In wireless-powered cognitive radio networks, short-packet communication has emerged as a pivotal technology for supporting Internet of Things (IoT) services due to its low-latency characteristics. However, the traditional Shannon capacity theory fails to accurately characterize the finite blocklength transmission properties of short-packet communication. Moreover, the inherent uncertainties in spectrum contention between primary and secondary users, coupled with energy harvesting in coverage-limited scenarios, further complicate the optimization of Age of Information (AoI). To address these challenges, this paper proposes a dynamic scheduling method for AoI-sensitive short-packet communication. First, based on the finite blocklength transmission theory, we derive a closed-form expression for the successful transmission probability of cognitive users’ short-packet data under interference constraints, which quantifies the impact of energy harvesting efficiency and spectrum sensing accuracy on transmission reliability. Second, we formulate a mixed-integer nonlinear programming problem to minimize the system’s expected weighted AoI, jointly optimizing spectrum access, energy allocation, and short packet encoding parameters. To solve this problem, we design a Lyapunov optimization-based maximum weight scheduling strategy, which achieves real-time decision-making by dynamically balancing data queue backlog and AoI weight factors. Simulation results demonstrate that the proposed strategy significantly outperforms round-robin and random scheduling strategies, achieving performance closer to the theoretical lower bound. Furthermore, the impact of short-packet coding length and transmission power on the system’s weighted sum AoI is thoroughly investigated.

Remote monitoring systems heavily rely on the Age of Information (AoI) as a critical metric to gauge the timeliness of status updates received by a destination. Presently, the predominant focus of AoI evaluations in sensor networks revolves around communication systems employing homogeneous preemption, often neglecting the issue of packet loss. Consequently, our research directs attention towards the single-buffer state update system featuring non-homogeneous preemption in scenarios involving packet dropping. This system entails a wireless communication network comprising three distinct components: a buffer, a server, and a destination node, each generated following the Poisson process and subsequently encapsulated into brief packets for transmission by the server. Initially, a diverse source buffer preemption strategy was employed, wherein packets of higher priority consistently superseded those of lower priority in the buffer, and packets originating from the same source were preempted in the buffer, resulting in the direct discarding of preempted packets. Subsequently, we compute the average Age of Information (AAoI) for diverse sources by leveraging Stochastic Hybrid System (SHS) methodologies to manage packet priorities. Ultimately, system simulations and numerical assessments unveil that with a 0.2 probability of detecting update packets, the AoI diminishes by 23.9% as the Signal-to-Noise Ratio (SNR) escalates from 30 dB to 60 dB. Holding the SNR constant at 60 dB while extending the packet length for status updates from 200 to 600 bits results in an average AoI reduction of 14.5%.

Unlike most reinforcement learning agents which require an unrealistic amount of environment interactions to learn a new behaviour, humans excel at learning quickly by merely observing and imitating others. This ability highly depends on the fact that humans have a model of their own embodiment that allows them to infer the most likely actions that led to the observed behaviour. In this paper, we propose Action Inference by Maximising Evidence (AIME) to replicate this behaviour using world models. AIME consists of two distinct phases. In the first phase, the agent learns a world model from its past experience to understand its own body by maximising the ELBO. While in the second phase, the agent is given some observation-only demonstrations of an expert performing a novel task and tries to imitate the expert's behaviour. AIME achieves this by defining a policy as an inference model and maximising the evidence of the demonstration under the policy and world model. Our method is "zero-shot" in the sense that it does not require further training for the world model or online interactions with the environment after given the demonstration. We empirically validate the zero-shot imitation performance of our method on the Walker and Cheetah embodiment of the DeepMind Control Suite and find it outperforms the state-of-the-art baselines. Code is available at: https://github.com/argmax-ai/aime.

Offline reinforcement learning (RL) aims at learning effective policies from historical data without extra environment interactions. During our experience of applying offline RL, we noticed that previous offline RL benchmarks commonly involve significant reality gaps, which we have identified include rich and overly exploratory datasets, degraded baseline, and missing policy validation. In many real-world situations, to ensure system safety, running an overly exploratory policy to collect various data is prohibited, thus only a narrow data distribution is available. The resulting policy is regarded as effective if it is better than the working behavior policy; the policy model can be deployed only if it has been well validated, rather than accomplished the training. In this paper, we present a Near real-world offline RL benchmark, named NeoRL, to reflect these properties. NeoRL datasets are collected with a more conservative strategy. Moreover, NeoRL contains the offline training and offline validation pipeline before the online test, corresponding to real-world situations. We then evaluate recent state-of-the-art offline RL algorithms in NeoRL. The empirical results demonstrate that some offline RL algorithms are less competitive to the behavior cloning and the deterministic behavior policy, implying that they could be less effective in real-world tasks than in the previous benchmarks. We also disclose that current offline policy evaluation methods could hardly select the best policy. We hope this work will shed some light on future research and deploying RL in real-world systems.

