Hyperspectral images with high spectral resolution provide new insights into recognizing subtle differences in similar substances. However, object detection in hyperspectral images faces significant challenges in intra- and inter-class similarity due to the spatial differences in hyperspectral inter-bands and unavoidable interferences, e.g., sensor noises and illumination. To alleviate the hyperspectral inter-bands inconsistencies and redundancy, we propose a novel network termedSpectralDiscrepancy andCross-Modal semantic consistency learning (SDCM), which facilitates the extraction of consistent information across a wide range of hyperspectral bands while utilizing the spectral dimension to pinpoint regions of interest. Specifically, we leverage a semantic consistency learning (SCL) module that utilizes inter-band contextual cues to diminish the heterogeneity of information among bands, yielding highly coherent spectral dimension representations. On the other hand, we incorporate a spectral gated generator (SGG) into the framework that filters out the redundant data inherent in hyperspectral information based on the importance of the bands. Then, we design the spectral discrepancy aware (SDA) module to enrich the semantic representation of high-level information by extracting pixel-level spectral features. Extensive experiments on two hyperspectral datasets demonstrate that our proposed method achieves state-of-the-art performance when compared with other ones.

Recent advances in blockchain research have been made in two important directions. One is refined resilience analysis utilizing game theory to study the consequences of selfish behavior of users (miners), and the other is the extension from a linear (chain) structure to a non-linear (graphical) structure for performance improvements, such as IOTA and Graphcoin. The first question that comes to mind is what improvements a blockchain system would see by leveraging these new advances. In this article, we consider three major properties for a blockchain system: α-partial verification, scalability, and finality-duration. We establish a formal framework and prove that no blockchain system can achieve α-partial verification for any fixed constant α, high scalability, and low finality-duration simultaneously. We observe that classical blockchain systems like Bitcoin achieve full verification (α =1) and low finality-duration, Ethereum 2.0 Sharding achieves low finality-duration and high scalability. We are interested in whether it is possible to partially satisfy the three properties.

btaining high signal-to-noise ratio (SNR) databtaining high signal-to-noise ratio (SNR) dataO is significant for the subsequent processing and interpretation of seismic data. In recent years, the convolutional neural network (CNN) has been widely used in seismic data denoising. However, the existing CNN-based method usually has a single receptive field, making it difficult to effectively extract feature maps at different scales. Therefore, we propose a multiscale residual U-shaped CNN (MRUnet) by combining the multiscale structure, residual structure, and skip connection structure to cope with the random noise of the post-stack seismic data. The network can use convolutional kernels of different sizes for feature extraction and transfer these features through more extensive skip connections. We construct a training set using existing seismic data and transfer the trained model to field data for denoising experiments. Experiments on synthetic and field data demonstrate that by training the network, a model that removes the random noise from the post-stack seismic data can be obtained and outperforms the existing ones.

Trusted execution environment (TEE) technology has many uses, such as protecting data in the cloud and improving security for industrial IoT. However, there are technical challenges that limit its widespread adoption. These challenges include the fact that different TEE vendors have incompatible solutions, and devices equipped with the same TEE technology may belong to different owners, making it difficult to establish trust between them. To address these challenges and fully utilize TEE technology, a decentralized coordination mechanism called DHTee is proposed. DHTee uses blockchain technology to support key TEE functions in a heterogeneous TEE environment, especially attestation service. Devices equipped with TEE can interact securely with the blockchain to determine whether potential collaborating devices meet the requirements. DHTee is also flexible and can support new TEE schemes without affecting existing TEEs.

This paper proposes a new graph convolutional operator called central difference graph convolution (CDGC) for skeleton based action recognition. It is not only able to aggregate node information like a vanilla graph convolutional operation but also gradient information. Without introducing any additional parameters, CDGC can replace vanilla graph convolution in any existing Graph Convolutional Networks (GCNs). In addition, an accelerated version of the CDGC is developed which greatly improves the speed of training. Experiments on two popular large-scale datasets NTU RGB+D 60 & 120 have demonstrated the efficacy of the proposed CDGC. Code is available athttps://github.com/iesymiao/CD-GCN.

