While Self-supervised Learning (SSL) has significantly improved Spoken Language Identification (LID), existing models often struggle to consistently classify dialects and accents of the same language as a unified class. To address this challenge, we propose geolocation-aware LID, a novel approach that incorporates language-level geolocation information into the SSL-based LID model. Specifically, we introduce geolocation prediction as an auxiliary task and inject the predicted vectors into intermediate representations as conditioning signals. This explicit conditioning encourages the model to learn more unified representations for dialectal and accented variations. Experiments across six multilingual datasets demonstrate that our approach improves robustness to intra-language variations and unseen domains, achieving new state-of-the-art accuracy on FLEURS (97.7%) and 9.7% relative improvement on ML-SUPERB 2.0 dialect set.

Camouflaged Object Detection (COD) aims to segment objects that seamlessly blend into the background. This paper proposes a Dual-domain Iterative Refinement Network (DIR-Net), which integrates both spatial and frequency domain information, balancing the pixel-level processing of spatial domain information and the noise robustness provided by the low-frequency smoothness in the frequency domain. DIR-Net consists of two stages: coarse localization and iterative refinement. The first stage uses a Frequency-Spatial Fusion (FSF) module for intra- and inter-frequency interactions, and a Dual-Domain Difference Convolution (DDC) to supplement spatial information. The second stage adopts an Iterative Masking Strategy (IMS) to supplement high-resolution information for fine-grained segmentation. Experimental results on four COD datasets demonstrate that DIR-Net achieves state-of-the-art performance.

Camouflaged Object Detection (COD) is a challenging task due to the inherent difficulty of distinguishing camouflaged objects from their highly similar backgrounds. Existing methods predominantly rely on structural cues but often suffer from misinterpretations and noise, especially when detecting small objects. To address these issues, we propose the Structure-Guided Network (SGNet), which progressively supplements structural information from points to regions. SGNet incorporates three key modules: the Key Point Local Enhancement (KLE) to enhance point-level detail, the Hybrid Resolution Adaptation (HRA) mechanism for integrating high-resolution features, and the Structure-Guided Patch (SGP) for selective high-resolution patch extraction based on object shape. Experimental results on three widely used COD datasets demonstrate that SGNet significantly outperforms state-of-the-art methods, achieving more accurate localization and finer edge segmentation, while minimizing background noise.

The application of automated guided vehicle (AGV) greatly improves the production efficiency of workshop. However, machine flexibility and limited logistics equipment increase the complexity of collaborative scheduling, and frequent dynamic events bring uncertainty. Therefore, this article proposes a real-time scheduling method for dynamic flexible job shop scheduling problem with AGVs using multiagent reinforcement learning (MARL). Specifically, a real-time scheduling framework is proposed in which a multiagent scheduling architecture is designed for achieving task selection, machine allocation and AGV allocation. Then, an action space and an efficient action decoding algorithm are proposed, which enable agents to explore in the high-quality solution space and improve the learning efficiency. In addition, a state space with generalization, a reward function considering machine idle time and a strategy for handling four disturbance events are designed to minimize the total tardiness cost. Comparison experiments show that the proposed method outperforms the priority dispatching rules, genetic programming and four popular reinforcement learning (RL)-based methods, with performance improvements mostly exceeding 10%. Furthermore, experiments considering four disturbance events demonstrate that the proposed method has strong robustness, and it can provide appropriate scheme for uncertain manufacturing system.

Speech is a natural user interface for the Internet of Things system. However, the presence of noise affects severely the performance of such system. With the deployment of smart devices with microphones, one can form a powerful acoustic sensor network to enhance the speech via beamforming techniques. On the other hand, reliability of data transmission also determines the beamforming performance, since faulty data will drift the beamformer steering location randomly. Currently, there is no protection scheme for acoustic data transmitted over the wireless network in order to keep steady beamforming performance. In this article, we design a compound distributed beamformer, where nodes are grouped and the system is embedded with blockchain technology to protect the data integrity during transmission. It attempts to provide more possible reliable connections between groups. Simulated experiments show that the distributed beamformer with blockchain protection is able to maintain steady beamforming performance.

There is growing demand for accuracy in image processing and visualization, and the super-resolution (SR) technique for multi-observed RGB-D images has become popular, because it provides space-redundant information and produces a detailed reconstruction even with a large magnification factor. This technique has been thoroughly investigated in recent years. Nevertheless, technical challenges remain, such as finding sub-pixel correspondences with low-resolution (LR) observations, exploiting space-redundant information, formulating space homogeneity constraints, and leveraging cross-image similarities in structures. To address these challenges, this paper proposes a unified optimization framework to estimate both the super-resolved RGB image and the super-resolved depth image from the multi-observed LR RGB-D images using their correlations. Using depth-assisted cross-image correspondences, the RGB image SR problem is formulated as an effective regularization function by incorporating the normalized bilateral total variation regularizer, and it is efficiently solved by a first-order primal-dual algorithm. The depth image SR estimate can be obtained by minimizing a nonlocal regression-based energy, which integrates the structural cues of the super-resolved RGB image in a detail-preserving fashion. Essentially, our unified optimization framework uses the RGB image and depth image as a priori knowledge that the SR process uses for better accuracy. Our extensive experiments on public RGB-D benchmarks and real data and our quantitative comparison with several state-of-the-art methods demonstrate the superiority of our method in terms of accuracy, versatility, and reliability of details and sharp feature preservation.