3D Hand pose estimation from a single depth image is an essential topic in computer vision and human-computer interaction. Although the rising of deep learning boosts the accuracy a lot, the problem is still hard to solve due to the complex structure of the human hand. Two existing types of methods with deep learning, i.e. the regression-based and detection-based methods, either lose spatial information of the hand structure or lack direct supervision of the joint coordinates. In this paper, we propose a novel Differentiable Spatial Regression method which combines the advantages of these two types of methods to overcome each other's shortcomings. Our method uses spatial-form representation (SFR) to maintain spatial information and differentiable decoder to establish a direct supervision. Following the procedure suggested by our method, a particular model named SRNet is designed which uses a combination of 2D heatmaps and local offset maps as SFRs. Two modules named Plane Regression and Depth Regression are designed as differentiable decoder to regress plane coordinates and depth coordinates respectively. Ablation study demonstrates the superiority of our method over the two combined methods since the differentiable decoder leads to better SFRs learned by the network itself other than human design. Extensive experiments on four public datasets demonstrate that SRNet is comparable with the state-of-the-art models.

Just like many other topics in computer vision, image classification has achieved significant progress recently by using deep learning neural networks, especially the Convolutional Neural Networks (CNNs). Most of the existing works focused on classifying very clear natural images, evidenced by the widely used image databases, such as Caltech-256, PASCAL VOCs, and ImageNet. However, in many real applications, the acquired images may contain certain degradations that lead to various kinds of blurring, noise, and distortions. One important and interesting problem is the effect of such degradations to the performance of CNN-based image classification and whether degradation removal helps CNN-based image classification. More specifically, we wonder whether image classification performance drops with each kind of degradation, whether this drop can be avoided by including degraded images into training, and whether existing computer vision algorithms that attempt to remove such degradations can help improve the image classification performance. In this article, we empirically study those problems for nine kinds of degraded images-hazy images, motion-blurred images, fish-eye images, underwater images, low resolution images, salt-and-peppered images, images with white Gaussian noise, Gaussian-blurred images, and out-of-focus images. We expect this article can draw more interests from the community to study the classification of degraded images.

Although clear image classification and degraded image restoration have been studied a lot, regrettably, the degraded image classification problem has been largely overlooked. Degraded images usually have low classification performance due to the presence of blur, noise and other imperfections. Existing methods improve classification performance of degraded images by simple restoration, fine-tuning or data augment techniques. However, they ignore the useful information guided by clear images, which leads to the performance gap between degraded images and clear images. In this article, we find that the category distribution, feature distribution and visual attention of degraded images are usually inconsistent with that of clear images. Motivated by this observation, we propose an end-to-end Consistency Guided Network, named CG-Net, for degraded image classification. More specifically, we first propose Category Consistency Loss (CCL) to guide the model to learn category distribution that is more consistent with clear images. Second, we propose Semantic Consistency Loss (SCL) to enforce the model to learn more robust feature representation that is guided by clear images. Third, we propose Visual Attention Alignment Loss (VAAL), which can align the semantically informative regions between clear images and degraded images to improve the performance of degraded images. Besides, our method is more general and suitable for various kinds of degraded images. We conduct extensive experiments on various degraded images. The experimental results show that the proposed method significantly outperforms baselines, which demonstrate the effectiveness of our proposed method.

