Serverless edge computing seamlessly integrates edge computing with serverless computing, not only overcoming the limitations of resource-constrained edge nodes but also alleviating the high latency associated with cloud response. Due to the elastic scalability of serverless computing platforms, the cold start of latency-sensitive serverless functions (SFs) has become a significant challenge. Traditional strategies, such as resource reservation and prewarming, often suffer from low resource utilization. Meanwhile, offloading-based approaches simplify the problem by assuming a fixed high cold start delay cost, which is unsuitable for heterogeneous serverless edge computing scenarios. This paper proposes a Cold-Start aware offloading by double-dueling-DQN (CSODQN) model for SFs in a cloud-edge-device serverless computing system. The model creates an instance warming pool for SFs to enable reuse and allocates edge service node resources based on the priority of user and SFs, achieving multi-objective offloading optimization that considers cold starts. Our goal is to balance the frequency of cold start and resource utilization. To address the partially observable offloading optimization problem among agents, we employ a multi-agent deep reinforcement learning approach. By introducing an priority of action based sampling strategy, we accelerate the convergence of learning for each agent. Simulation results demonstrate that our method improves task success rates, reduces average task latency and cold start occurrences, and enhances resource utilization. Our approach alleviates the frequency of cold starts without excessively consuming system resources and costs, achieving long-term optimization of service quality, device energy consumption, and expenses.

Nonrigid deformation (NRD) and image noise in multimodal remote sensing images (MRSI) lead to abrupt changes in feature directions, resulting in sensitivity to rotational variation, sparse correct matches, and high false match rates. In order to address these challenges, this article proposes a second-order tensor orientation feature transformation (SOFT) method to improve the rotational invariance of MRSI matching and increase the number of correct matches (NCMs). The SOFT method has two main contributions: 1) a novel second-order tensor orientation descriptor is constructed by generating a tensor orientation feature map using a designed second-order tensor function, which is then combined with a gradient location and orientation histogram (GLOH)-like descriptor framework to achieve robust rotational invariance in multimodal image matching and 2) an error-removal global-local iterative optimization (EGIO) is introduced, employing a skewness of mixed pixel intensity (SMPI) function to automatically select matching seed points, followed by an iterative partition optimization strategy for refining corresponding points. Experiments on 744 groups of typical MRSIs demonstrate that the SOFT method significantly outperforms nine state-of-the-art methods, achieving an average 97% improvement in the NCMs, an average 25.51% improvement in the rate of correct matches (RCMs), and an average reduction in RMSE of 2.69 pixels. The proposed SOFT method, thus, offers robust MRSI matching with strong rotational invariance and precise identification of corresponding points, proving its effectiveness for complex remote sensing scenarios. Access to experiment-related data and codes will be provided athttps://skyearth.org/research/.

Video Anomaly detection, aiming to detect the abnormal behaviors in surveillance videos, is a challenging task since the anomalous events are diversified and complicated in different situations. And this makes it difficult to use one single static network architecture to extract useful information from diverse abnormal patterns. Therefore, in this article, we propose a novel Dynamic Self-Supervised Network (DSS-Net) to explore both spatial and temporal anomalous information. In our DSS-Net, we design a dynamic network to adaptively select suitable network architecture to extract latent features from different anomalous patterns and normal patterns. Specifically, we generate spatial and temporalpseudo-abnormaldata as the input of the dynamic network to conduct self-supervised learning. And we have a specific design on Hybrid Anomaly Dynamic Convolution (HAD-Conv) to extract features for diversified anomalous events adaptively. We utilize both normal and pseudo-abnormal data to encourage the dynamic network to mine the discriminative information. Furthermore, we design a feature separation loss to maximize the difference between the anomalous and normal videos. We evaluate our proposed method on four public anomaly detection datasets and achieve competitive results compared with the state-of-the-art approaches.

ASR model deployment environment is ever-changing, and the incoming speech can be switched across different domains during a session. This brings a challenge for effective domain adaptation when only target domain text data is available, and our objective is to obtain obviously improved performance on the target domain while the performance on the general domain is less undermined. In this paper, we propose an adaptive LM fusion approach called internal language model estimation based adaptive domain adaptation (ILME-ADA). To realize such an ILME-ADA, an interpolated log-likelihood score is calculated based on the maximum of the scores from the internal LM and the external LM (ELM) respectively. We demonstrate the efficacy of the proposed ILME-ADA method with both RNN-T and LAS modeling frameworks employing neural network and n-gram LMs as ELMs respectively on two domain specific (target) test sets. The proposed method can achieve significantly better performance on the target test sets while it gets minimal performance degradation on the general test set, compared with both shallow and ILME-based LM fusion methods.