通过深度学习技术的开花，完全有监督的基于骨架的动作识别取得了巨大进步。但是，这些方法需要足够的标记数据，这不容易获得。相比之下，基于自我监督的骨骼的动作识别引起了更多的关注。通过利用未标记的数据，可以学会更多可概括的功能来减轻过度拟合的问题并减少大规模标记的培训数据的需求。受到MAE的启发，我们提出了一个空间式蒙面的自动编码器框架，用于基于3D骨架的自我监管的动作识别（Skeletonmae）。在MAE的掩蔽和重建管道之后，我们利用基于骨架的编码器变压器体系结构来重建蒙版的骨架序列。一种新颖的掩蔽策略，称为时空掩蔽，是根据骨架序列的联合级别和框架级别引入的。这种预训练策略使编码器输出可推广的骨骼特征具有空间和时间依赖性。给定未掩盖的骨架序列，编码器用于动作识别任务。广泛的实验表明，我们的骨架达到了出色的性能，并优于NTU RGB+D和NTU RGB+D 120数据集的最新方法。

大多数现有的视觉语言预训练方法侧重于在预先绘制期间了解解决任务并使用伯特样目标（屏蔽语言建模和图像 - 文本匹配）。虽然它们在许多理解下游任务中表现良好，但是，例如，视觉问题应答，图像文本检索和视觉存在，它们没有生成的能力。为了解决这个问题，我们为视觉语言理解和一代（UNIVL）提出了统一的多模式预培训。建议的UNIVL能够处理理解任务和生成任务。我们增强了现有的预押范例，只使用带有因果面罩的随机掩模，即掩盖未来令牌的三角面具，使得预先接受的模型可以通过设计具有自动发育能力。我们将几个以前的理解任务作为文本生成任务制定，并建议使用基于提示的方法来进行不同的下游任务进行微调。我们的实验表明，在使用相同型号的同时了解任务和生成任务之间存在权衡，以及改善两个任务的可行方式是使用更多数据。我们的UNIVL框架可以在近似验证任务和生成任务中获得最近的愿景预培训方法的性能。此外，我们开展了基于及时的FineTuning更具数据效率 - 在几次拍摄场景中表现出差异的方法。

Hybrid unmanned aerial vehicles (UAVs) integrate the efficient forward flight of fixed-wing and vertical takeoff and landing (VTOL) capabilities of multicopter UAVs. This paper presents the modeling, control and simulation of a new type of hybrid micro-small UAVs, coined as lifting-wing quadcopters. The airframe orientation of the lifting wing needs to tilt a specific angle often within $ 45$ degrees, neither nearly $ 90$ nor approximately $ 0$ degrees. Compared with some convertiplane and tail-sitter UAVs, the lifting-wing quadcopter has a highly reliable structure, robust wind resistance, low cruise speed and reliable transition flight, making it potential to work fully-autonomous outdoor or some confined airspace indoor. In the modeling part, forces and moments generated by both lifting wing and rotors are considered. Based on the established model, a unified controller for the full flight phase is designed. The controller has the capability of uniformly treating the hovering and forward flight, and enables a continuous transition between two modes, depending on the velocity command. What is more, by taking rotor thrust and aerodynamic force under consideration simultaneously, a control allocation based on optimization is utilized to realize cooperative control for energy saving. Finally, comprehensive Hardware-In-the-Loop (HIL) simulations are performed to verify the advantages of the designed aircraft and the proposed controller.

Technology advancements in wireless communications and high-performance Extended Reality (XR) have empowered the developments of the Metaverse. The demand for Metaverse applications and hence, real-time digital twinning of real-world scenes is increasing. Nevertheless, the replication of 2D physical world images into 3D virtual world scenes is computationally intensive and requires computation offloading. The disparity in transmitted scene dimension (2D as opposed to 3D) leads to asymmetric data sizes in uplink (UL) and downlink (DL). To ensure the reliability and low latency of the system, we consider an asynchronous joint UL-DL scenario where in the UL stage, the smaller data size of the physical world scenes captured by multiple extended reality users (XUs) will be uploaded to the Metaverse Console (MC) to be construed and rendered. In the DL stage, the larger-size 3D virtual world scenes need to be transmitted back to the XUs. The decisions pertaining to computation offloading and channel assignment are optimized in the UL stage, and the MC will optimize power allocation for users assigned with a channel in the UL transmission stage. Some problems arise therefrom: (i) interactive multi-process chain, specifically Asynchronous Markov Decision Process (AMDP), (ii) joint optimization in multiple processes, and (iii) high-dimensional objective functions, or hybrid reward scenarios. To ensure the reliability and low latency of the system, we design a novel multi-agent reinforcement learning algorithm structure, namely Asynchronous Actors Hybrid Critic (AAHC). Extensive experiments demonstrate that compared to proposed baselines, AAHC obtains better solutions with preferable training time.

In this paper, we propose an effective unified control law for accurately tracking agile trajectories for lifting-wing quadcopters with different installation angles, which have the capability of vertical takeoff and landing (VTOL) as well as high-speed cruise flight. First, we derive a differential flatness transform for the lifting-wing dynamics with a nonlinear model under coordinated turn condition. To increase the tracking performance on agile trajectories, the proposed controller incorporates the state and input variables calculated from differential flatness as feedforward. In particular, the jerk, the 3-order derivative of the trajectory, is converted into angular velocity as a feedforward item, which significantly improves the system bandwidth. At the same time, feedback and feedforward outputs are combined to deal with external disturbances and model mismatch. The control algorithm has been thoroughly evaluated in the outdoor flight tests, which show that it can achieve accurate trajectory tracking.