Most existing text detection methods are mainly motivated by deep learning‐based object detection approaches, which may result in serious overlapping between detected text lines, especially in dense text scenarios. It is because text boxes are not commonly overlapped, as different from general objects in natural scenes. Moreover, text detection requires higher localisation accuracy than object detection. To tackle these problems, the authors propose a novel dense text detection network (DTDN) to localise tighter text lines without overlapping. Their main novelties are: (i) propose an intersection‐over‐union overlap loss, which considers correlations between one anchor and GT boxes and measures how many text areas one anchor contains, (ii) propose a novel anchor sample selection strategy, named CMax‐OMin, to select tighter positive samples for training. CMax‐OMin strategy not only considers whether an anchor has the largest overlap with its corresponding GT box (CMax), but also ensures the overlapping between one anchor and other GT boxes as little as possible (OMin). Besides, they train a bounding‐box regressor as post‐processing to further improve text localisation performance. Experiments on scene text benchmark datasets and their proposed dense text dataset demonstrate that the proposed DTDN achieves competitive performance, especially for dense text scenarios.

In real-time systems with threads, resource locking and priority scheduling, one faces the problem of Priority Inversion. This problem can make the behaviour of threads unpredictable and the resulting bugs can be hard to find. The Priority Inheritance Protocol is one solution implemented in many systems for solving this problem, but the correctness of this solution has never been formally verified in a theorem prover. As already pointed out in the literature, the original informal investigation of the Property Inheritance Protocol presents a correctness “proof” for an incorrect algorithm. In this paper we fix the problem of this proof by making all notions precise and implementing a variant of a solution proposed earlier. We also generalise the scheduling problem to the practically relevant case where critical sections can overlap. Our formalisation in Isabelle/HOL is based on Paulson’s inductive approach to protocol verification. The formalisation not only uncovers facts overlooked in the literature, but also helps with an efficient implementation of this protocol. Earlier implementations were criticised as too inefficient. Our implementation builds on top of the small PINTOS operating system used for teaching.

By involving only subtle motions of body parts, video-based microaction recognition is a very important but challenging problem. Most existing action recognition methods are developed for general actions, and the current state-of-the-art methods usually largely rely on high-layer features learned from convolutional neural networks (CNNs). High-layer CNN features usually contain more semantic information but less detailed information. However, detailed information can be important for microactions due to the motion subtleness of such actions. In this paper, we propose to more effectively learn midlayer CNN features for enhancing microaction recognition. More specifically, we develop a new dual-branch network for microaction recognition: one branch uses the high-layer CNN features for classification, and the second branch further explores the midlayer CNN features for classification. In the second branch, we introduce a novel subtle motion detector consisting of three modules: 1) a discriminative spatial-temporal feature learning module, which further learns the subtle motion features corresponding to the discriminative spatial-temporal regions, 2) a parallel multiplier attention module, which further refines the features learned in channels and spatial-temporal domains, and 3) an activation fusion module, which fuses the max and average activations from midlayer CNN features for classification. In the experiments, we build a new microaction video dataset, where the micromotions of interest are mixed with other larger general motions such as walking. Comprehensive experimental results verify that the proposed method yields new state-of-the-art performance in two microaction video datasets, while its performance on two generalaction video datasets is also very promising.

The correctness of a routing protocol can be divided into two parts, a liveness property proof and a safety property proof. The former requires that route(s) should be discovered and data be transmitted successfully, while the latter requires that the discovered routes have some desired characters such as containing only benign nodes. While safety properties are relatively easier to prove, the proof of liveness properties is usually harder. This paper presented a liveness proof of a secure routing protocol, SRP (P. Papadimitratos and Z. J. Haas, 2002) in Isabelle/HOL (T. Nipkow et al., 2002). The liveness property proved says that if a data package needs to be sent, then it will be sent and then received, and finally, the sender will receive an acknowledgement sent back by the receiver. There are three main contributions in this paper. Firstly, a liveness property is proved for a secure routing protocol, and this has never been done before. Secondly, our validation model can deal with arbitrarily many nodes including malicious ones, and nodes are allowed to move randomly. Thirdly, a fail set is defined to restrict the attackers' actions, so that the safety properties used to prove the liveness property can be established. The paper explains why it is reasonable to prevent malicious nodes from performing the events in fail set.

Side-effects are widely believed to impede program comprehension and have a detrimental effect upon software maintenance. This paper introduces an algorithm for side-effect removal which splits the side-effects into their pure expression meaning and their state-changing meaning. Symbolic execution is used to determine the expression meaning, while transformation is used to place the state-changing part in a suitable location in a transformed version of the program. This creates a program which is semantically equivalent to the original but guaranteed to be free from side-effects. The paper also reports the results of an empirical study which demonstrates that the application of the algorithm causes a significant improvement in program comprehension.