State-of-the-art object detectors usually progressively downsample the input image until it is represented by small feature maps, which loses the spatial information and compromises the representation of small objects. In this article, we propose a context-aware block net (CAB Net) to improve small object detection by building high-resolution and strong semantic feature maps. To internally enhance the representation capacity of feature maps with high spatial resolution, we delicately design the context-aware block (CAB). CAB exploits pyramidal dilated convolutions to incorporate multilevel contextual information without losing the original resolution of feature maps. Then, we assemble CAB to the end of the truncated backbone network (e.g., VGG16) with a relatively small downsampling factor (e.g., 8) and cast off all following layers. CAB Net can capture both basic visual patterns as well as semantical information of small objects, thus improving the performance of small object detection. Experiments conducted on the benchmark Tsinghua-Tencent 100K and the Airport dataset show that CAB Net outperforms other top-performing detectors by a large margin while keeping real-time speed, which demonstrates the effectiveness of CAB Net for small object detection.

In this paper, we present the design and implementation of a privacy preserving event based UTXO (Unspent Transaction Output) transaction system. Unlike the existing approaches that often depend on smart contracts where digital assets are first locked in a vault, and then released according to event triggers, the event based transaction system encodes event outcome as part of the UTXO note and safeguards event privacy by shielding it with zero-knowledge proof based protocols such that associations between UTXO notes and events are hidden from the validators. Without relying on any triggering mechanism, the proposed transaction system separates event processing from the transaction processing where confidential event based UTXO notes (event based UTXOs or conditional UTXOs) can be transferred freely with full privacy in an asynchronous manner, only with their asset values conditional to the linked event outcomes. The main advantage of such design is that it enables free trade of event based digital assets and prevents the assets from being locked. We implemented the proposed transaction system by extending the Zerocoin data model and protocols. The system is implemented and evaluated using xJsnark.

Industrial IoT (IIoT) is critical for industrial infrastructure modernization and digitalization. Therefore, it is of utmost importance to provide adequate protection of the IIoT system. A modern IIoT system usually consists of a large number of devices that are deployed in multiple locations and owned/managed by different entities who do not fully trust each other. These features make it harder to manage the system in a coherent manner and utilize existing security mechanisms to offer adequate protection. The emerging blockchain technology provides a powerful tool for IIoT system management and protection because the IIoT nature of distributed deployment and involvement of multiple stakeholders fits the design philosophy of blockchain well. Most existing blockchain construction mechanisms are not scalable enough and too heavy for an IIoT system. One promising way to overcome these limitations is utilizing hardware based trusted execution environment (TEE) in blockchain construction. However, most of the existing works on this direction do not consider the characteristics of IIoT devices (e.g., fixed functionality and limited supply) and face several limitations when they are applied for IIoT system management and protection, such as high energy consumption, single root-of-trust, and low decentralization level. To mitigate these challenges, we propose a novel field programmable gate array (FPGA) based blockchain system. It leverages the FPGA to build a simple but efficient TEE for IIoT devices, and removes the single root-of-trust by allowing all stakeholders to participate in the management of the devices. The FPGA based blockchain system shifts the computation/storage intensive part of blockchain management to more powerful computers but still involves the IIoT devices in the block construction to achieve a high level of decentralization. We implement the major FPGA components of the design and evaluate the performance of the whole system with a simulation tool to demonstrate its feasibility for IIoT applications.

IoT devices provide a rich data source that is not available in the past, which is valuable for a wide range of intelligence applications, especially deep neural network (DNN) applications that are data-thirsty. An established DNN model provides useful analysis results that can improve the operation of IoT systems in turn. The progress in distributed/federated DNN training further unleashes the potential of integration of IoT and intelligence applications. When a large number of IoT devices are deployed in different physical locations, distributed training allows training modules to be deployed to multiple edge data centers that are close to the IoT devices to reduce the latency and movement of large amounts of data. In practice, these IoT devices and edge data centers are usually owned and managed by different parties, who do not fully trust each other or have conflicting interests. It is hard to coordinate them to provide end-to-end integrity protection of the DNN construction and application with classical security enhancement tools. For example, one party may share an incomplete data set with others, or contribute a modified sub DNN model to manipulate the aggregated model and affect the decision-making process. To mitigate this risk, we propose a novel blockchain based end-to-end integrity protection scheme for DNN applications integrated with an IoT system in the edge computing environment. The protection system leverages a set of cryptography primitives to build a blockchain adapted for edge computing that is scalable to handle a large number of IoT devices. The customized blockchain is integrated with a distributed/federated DNN to offer integrity and authenticity protection services.

Bribery in election (or computational social choice in general) is an important problem that has received a considerable amount of attention. In the classic bribery problem, the briber (or attacker) bribes some voters in attempting to make the briber’s designated candidate win an election. In this paper, we introduce a novel variant of the bribery problem, “Election with Bribed Voter Uncertainty” or BVU for short, accommodating the uncertainty that the vote of a bribed voter may or may not be counted. This uncertainty occurs either because a bribed voter may not cast its vote in fear of being caught, or because a bribed voter is indeed caught and therefore its vote is discarded. As a first step towards ultimately understanding and addressing this important problem, we show that it does not admit any multiplicative O(1)-approximation algorithm modulo standard complexity assumptions. We further show that there is an approximation algorithm that returns a solution with an additive-ε error in FPT time for any fixed ε.

