Deep learning (DL)-based physical-layer authentication (PLA) has shown promising performance in Industrial Internet of Things (IIoT) scenarios. Existing methods formulate PLA as a single multi-classification task with a static training dataset and implicitly assume the training and authentication data are drawn from the same distribution. However, user mobility over time in mobile IIoT leads to temporal distribution shift in Channel Impulse Response (CIR), severely degrading authentication performance. To address this challenge, we propose TMML-PLA, a Temporal Meta-Metric Learning method that reformulates multi-user PLA as a sequence of temporal few-shot classification tasks based on the intrinsic temporal correlation characteristic of CIR. When new CIR samples require authentication, the model dynamically constructs a task using a small set of the most recent CIR samples of each user as the support set to ensure distributional consistency. A temporal meta-metric learning scheme based on the Prototypical Network is introduced to tackle these tasks under evolving CIR distributions, and a temporal decay mechanism is designed to emphasize recent training samples. Experiments on a real-world IIoT dataset demonstrate that TMML-PLA significantly improves both accuracy and robustness. For instance, when the number of users is 15 and the authenticating CIR samples increase over time, TMML-PLA maintains stable accuracy from 88.20% to 85.75% while the DL-based ResNet drops sharply from 83.93% to 46.95%, confirming its robustness and accuracy in mobile IIoT scenarios.

To make the video more attractive, original video materials usually need postprocessing by video editors, especially to eliminate low-quality abnormal clips, which seriously affect the visual effect. One of the main reasons for the low-quality abnormal clips is that there are occluders that accidentally break into the shot to occlude the protagonist, resulting in the loss of the video protagonist’s information. However, it is time-consuming and laborious to manually find shot occlusion clips, so computer vision technology can be used to assist editors in completing this work. The previous solutions directly utilize neural networks to detect shot occlusion, so their performance is affected by the size and quality of the dataset. In contrast, inspired by the change of depth information in the frame caused by the occluder breaking into the shot, we propose an algorithm for video shot occlusion detection based on the fluctuation of depth information. This algorithm does not need occlusion data training and can detect shot occlusion well only by capturing the abnormal fluctuations of the frame depth information. Additionally, to overcome the defect in that the first video shot occlusion detection (VSOD) dataset released in our conference publication can only verify the sensitivity of detection methods, we expand the VSOD dataset to evaluate the comprehensive performance of detection algorithms. The plentiful experimental results show that, compared with state-of-the-art occlusion detection methods and self-designed baseline methods, our algorithm significantly improves the comprehensive performance of video shot occlusion detection. Furthermore, through verification on datasets with different data types and distributions, our shot occlusion detection algorithm can maintain an occlusion event recall of over 95%, while the false positive rate does not exceed 3%, demonstrating good generalization ability. To promote reproducible research, the code and dataset are available athttps://github.com/Junhua-Liao/VSOD.

Active speaker detection is a challenging task in audiovisual scenarios, with the aim to detect who is speaking in one or more speaker scenarios. This task has received considerable attention because it is crucial in many applications. Existing studies have attempted to improve the performance by inputting multiple candidate information and designing complex models. Although these methods have achieved excellent performance, their high memory and computational power consumption render their application to resource-limited scenarios difficult. Therefore, in this study, a lightweight active speaker detection architecture is constructed by reducing the number of input candidates, splitting 2D and 3D convolutions for audio-visual feature extraction, and applying gated recurrent units with low computational complexity for cross-modal modeling. Experimental results on the AVA-ActiveSpeaker dataset reveal that the proposed framework achieves competitive mAP performance (94.1% vs. 94.2%), while the resource costs are significantly lower than the state-of-the-art method, particularly in model parameters (1.0M vs. 22.5M, approximately 23×) and FLOPs (0.6G vs. 2.6G, approximately 4×). Additionally, the proposed framework also performs well on the Columbia dataset, thus demonstrating good robustness. The code and model weights are available at https://github.com/Junhua-Liao/Light-ASD.

In this article, the data-driven optimal formation control problem is addressed for a heterogeneous quadrotor team with a virtual leader. Each quadrotor is considered as a highly nonlinear system with six degrees of freedom and the accurate dynamic information of the quadrotor is difficult to obtain in practical applications. An optimal cascade formation controller, including a position controller and an attitude controller, is proposed to track a virtual leader and form a predesigned formation. By using the reinforcement learning (RL) approach, the optimal formation controller is learned from the quadrotor system data without any knowledge of dynamic information of the quadrotors. Simulation results of a heterogeneous multiquadrotor system in a formation flight are given to show the effectiveness of the proposed controllers.

In this paper, a model-free optimal synchronization controller is designed to achieve the aggressive attitude synchronization for multiple heterogeneous quadrotor systems with highly nonlinear and coupled dynamics by using a reinforcement learning (RL) approach. A distributed observer is first designed for each following quadrotor to estimate the states of a virtual leader. A performance function is then utilized for each quadrotor to penalize the observed synchronization error and the control effort. An RL approach is finally employed to learn the optimal control law without any knowledge of the dynamic model information of the followers. The control law depends on the quadrotor states and the observer states, and guarantees that the attitude synchronization error converges to zero for all quadrotors, under aggressive maneuvers. Simulation results are provided to verify the effectiveness of the proposed controller.

In this article, the model-free robust formation control problem is addressed for cooperative underactuated quadrotors involving unknown nonlinear dynamics and disturbances. Based on the hierarchical control scheme and the reinforcement learning theory, a robust controller is proposed without knowledge of each quadrotor dynamics, consisting of a distributed observer to estimate the position state of the leader, a position controller to achieve the desired formation, and an attitude controller to control the rotational motion. Simulation results on the multiquadrotor system confirm the effectiveness of the proposed model-free robust formation control method.