Dynamic facial expression recognition (DFER) infers emotions from the temporal evolution of expressions, unlike static facial expression recognition (SFER), which relies solely on a single snapshot. This temporal analysis provides richer information and promises greater recognition capability. However, current DFER methods often exhibit unsatisfied performance largely due to fewer training samples compared to SFER. Given the inherent correlation between static and dynamic expressions, we hypothesize that leveraging the abundant SFER data can enhance DFER. To this end, we propose Static-for-Dynamic (S4D), a unified dual-modal learning framework that integrates SFER data as a complementary resource for DFER. Specifically, S4D employs dual-modal self-supervised pre-training on facial images and videos using a shared Vision Transformer (ViT) encoder-decoder architecture, yielding improved spatiotemporal representations. The pre-trained encoder is then fine-tuned on static and dynamic expression datasets in a multi-task learning setup to facilitate emotional information interaction. Unfortunately, vanilla multi-task learning in our study results in negative transfer. To address this, we propose an innovative Mixture of Adapter Experts (MoAE) module that facilitates task-specific knowledge acquisition while effectively extracting shared knowledge from both static and dynamic expression data. Extensive experiments demonstrate that S4D achieves a deeper understanding of DFER, setting new state-of-the-art performance on FERV39K, MAFW, and DFEW benchmarks, with weighted average recall (WAR) of 53.65%, 58.44%, and 76.68%, respectively. Additionally, a systematic correlation analysis between SFER and DFER tasks is presented, which further elucidates the potential benefits of leveraging SFER.

Movable antenna (MA)-enabled multiple-input multiple-output (MIMO) systems offer a promising enhancement for integrated sensing and communication (ISAC) applications. Unlike conventional MIMO systems with fixed-position antenna (FPA) arrays, MAs can flexibly adjust their positions within a given region, enabling reconfiguration of both communication and sensing channels with additional spatial degrees of freedom. In this paper, we propose a unified mutual information (MI) framework for MA-enabled MIMO ISAC systems, where MI characterizes communication performance as reliably conveyable information and sensing performance as extractable target information in cluttered environments. We formulate an optimization problem to maximize the weighted sum of communication and sensing MI by jointly optimizing the transmit beamforming matrix under a transmit power constraint and the MA positions under practical constraints, with a weighting coefficient characterizing their trade-off. To tackle the non-convexity arising from the log-det objective, position constraints, and the nonlinear coupling between optimization variables, we develop an alternating optimization-based algorithm that iteratively updates the transmit beamforming matrix and the MA positions. Specifically, with the fixed MA positions, we optimize the beamforming by approximating the objective function using weighted mean square error and majorization-minimization methods, yielding a closed-form solution. Moreover, with fixed beamforming, the MA positions are sequentially refined by decomposing the position optimization into simpler subproblems, resulting in an efficient suboptimal solution. Numerical results show that the unified MI framework with MAs significantly outperforms conventional FPA systems in both communication and sensing. Channel amplitude heatmap visualizations further illustrate how MA positioning strategies exploit spatial flexibility in array geometry to enhance overall system performance.

Re-establishing emergency communication and ensuring rapid response are critical for rescue operations in natural disaster scenarios, such as earthquakes, floods, and wildfires. Unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) networks have emerged as a promising solution to re-establish communication links and provide flexible computational support in these complex environments. However, the existing UAV-assisted MEC research has not fully investigated the joint optimization of task offloading and resource allocation (JTORA) problem, considering both terrain obstacles and high-interference zones. In this paper, we investigate the JTORA problem to minimize the energy consumption for communication and computation in a rate-splitting multiple access (RSMA)-based UAV-assisted mobile edge computing (MEC) network. RSMA is utilized to enhance interference management and improve spectral efficiency. We propose a proximal policy optimization (PPO)-based method to optimize the task offloading ratio, message splitting ratio, and RSMA precoding matrix for the proposed JTORA problem. Simulation results show that the proposed approach effectively enhances system efficiency and sustainability.