We consider the electoral bribery problem in computational social choice. In this context, extensive studies have been carried out to analyze the computational vulnerability of various voting (or election) rules. However, essentially all prior studies assume a deterministic model where each voter has an associated threshold value, which is used as follows. A voter will take a bribe and vote according to the attacker's (i.e., briber's) preference when the amount of the bribe is above the threshold, and a voter will not take a bribe when the amount of the bribe is not above the threshold (in this case, the voter will vote according to its own preference, rather than the attacker's). In this paper, we initiate the study of a more realistic model where each voter is associated with a willingness function, rather than a fixed threshold value. The willingness function characterizes the likelihood a bribed voter would vote according to the attacker's preference; we call this bribe-effect uncertainty. We characterize the computational complexity of the electoral bribery problem in this new model. In particular, we discover a dichotomy result: a certain mathematical property of the willingness function dictates whether or not the computational hardness can serve as a deterrence to bribery attackers.

With deep convolutional features, cross-region matching (CRM) has recently shown superior performance on image retrieval. It evaluates image similarity by comparing image regions at different locations and scales, and is, therefore, more robust to geometric variance of objects. This paper first scrutinizes CRM-based image retrieval to provide a rigorous probabilistic interpretation by following the probability ranking principle. In addition to manifesting the assumptions implicitly taken by CRM, our interpretation highlights a fundamental issue hindering the performance of CRM-when comparing two image regions, CRM ignores modeling the distribution of the visual concept class associated with an image region, making the similarity comparison less precise. Taking advantage of the unprecedented representation capability of deep convolutional features, this paper proposes one approach to tackle that issue. It treats locally clustered image regions as a pseudo-labeled class sharing the same visual concept and utilizes them to model the distribution of the visual concept class associated with an image region. Both non-parametric and parametric methods are developed for this purpose, with careful probabilistic justification. Extensive experimental study on multiple benchmark data sets demonstrates the superior performance of the proposed pseudo-label approach to CRM and other comparable methods, with the maximum improvement of more than 10 percentage points over CRM.

This paper proposes three simple, compact yet effective representations of depth sequences, referred to respectively as dynamic depth images (DDI), dynamic depth normal images (DDNI), and dynamic depth motion normal images (DDMNI), for both isolated and continuous action recognition. These dynamic images are constructed from a segmented sequence of depth maps using hierarchical bidirectional rank pooling to effectively capture the spatial-temporal information. Specifically, DDI exploits the dynamics of postures over time, and DDNI and DDMNI exploit the 3-D structural information captured by depth maps. Upon the proposed representations, a convolutional neural network (ConvNet)-based method is developed for action recognition. The image-based representations enable us to fine-tune the existing ConvNet models trained on image data without training a large number of parameters from scratch. The proposed method achieved the state-of-art results on three large datasets, namely, the large-scale continuous gesture recognition dataset (means the Jaccard index 0.4109), the large-scale isolated gesture recognition dataset (59.21%), and the NTU RGB+D dataset (87.08% cross-subject and 84.22% cross-view) even though only the depth modality was used.

Scene flow describes the motion of 3D objects in real world and potentially could be the basis of a good feature for 3D action recognition. However, its use for action recognition, especially in the context of convolutional neural networks (ConvNets), has not been previously studied. In this paper, we propose the extraction and use of scene flow for action recognition from RGB-D data. Previous works have considered the depth and RGB modalities as separate channels and extract features for later fusion. We take a different approach and consider the modalities as one entity, thus allowing feature extraction for action recognition at the beginning. Two key questions about the use of scene flow for action recognition are addressed: how to organize the scene flow vectors and how to represent the long term dynamics of videos based on scene flow. In order to calculate the scene flow correctly on the available datasets, we propose an effective self-calibration method to align the RGB and depth data spatially without knowledge of the camera parameters. Based on the scene flow vectors, we propose a new representation, namely, Scene Flow to Action Map (SFAM), that describes several long term spatio-temporal dynamics for action recognition. We adopt a channel transform kernel to transform the scene flow vectors to an optimal color space analogous to RGB. This transformation takes better advantage of the trained ConvNets models over ImageNet. Experimental results indicate that this new representation can surpass the performance of state-of-the-art methods on two large public datasets.

