Abstract:Understanding emotions from diverse contexts has received widespread attention in computer vision communities. The core philosophy of Context-Aware Emotion Recognition (CAER) is to provide valuable semantic cues for recognizing the emotions of target persons by leveraging rich contextual information. Current approaches invariably focus on designing sophisticated structures to extract perceptually critical representations from contexts. Nevertheless, a long-neglected dilemma is that a severe context bias in existing datasets results in an unbalanced distribution of emotional states among different contexts, causing biased visual representation learning. From a causal demystification perspective, the harmful bias is identified as a confounder that misleads existing models to learn spurious correlations based on likelihood estimation, limiting the models' performance. To address the issue, we embrace causal inference to disentangle the models from the impact of such bias, and formulate the causalities among variables in the CAER task via a customized causal graph. Subsequently, we present a Contextual Causal Intervention Module (CCIM) to de-confound the confounder, which is built upon backdoor adjustment theory to facilitate seeking approximate causal effects during model training. As a plug-and-play component, CCIM can easily integrate with existing approaches and bring significant improvements. Systematic experiments on three datasets demonstrate the effectiveness of our CCIM.
Abstract:Understanding human intentions (e.g., emotions) from videos has received considerable attention recently. Video streams generally constitute a blend of temporal data stemming from distinct modalities, including natural language, facial expressions, and auditory clues. Despite the impressive advancements of previous works via attention-based paradigms, the inherent temporal asynchrony and modality heterogeneity challenges remain in multimodal sequence fusion, causing adverse performance bottlenecks. To tackle these issues, we propose a Multimodal fusion approach for learning modality-Exclusive and modality-Agnostic representations (MEA) to refine multimodal features and leverage the complementarity across distinct modalities. On the one hand, MEA introduces a predictive self-attention module to capture reliable context dynamics within modalities and reinforce unique features over the modality-exclusive spaces. On the other hand, a hierarchical cross-modal attention module is designed to explore valuable element correlations among modalities over the modality-agnostic space. Meanwhile, a double-discriminator strategy is presented to ensure the production of distinct representations in an adversarial manner. Eventually, we propose a decoupled graph fusion mechanism to enhance knowledge exchange across heterogeneous modalities and learn robust multimodal representations for downstream tasks. Numerous experiments are implemented on three multimodal datasets with asynchronous sequences. Systematic analyses show the necessity of our approach.
Abstract:With the rising demand for high-rate and timely communications, fog radio access networks (F-RANs) offer a promising solution. This work investigates age of information (AoI) performance in F-RANs, consisting of multiple content users (CUs), enhanced remote radio heads (eRRHs), and content providers (CPs). Time-critical CUs need rapid content updates from CPs but cannot communicate directly with them; instead, eRRHs act as intermediaries. CUs decide whether to request content from a CP and which eRRH to send the request to, while eRRHs decide whether to command CPs to update content or use cached content. We study two general classes of policies: (i) oblivious policies, where decision-making is independent of historical information, and (ii) non-oblivious policies, where decisions are influenced by historical information. First, we obtain closed-form expressions for the average AoI of eRRHs under both policy types. Due to the complexity of calculating closed-form expressions for CUs, we then derive general upper bounds for their average AoI. Next, we identify optimal policies for both types. Under both optimal policies, each CU requests content from each CP at an equal rate, consolidating all requests to a single eRRH when demand is low or resources are limited, and distributing requests evenly among eRRHs when demand is high and resources are ample. eRRHs command content from each CP at an equal rate under an optimal oblivious policy, while prioritize the CP with the highest age under an optimal non-oblivious policy. Our numerical results validate these theoretical findings.
Abstract:In order to transmit data and transfer energy to the low-power Internet of Things (IoT) devices, integrated data and energy networking (IDEN) system may be harnessed. In this context, we propose a bitwise end-to-end design for polar coded IDEN systems, where the conventional encoding/decoding, modulation/demodulation, and energy harvesting (EH) modules are replaced by the neural networks (NNs). In this way, the entire system can be treated as an AutoEncoder (AE) and trained in an end-to-end manner. Hence achieving global optimization. Additionally, we improve the common NN-based belief propagation (BP) decoder by adding an extra hypernetwork, which generates the corresponding NN weights for the main network under different number of iterations, thus the adaptability of the receiver architecture can be further enhanced. Our numerical results demonstrate that our BP-based end-to-end design is superior to conventional BP-based counterparts in terms of both the BER and power transfer, but it is inferior to the successive cancellation list (SCL)-based conventional IDEN system, which may be due to the inherent performance gap between the BP and SCL decoders.
Abstract:The task of steel surface defect recognition is an industrial problem with great industry values. The data insufficiency is the major challenge in training a robust defect recognition network. Existing methods have investigated to enlarge the dataset by generating samples with generative models. However, their generation quality is still limited by the insufficiency of defect image samples. To this end, we propose Stable Surface Defect Generation (StableSDG), which transfers the vast generation distribution embedded in Stable Diffusion model for steel surface defect image generation. To tackle with the distinctive distribution gap between steel surface images and generated images of the diffusion model, we propose two processes. First, we align the distribution by adapting parameters of the diffusion model, adopted both in the token embedding space and network parameter space. Besides, in the generation process, we propose image-oriented generation rather than from pure Gaussian noises. We conduct extensive experiments on steel surface defect dataset, demonstrating state-of-the-art performance on generating high-quality samples and training recognition models, and both designed processes are significant for the performance.