Natural disasters often destroy critical infrastructure, such as terrestrial communication networks and transportation routes, thereby severely disrupting post-disaster rescue operations. To rapidly re-establish communication links and provide flexible computational support in disaster rescue scenarios, the integration of unmanned aerial vehicles (UAVs) and mobile edge computing (MEC) has emerged as a promising solution. Nevertheless, the highly complex and resource-constrained characteristics of disaster environments pose significant challenges for UAV-assisted computation task offloading. In this paper, we investigate the joint task offloading and resource allocation (JTORA) problem to minimize the energy consumption associated with communication and computation during task offloading. Specifically, we develop a twin-delayed deep deterministic policy gradient (TD3)-based JTORA (JTORA-TD3) algorithm, which enables the UAV to optimize decisions of task offloading and resource allocation intelligently. To further enhance the training efficiency of the JTORA-TD3 algorithm in a complex disaster rescue environment, we integrate a large AI model (LAM) into the TD3 framework. Based on the textual interaction, we propose an LAM-enabled TD3-based JTORA (JTORA-LAM4TD3) algorithm. Simulation results demonstrate that the proposed JTORA-LAM4TD3 algorithm significantly outperforms baselines. These findings confirm the effectiveness of integrating LAMs with deep reinforcement learning (DRL) for solving the decision optimization problem.

Engagement estimation plays a crucial role in understanding human social behaviors, attracting increasing research interests in fields such as affective computing and human-computer interaction. In this paper, we propose a Dialogue-Aware Transformer framework (DAT) with Modality-Group Fusion (MGF), which relies solely on audio-visual input and is language-independent, for estimating human engagement in conversations. Specifically, our method employs a modality-group fusion strategy that independently fuses audio and visual features within each modality for each person before inferring the entire audio-visual content. This strategy significantly enhances the model's performance and robustness. Additionally, to better estimate the target participant's engagement levels, the introduced Dialogue-Aware Transformer considers both the participant's behavior and cues from their conversational partners. Our method was rigorously tested in the Multi-Domain Engagement Estimation Challenge held by MultiMediate'24, demonstrating notable improvements in engagement-level regression precision over the baseline model. Notably, our approach achieves a CCC score of 0.76 on the NoXi Base test set and an average CCC of 0.64 across the NoXi Base, NoXi-Add, and MPIIGI test sets. The source code will be available at https://github.com/MSA-LMC/DAT.

Abstract Reactive jammers select jamming strategies according to the users’ responses; thus, conventional anti‐jamming methods such as frequency hopping are inadequate to defeat the jamming attack. In this article, the authors propose a novel uncoupled deception scheme to trap the reactive jammer into attacking a decoy channel in distributed networks. Specifically, the authors design a multi‐functional network utility for every user to mislead the jammer with a minimum energy consumption while achieving the highest network throughput. Based on the network utility, the anti‐jamming problem is formulated as an exact potential game such that the existence of Nash equilibrium can be guaranteed theoretically. The authors further propose a back‐to‐back coordination‐based learning algorithm to reach the optimal channel selection and power adaption in a non‐cooperative way. To alleviate the lack of mutual information exchange, the back‐to‐back coordination mechanism derives all users to deceive the jammer by inferring others’ strategies based on a shared belief. Simulation results show that the proposed algorithm yields higher network throughput and efficiency‐cost ratio compared to the state‐of‐the‐art cooperative schemes.

Abstract In this paper, the problem of mission planning and spectrum resource allocation for cooperative reconnaissance of ground targets with multiple unmanned aerial vehicles (UAVs) is studied. A joint mission planning and spectrum resource optimization algorithm for multi‐UAVs is proposed to improve the information transmission rate by reusing the spectrum of existing users. The joint optimization problem is formulated as mixed‐integer non‐linear programming. The block coordinate descent (BCD) method is further applied to achieve the optimal strategies of mission planning, channel allocation, and power control. Specifically, an improved genetic algorithm (GA) combined with the successive convex approximation (SCA) is used to solve the sub‐problem of mission planning. For the channel allocation sub‐problem, an iterative convergence channel allocation algorithm is proposed. Numerical results show that the proposed algorithm can achieve a higher UAV transmission rate and better robustness than existing algorithms.