Modern supply chain is a complex system and plays an important role for different sectors under the globalization economic integration background. Supply chain management system is proposed to handle the increasing complexity and improve the efficiency of flows of goods. It is also useful to prevent potential frauds and guarantee trade compliance. Currently, most companies maintain their own IT system for supply chain management. However, this approach has some limitations that prevent one to get most of the supply chain information. Using emerging decentralized ledger technology to build supply chain management system is a promising direction. However, decentralized ledger usually suffers from low performance and lack of capability to protect information stored on the ledger. To overcome these challenges, we propose CoC, a novel supply chain management system based on hybrid decentralized ledger. We develop an efficient block construction method with the model and security mechanism to prevent unauthorized access to data stored on the ledger.

Neural activations produced by deep convolutional networks have recently become state-of-the-art representation for image retrieval. To obtain a global image representation, sum-pooling has been frequently used to aggregate activations of convolutional feature maps. This work first presents an understanding on the effectiveness of sum-pooling via probabilistic interpretation, by proving that sum-pooling is an upper bound of the probability that a visual pattern is present in an image. To further answer the optimality of sum-pooling, a quantitative analysis based on the Infomax principle in neural networks is provided. It shows that sum-pooling aligns well with the leading eigenvector of principal component analysis (PCA) applied to the activations of a feature map. Moreover, considering the 2D matrix structure of feature maps, a two-directional 2DPCA-based pooling scheme is proposed to aggregate the convolutional activations. Experiments on multiple benchmark image retrieval datasets demonstrate the above analysis and the superiority of the proposed pooling scheme.

Blockchain, or distributed ledger, provides a way to build various decentralized systems without relying on any single trusted party. This is especially attractive for smart contracts, that different parties do not need to trust each other to have a contract, and the distributed ledger can guarantee correct execution of the contract. Most existing distributed ledger based smart contract systems process smart contracts in a serial manner, i.e., all users have to run a contract before its result can be accepted by the system. Although this approach is easy to implement and manage, it is not scalable and greatly limits the system's capability of handling a large number of smart contracts. In order to address this problem, we propose a scalable smart contract execution scheme that can run multiple smart contract in parallel to improve throughput of the system. Our scheme relies on two key techniques: a fair contract partition algorithm leveraging integer linear programming to partition a set of smart contracts into multiple subsets, and a random assignment protocol assigning subsets randomly to a subgroup of users. We prove that, our scheme is secure as long as more than 50% of the computational power is possessed by honest nodes. We then conduct experiments with data from existing smart contract system to evaluate the efficiency of our scheme. The results demonstrate that our approach is scalable and much more efficient than the existing smart contract platform.

Transaction system build on top of blockchain, especially smart contract, is becoming an important part of world economy. However, there is a lack of formal study on the behavior of users in these systems, which leaves the correctness and security of such system without a solid foundation. Unlike mining, in which the reward for mining a block is fixed, different execution results of a smart contract may lead to significantly different payoffs of users, which gives more incentives for some user to follow a branch that contains a wrong result, even if the branch is shorter. It is thus important to understand the exact probability that a branch is being selected by the system. We formulate this problem as the (+-)-Biased Ballot Problem as follows: there are n voters one by one voting for either of the two candidates A and B. The probability of a user voting for A or B depends on whether the difference between the current votes of A and B is positive or negative. Our model takes into account the behavior of three different kinds of users when a branch occurs in the system -- users having preference over a certain branch based on the history of their transactions, and users being indifferent and simply follow the longest chain. We study two important probabilities that are closely related with a blockchain based system - the probability that A wins at last, and the probability that A receives d votes first. We show how to recursively calculate the two probabilities for any fixed n and d, and also discuss their asymptotic values when n and d are sufficiently large.

Efficient Human Epithelial-2 cell image classification can facilitate the diagnosis of many autoimmune diseases. This paper proposes an automatic framework for this classification task, by utilizing the deep convolutional neural networks (CNNs) which have recently attracted intensive attention in visual recognition. In addition to describing the proposed classification framework, this paper elaborates several interesting observations and findings obtained by our investigation. They include the important factors that impact network design and training, the role of rotation-based data augmentation for cell images, the effectiveness of cell image masks for classification, and the adaptability of the CNN-based classification system across different datasets. Extensive experimental study is conducted to verify the above findings and compares the proposed framework with the well-established image classification models in the literature. The results on benchmark datasets demonstrate that 1) the proposed framework can effectively outperform existing models by properly applying data augmentation, 2) our CNN-based framework has excellent adaptability across different datasets, which is highly desirable for cell image classification under varying laboratory settings. Our system is ranked high in the cell image classification competition hosted by ICPR 2014.