Abstract:Multimodal sentiment analysis (MSA) aims to understand human sentiment through multimodal data. Most MSA efforts are based on the assumption of modality completeness. However, in real-world applications, some practical factors cause uncertain modality missingness, which drastically degrades the model's performance. To this end, we propose a Correlation-decoupled Knowledge Distillation (CorrKD) framework for the MSA task under uncertain missing modalities. Specifically, we present a sample-level contrastive distillation mechanism that transfers comprehensive knowledge containing cross-sample correlations to reconstruct missing semantics. Moreover, a category-guided prototype distillation mechanism is introduced to capture cross-category correlations using category prototypes to align feature distributions and generate favorable joint representations. Eventually, we design a response-disentangled consistency distillation strategy to optimize the sentiment decision boundaries of the student network through response disentanglement and mutual information maximization. Comprehensive experiments on three datasets indicate that our framework can achieve favorable improvements compared with several baselines.
Abstract:Large Language Models (LLMs) have revolutionized natural language processing tasks. However, their deployment in wireless networks still face challenges, i.e., a lack of privacy and security protection mechanisms. Federated Learning (FL) has emerged as a promising approach to address these challenges. Yet, it suffers from issues including inefficient handling with big and heterogeneous data, resource-intensive training, and high communication overhead. To tackle these issues, we first compare different learning stages and their features of LLMs in wireless networks. Next, we introduce two personalized wireless federated fine-tuning methods with low communication overhead, i.e., (1) Personalized Federated Instruction Tuning (PFIT), which employs reinforcement learning to fine-tune local LLMs with diverse reward models to achieve personalization; (2) Personalized Federated Task Tuning (PFTT), which can leverage global adapters and local Low-Rank Adaptations (LoRA) to collaboratively fine-tune local LLMs, where the local LoRAs can be applied to achieve personalization without aggregation. Finally, we perform simulations to demonstrate the effectiveness of the proposed two methods and comprehensively discuss open issues.
Abstract:In recent years, reports of illegal drones threatening public safety have increased. For the invasion of fully autonomous drones, traditional methods such as radio frequency interference and GPS shielding may fail. This paper proposes a scheme that uses an autonomous multicopter with a strapdown camera to intercept a maneuvering intruder UAV. The interceptor multicopter can autonomously detect and intercept intruders moving at high speed in the air. The strapdown camera avoids the complex mechanical structure of the electro-optical pod, making the interceptor multicopter compact. However, the coupling of the camera and multicopter motion makes interception tasks difficult. To solve this problem, an Image-Based Visual Servoing (IBVS) controller is proposed to make the interception fast and accurate. Then, in response to the time delay of sensor imaging and image processing relative to attitude changes in high-speed scenarios, a Delayed Kalman Filter (DKF) observer is generalized to predict the current image position and increase the update frequency. Finally, Hardware-in-the-Loop (HITL) simulations and outdoor flight experiments verify that this method has a high interception accuracy and success rate. In the flight experiments, a high-speed interception is achieved with a terminal speed of 20 m/s.
Abstract:Semantic Communication (SC) is a novel paradigm for data transmission in 6G. However, there are several challenges posed when performing SC in 3D scenarios: 1) 3D semantic extraction; 2) Latent semantic redundancy; and 3) Uncertain channel estimation. To address these issues, we propose a Generative AI Model assisted 3D SC (GAM-3DSC) system. Firstly, we introduce a 3D Semantic Extractor (3DSE), which employs generative AI models, including Segment Anything Model (SAM) and Neural Radiance Field (NeRF), to extract key semantics from a 3D scenario based on user requirements. The extracted 3D semantics are represented as multi-perspective images of the goal-oriented 3D object. Then, we present an Adaptive Semantic Compression Model (ASCM) for encoding these multi-perspective images, in which we use a semantic encoder with two output heads to perform semantic encoding and mask redundant semantics in the latent semantic space, respectively. Next, we design a conditional Generative adversarial network and Diffusion model aided-Channel Estimation (GDCE) to estimate and refine the Channel State Information (CSI) of physical channels. Finally, simulation results demonstrate the advantages of the proposed GAM-3DSC system in effectively transmitting the goal-oriented 3D scenario.
Abstract:Context-aware emotion recognition (CAER) has recently boosted the practical applications of affective computing techniques in unconstrained environments. Mainstream CAER methods invariably extract ensemble representations from diverse contexts and subject-centred characteristics to perceive the target person's emotional state. Despite advancements, the biggest challenge remains due to context bias interference. The harmful bias forces the models to rely on spurious correlations between background contexts and emotion labels in likelihood estimation, causing severe performance bottlenecks and confounding valuable context priors. In this paper, we propose a counterfactual emotion inference (CLEF) framework to address the above issue. Specifically, we first formulate a generalized causal graph to decouple the causal relationships among the variables in CAER. Following the causal graph, CLEF introduces a non-invasive context branch to capture the adverse direct effect caused by the context bias. During the inference, we eliminate the direct context effect from the total causal effect by comparing factual and counterfactual outcomes, resulting in bias mitigation and robust prediction. As a model-agnostic framework, CLEF can be readily integrated into existing methods, bringing consistent performance gains.