Abstract In unmanned aerial vehicle (UAV)‐assisted wireless sensor networks (WSNs), UAVs are employed to collect sensing data from each sensor node (SN). Because of limited battery capacity, shortening the time of data collection by the UAV is necessary. Notably, the task completion time is related to UAV trajectory and spectrum allocation. In this paper, joint trajectory design and spectrum allocation is studied to minimize the task completion time of UAVs while ensuring the target upload data amount for each SN. The cases that all SNs are located within the communication range of a UAV is explored first; the formulated problem is non‐convex and difficult to solve directly. Hence, an iterative algorithm based on block coordinate descent and successive convex approximation is proposed to decompose and transformed the original problem into two convex optimizations. Furthermore, the proposed algorithm is applied to the general case that all SNs are widely distributed by leveraging the spiral algorithm and traveling salesman problem technique. Simulation results show that the proposed algorithm can effectively reduce the task time of UAV compared to other benchmark algorithms.

Abstract A proactive spectrum monitoring and spectrum monitoring data (SMD) transmission coexistence system is investigated in dynamic spectrum sharing network, where a spectrum monitor (SM) aims to monitor the spectrum information from the electromagnetic signal sent by the suspicious transmitter to the suspicious destination by using a portion of its antennas and transmit its SMD to the spectrum data fusion center by using the rest antennas. The SMD transmission of the SM can also be employed to jam the suspicious destination to realise the effective proactive spectrum monitoring. Thus, the precoding and antenna selection scheme are jointly designed at the SM to maximise the sum of the achievable spectrum monitoring rate and the SMD transmission rate. The scenario that the SM can assess the statistical channel state information of the suspicious links based on the spectrum information obtained from the spectrum database as the spectrum management node is then considered. The spectrum monitoring/SMD transmission success probability is also derived, and a trade‐off between them is further revealed. Simulation results show that the proposed schemes can obtain higher sum rate of the spectrum monitoring and the SMD transmission, which also verifies its effectiveness and above “security‐reliability” trade‐off.

In order to make device-to-device (D2D) content sharing give full play to its advantage of improving local area services, one of the important issues is to decide the channels that D2D pairs occupy. Most existing works study this issue in static environment, and ignore the guidance for D2D pairs to select the channel adaptively. In this paper, we investigate this issue in dynamic environment where D2D pairs’ activeness and wireless channel are dynamic. Specifically, we propose a pricing-based approach to guide D2D pairs to select different channels according to the spectrum resource states adaptively. Then, we formulate the pricing-based channel selection problem as an expected global price-to-performance ratio minimum problem. In order to solve it in a tractable manner, we make an approximately equivalent transformation to it. After that, we model the transformed problem as a stochastic game and prove it to be an exact potential game, which has at least one pure strategy Nash Equilibrium (NE) point. In order to reach the pure strategy NE points in dynamic environment, we design a channel selection learning algorithm based on stochastic learning automata, which only requires little information exchange. Simulation results show that our proposed algorithm outperforms other benchmark algorithms.

This letter studies the legitimate surveillance with one half-duplex legitimate monitor (E) over the suspicious multichannel relaying system, where the suspicious transmitter (ST) and relay (SR) implement the optimal power allocation over all orthogonal channels under a joint sum-power constraint to maximize the communication rate of the suspicious system. Under this setup and considering that SR operates in amplify-and-forward (AF) or decode-and-forward (DF) mode, E aims to i) determine the optimal set of sub-channels for jamming and ii) optimize its jamming power over these sub-channels in order to deliberately force ST and SR reallocating power to the unjammed sub-channels to the most, so as to increase the perceived power of E over the unjammed sub-channels and then maximize the eavesdropping rate. In particular, for the AF case, the formulated problem is non-convex, for which the slack variables are introduced and successive convex approximation is exploited. For the DF case, some insights are provided for the optimization process. Results present the considerable gain of the proposed strategy compared to intuitive schemes.

This paper presents a new ground-based visual approach for guidance and safe landing of an unmanned aerial vehicle (UAV) in Global Navigation Satellite System(GNSS)-denied environments. In our previous work, the old system consists of one pan-tilt unit(PTU) with two cameras, whose detection range is limited by the baseline. To achieve long-range detection and cover wide field of regard, we mounted two separate sets of PTU integrated with visible light camera on both sides of the runway instead of our previous assembled stereo vision system. Then, the well-known AdaBoost method was evaluated with regard to detecting and tracking the target. To achieve the relative position between the UAV and landing area, we used triangulation to calculate the 3D coordinates of the UAV. By combining the estimated position in the closed loop control, we obtain the autonomous landing strategy. Finally, we present several real flights in outdoor environments, and compare its accuracy with ground truth provided by GNSS. The results support the validity and accuracy of the presented system.