB-51) with the help of encoding spatiotemporal and motion features together.
The emerging mobile edge computing (MEC) evolutionarily extends the cloud services to the network edge. In order to efficiently coordinate distributed edge resources, software defined networking ...(SDN) at the network edge has been explored to realize the integrated management of communication, computation, and cache (3C) resources. However, many research efforts, in software-defined edge networks, are mainly devoted to 1C or 2C resource sharing. Motivated by high service performance and user demands, we propose a user-centric edge resource sharing model for software-defined ultra-dense network (SD-UDN) where multiple MEC servers around small base stations (SBSs) can share their 3C resources through OpenFlow-enabled switches. In particular, the service models of MEC servers and users are formulated to optimize the service process by minimizing the service delay, which is NP-hard. To address this NP-hard issue, a service association model is constructed based on design structure matrix (DSM), and a simulated annealing algorithm is employed to further optimize the service association model for reducing time complexity and offering a nearoptimal solution. Compared with traditional 1C or 2C resource sharing, the proposed edge resource sharing model can guarantee lower service delay for users.
Current CNN based object detectors need initialization from pre-trained ImageNet classification models, which are usually time-consuming. In this paper, we present a fully convolutional feature mimic ...framework to train very efficient CNN based detectors, which do not need ImageNet pre-training and achieve competitive performance as the large and slow models. We add supervision from high-level features of the large networks in training to help the small network better learn object representation. More specifically, we conduct a mimic method for the features sampled from the entire feature map and use a transform layer to map features from the small network onto the same dimension of the large network. In training the small network, we optimize the similarity between features sampled from the same region on the feature maps of both networks. Extensive experiments are conducted on pedestrian and common object detection tasks using VGG, Inception and ResNet. On both Caltech and Pascal VOC, we show that the modified 2.5× accelerated Inception network achieves competitive performance as the full Inception Network. Our faster model runs at 80 FPS for a 1000×1500 large input with only a minor degradation of performance on Caltech.
This paper targets on the problem of set to set recognition, which learns the metric between two image sets. Images in each set belong to the same identity. Since images in a set can be ...complementary, they hopefully lead to higher accuracy in practical applications. However, the quality of each sample cannot be guaranteed, and samples with poor quality will hurt the metric. In this paper, the quality aware network (QAN) is proposed to confront this problem, where the quality of each sample can be automatically learned although such information is not explicitly provided in the training stage. The network has two branches, where the first branch extracts appearance feature embedding for each sample and the other branch predicts quality score for each sample. Features and quality scores of all samples in a set are then aggregated to generate the final feature embedding. We show that the two branches can be trained in an end-to-end manner given only the set-level identity annotation. Analysis on gradient spread of this mechanism indicates that the quality learned by the network is beneficial to set-to-set recognition and simplifies the distribution that the network needs to fit. Experiments on both face verification and person re-identification show advantages of the proposed QAN. The source code and network structure can be downloaded at GitHub.
To offload and alleviate the heavy base station (BS) traffic load caused by the rapidly growing video services, device-to-device (D2D) communication, as one of the most indispensable technologies of ...the future cellular networks, can be potentially exploited by mobile users to distribute videos for a BS. In this paper, an effective pricing-based multicast video distribution system and a grid-based clustering method are proposed to support the distribution. Moreover, with the consideration of users' mobility and social characteristics, we classify them into multicast and core types by studying the user stay probability and familiarity. In particular, core users can cooperate with the BS to distribute videos to the multicast users through intracluster D2D multicast. However, core users cannot selflessly help the BS to distribute videos; instead, they will evaluate their personal benefits before distributing the videos to the multicast users. Further, a Stackelberg game-based pricing mechanism is proposed to inspire the core users to distribute videos. Simulation results demonstrate that the proposed mechanism can not only effectively alleviate the BS traffic load, but also significantly improve the effectiveness and reliability of video transmission.
Convolutional neural networks have gained a remarkable success in computer vision. However, most usable network architectures are hand-crafted and usually require expertise and elaborate design. In ...this paper, we provide a block-wise network generation pipeline called BlockQNN which automatically builds high-performance networks using the Q-Learning paradigm with epsilon-greedy exploration strategy. The optimal network block is constructed by the learning agent which is trained sequentially to choose component layers. We stack the block to construct the whole auto-generated network. To accelerate the generation process, we also propose a distributed asynchronous framework and an early stop strategy. The block-wise generation brings unique advantages: (1) it performs competitive results in comparison to the hand-crafted state-of-the-art networks on image classification, additionally, the best network generated by BlockQNN achieves 3.54% top-1 error rate on CIFAR-10 which beats all existing auto-generate networks. (2) in the meanwhile, it offers tremendous reduction of the search space in designing networks which only spends 3 days with 32 GPUs, and (3) moreover, it has strong generalizability that the network built on CIFAR also performs well on a larger-scale ImageNet dataset.
Cascade has been widely used in face detection, where classifier with low computation cost can be firstly used to shrink most of the background while keeping the recall. The cascade in detection is ...popularized by seminal Viola-Jones framework and then widely used in other pipelines, such as DPM and CNN. However, to our best knowledge, most of the previous detection methods use cascade in a greedy manner, where previous stages in cascade are fixed when training a new stage. So optimizations of different CNNs are isolated. In this paper, we propose joint training to achieve end-to-end optimization for CNN cascade. We show that the back propagation algorithm used in training CNN can be naturally used in training CNN cascade. We present how jointly training can be conducted on naive CNN cascade and more sophisticated region proposal network (RPN) and fast R-CNN. Experiments on face detection benchmarks verify the advantages of the joint training.
Abstract
Members of the pentatricopeptide repeat (PPR) protein family are sequence-specific RNA-binding proteins that play crucial roles in organelle RNA metabolism. Each PPR protein consists of a ...tandem array of PPR motifs, each of which aligns to one nucleotide of the RNA target. The di-residues in the PPR motif, which are referred to as the PPR codes, determine nucleotide specificity. Numerous PPR codes are distributed among the vast number of PPR motifs, but the correlation between PPR codes and RNA bases is poorly understood, which hinders target RNA prediction and functional investigation of PPR proteins. To address this issue, we developed a modular assembly method for high-throughput construction of designer PPRs, and by using this method, 62 designer PPR proteins containing various PPR codes were assembled. Then, the correlation between these PPR codes and RNA bases was systematically explored and delineated. Based on this correlation, the web server PPRCODE (http://yinlab.hzau.edu.cn/pprcode) was developed. Our study will not only serve as a platform for facilitating target RNA prediction and functional investigation of the large number of PPR family proteins but also provide an alternative strategy for the assembly of custom PPRs that can potentially be used for plant organelle RNA manipulation.