As the quality of optical sensors improves, there is a need for processing large-scale images. In particular, the ability of devices to capture ultra-high definition (UHD) images and video places new demands on the image processing pipeline. In this paper, we consider the task of low-light image enhancement (LLIE) and introduce a large-scale database consisting of images at 4K and 8K resolution. We conduct systematic benchmarking studies and provide a comparison of current LLIE algorithms. As a second contribution, we introduce LLFormer, a transformer-based low-light enhancement method. The core components of LLFormer are the axis-based multi-head self-attention and cross-layer attention fusion block, which significantly reduces the linear complexity. Extensive experiments on the new dataset and existing public datasets show that LLFormer outperforms state-of-the-art methods. We also show that employing existing LLIE methods trained on our benchmark as a pre-processing step significantly improves the performance of downstream tasks, e.g., face detection in low-light conditions. The source code and pre-trained models are available at https://github.com/TaoWangzj/LLFormer.

Image restoration under hazy weather condition, which is called single image dehazing, has been of significant interest for various computer vision applications. In recent years, deep learning-based methods have achieved success. However, existing image dehazing methods typically neglect the hierarchy of features in the neural network and fail to exploit their relationships fully. To this end, we propose an effective image dehazing method named Hierarchical Contrastive Dehazing (HCD), which is based on feature fusion and contrastive learning strategies. HCD consists of a hierarchical dehazing network (HDN) and a novel hierarchical contrastive loss (HCL). Specifically, the core design in the HDN is a Hierarchical Interaction Module, which utilizes multi-scale activation to revise the feature responses hierarchically. To cooperate with the training of HDN, we propose HCL which performs contrastive learning on hierarchically paired exemplars, facilitating haze removal. Extensive experiments on public datasets, RESIDE, HazeRD, and DENSE-HAZE, demonstrate that HCD quantitatively outperforms the state-of-the-art methods in terms of PSNR, SSIM and achieves better visual quality.

Pre-trained language models for programming languages have shown a powerful ability on processing many Software Engineering (SE) tasks, e.g., program synthesis, code completion, and code search. However, it remains to be seen what is behind their success. Recent studies have examined how pre-trained models can effectively learn syntax information based on Abstract Syntax Trees. In this paper, we figure out what role the self-attention mechanism plays in understanding code syntax and semantics based on AST and static analysis. We focus on a well-known representative code model, CodeBERT, and study how it can learn code syntax and semantics by the self-attention mechanism and Masked Language Modelling (MLM) at the token level. We propose a group of probing tasks to analyze CodeBERT. Based on AST and static analysis, we establish the relationships among the code tokens. First, Our results show that CodeBERT can acquire syntax and semantics knowledge through self-attention and MLM. Second, we demonstrate that the self-attention mechanism pays more attention to dependence-relationship tokens than to other tokens. Different attention heads play different roles in learning code semantics; we show that some of them are weak at encoding code semantics. Different layers have different competencies to represent different code properties. Deep CodeBERT layers can encode the semantic information that requires some complex inference in the code context. More importantly, we show that our analysis is helpful and leverage our conclusions to improve CodeBERT. We show an alternative approach for pre-training models, which makes fully use of the current pre-training strategy, i.e, MLM, to learn code syntax and semantics, instead of combining features from different code data formats, e.g., data-flow, running-time states, and program outputs.

The Metaverse can be considered the extension of the present-day web, which integrates the physical and virtual worlds, delivering hyper-realistic user experiences. The inception of the Metaverse brings forth many ecosystem services such as content creation, social entertainment, in-world value transfer, intelligent traffic, healthcare. These services are compute-intensive and require computation offloading onto a Metaverse edge computing server (MECS). Existing Metaverse edge computing approaches do not efficiently and effectively handle resource allocation to ensure a fluid, seamless and hyper-realistic Metaverse experience required for Metaverse ecosystem services. Therefore, we introduce a new Metaverse-compatible, Unified, User and Task (UUT) centered artificial intelligence (AI)- based mobile edge computing (MEC) paradigm, which serves as a concept upon which future AI control algorithms could be built to develop a more user and task-focused MEC.

Recent deep learning methods have achieved promising results in image shadow removal. However, their restored images still suffer from unsatisfactory boundary artifacts, due to the lack of degradation prior embedding and the deficiency in modeling capacity. Our work addresses these issues by proposing a unified diffusion framework that integrates both the image and degradation priors for highly effective shadow removal. In detail, we first propose a shadow degradation model, which inspires us to build a novel unrolling diffusion model, dubbed ShandowDiffusion. It remarkably improves the model's capacity in shadow removal via progressively refining the desired output with both degradation prior and diffusive generative prior, which by nature can serve as a new strong baseline for image restoration. Furthermore, ShadowDiffusion progressively refines the estimated shadow mask as an auxiliary task of the diffusion generator, which leads to more accurate and robust shadow-free image generation. We conduct extensive experiments on three popular public datasets, including ISTD, ISTD+, and SRD, to validate our method's effectiveness. Compared to the state-of-the-art methods, our model achieves a significant improvement in terms of PSNR, increasing from 31.69dB to 34.73dB over SRD dataset.