This paper proposes three simple, compact yet effective representations of depth sequences, referred to respectively as Dynamic Depth Images (DDI), Dynamic Depth Normal Images (DDNI) and Dynamic Depth Motion Normal Images (DDMNI). These dynamic images are constructed from a sequence of depth maps using bidirectional rank pooling to effectively capture the spatial-temporal information. Such image-based representations enable us to fine-tune the existing ConvNets models trained on image data for classification of depth sequences, without introducing large parameters to learn. Upon the proposed representations, a convolutional Neural networks (ConvNets) based method is developed for gesture recognition and evaluated on the Large-scale Isolated Gesture Recognition at the ChaLearn Looking at People (LAP) challenge 2016. The method achieved 55.57% classification accuracy and ranked 2ndplace in this challenge but was very close to the best performance even though we only used depth data.

This paper addresses the problem of continuous gesture recognition from sequences of depth maps using Convolutional Neural networks (ConvNets). The proposed method first segments individual gestures from a depth sequence based on quantity of movement (QOM). For each segmented gesture, an Improved Depth Motion Map (IDMM), which converts the depth sequence into one image, is constructed and fed to a ConvNet for recognition. The IDMM effectively encodes both spatial and temporal information and allows the fine-tuning with existing ConvNet models for classification without introducing millions of parameters to learn. The proposed method is evaluated on the Large-scale Continuous Gesture Recognition of the ChaLearn Looking at People (LAP) challenge 2016. It achieved the performance of 0.2655 (Mean Jaccard Index) and ranked 3rdplace in this challenge.

Elliptic curve based cryptography has attracted a lot of attention because these schemes usually require less storage than those based on finite field. It is also used to construct bilinear pairing, which is an essential tool to construct various cryptography schemes. The security of a large portion of these schemes depends on the hardness of ECDLP. Unlike discrete logarithm problem on finite field and integer factorization problem, currently there is no sub-exponential algorithm for general ECDLP, and parallel collision search is the most effective approach. Using parallel collision search for ECDLP is not only computation intensive but also storage intensive. Therefore, it requires a large number of machines to collaborate to finish the job. Considering all these requirements, we propose a solution for ECDLP using MapReduce and parallel collision search in the cloud environment, which can be scaled to involve a huge number of computation nodes. We implement the solution using Amazon EC2, and the experiment results show its scalability and effectiveness.

This paper proposes a new method, i.e., weighted hierarchical depth motion maps (WHDMM) + three-channel deep convolutional neural networks (3ConvNets), for human action recognition from depth maps on small training datasets. Three strategies are developed to leverage the capability of ConvNets in mining discriminative features for recognition. First, different viewpoints are mimicked by rotating the 3-D points of the captured depth maps. This not only synthesizes more data, but also makes the trained ConvNets view-tolerant. Second, WHDMMs at several temporal scales are constructed to encode the spatiotemporal motion patterns of actions into 2-D spatial structures. The 2-D spatial structures are further enhanced for recognition by converting the WHDMMs into pseudocolor images. Finally, the three ConvNets are initialized with the models obtained from ImageNet and fine-tuned independently on the color-coded WHDMMs constructed in three orthogonal planes. The proposed algorithm was evaluated on the MSRAction3D, MSRAction3DExt, UTKinect-Action, and MSRDailyActivity3D datasets using cross-subject protocols. In addition, the method was evaluated on the large dataset constructed from the above datasets. The proposed method achieved 2-9% better results on most of the individual datasets. Furthermore, the proposed method maintained its performance on the large dataset, whereas the performance of existing methods decreased with the increased number of actions.

In this paper, we propose to adopt ConvNets to recognize human actions from depth maps on relatively small datasets based on Depth Motion Maps (DMMs). In particular, three strategies are developed to effectively leverage the capability of ConvNets in mining discriminative features for recognition. Firstly, different viewpoints are mimicked by rotating virtual cameras around subject represented by the 3D points of the captured depth maps. This not only synthesizes more data from the captured ones, but also makes the trained ConvNets view-tolerant. Secondly, DMMs are constructed and further enhanced for recognition by encoding them into Pseudo-RGB images, turning the spatial-temporal motion patterns into textures and edges. Lastly, through transferring learning the models originally trained over ImageNet for image classification, the three ConvNets are trained independently on the color-coded DMMs constructed in three orthogonal planes. The proposed algorithm was extensively evaluated on MSRAction3D, MSRAction3DExt and UTKinect-Action datasets and achieved the state-of-the-art results on these datasets.