Text-based person search (TBPS) aims to retrieve specific images of individuals from large datasets using textual descriptions. Existing TBPS methods focus primarily on identifying explicit positive attributes, often neglecting the critical role of negative descriptions. This oversight can lead to false positives, where images that should be excluded based on negative descriptions are incorrectly included, due to partial alignment with the positive criteria. To address this limitation, we propose the Dual Attribute Prompt Learning (DAPL) framework, which incorporates both positive and negative descriptions to improve the interpretative accuracy of vision-language models in TBPS tasks. DAPL combines Dual Image-Attribute Contrastive (DIAC) learning with Sensitive Image-Attribute Matching (SIAM) learning to enhance the detection of previously unseen attributes. Furthermore, to achieve a balance between coarse and fine-grained alignment of visual and textual embeddings, we introduce the Dynamic Token-wise Similarity (DTS) loss. This loss function refines the representation of both matching and non-matching descriptions at the token level, providing more precise and adaptable similarity assessments, and ultimately improving the accuracy of the matching process. Empirical results demonstrate that DAPL outperforms state-of-the-art methods, enhancing both precision and robustness in TBPS tasks.

Vehicular ad hoc network (VANET) has become an accessible technology for improving road safety and driving experience, the problems of heterogeneity and lack of resources it faces have also attracted widespread attention. With the development of software-defined networking (SDN) and multiaccess edge computing (MEC), a variety of resource allocation strategies in MEC-enabled software-defined networking-based VANET (SDVN) have been proposed to solve these problems. However, we note that few of these work involves the situation where SDVN is under Distributed Denial of Service (DDoS) attacks. Actually, Internet of Things (IoT) devices are extremely easy to be compromised by malicious users, and compromised IoT devices may be used to launch edge DDoS attacks against the MEC servers in MEC-enabled SDVN at any time. In this article, we propose a graph neural network (GNN)-based collaborative deep reinforcement learning (GCDRL) model to generate the resource provisioning and mitigating strategy. The model evaluates the trust value of the vehicles, formulates mitigation of edge DDoS attacks and resource provisioning strategies to ensure that the MEC servers can work normally under edge DDoS attacks. In addition, GNN is adopted in the DRL model to extract the structure feature of the graph composed of MEC servers, and help transfer computing tasks between MEC servers to alleviate the problem of resources imbalance between them. Experimental results show that the method of estimating the vehicular trust value is effective, and our method can make the average throughput of edge nodes more stable and lower down the average delay and the average energy consumption under the edge DDoS attack. Also, a real-world case study is conducted to verify our conclusion.

With the development of data plane programmable Software-Defined Networking (SDN), Distributed Denial of Service (DDoS) attacks on the data plane increasingly become fatal. Currently, traditional attack detection methods are mainly used to detect whether a DDoS attack occurs and it is difficult to find the path that the attack flow traverses the network, which makes it difficult to accurately mitigate DDoS attacks. In this article, we propose a detection method based on Spatial-Temporal Graph Convolutional Network (ST-GCN) over the data plane programmable SDN, which maps the network into a graph. It senses the state of switches through In-band Network Telemetry (INT) with sampling, inputs the network state into the spatial-temporal graph convolutional network detection model, and finally finds out the switches through which DDoS attack flows pass. Based on this, we propose a defense method combined with an enhanced whitelist and a precise dropping strategy, which can effectively mitigate DDoS attacks and minimize the impact on legitimate network traffic. The evaluation results show that our detection method can accurately detect the path that the DDoS attack flows pass through, and can effectively mitigate the DDoS attack. Compared to classic methods, our method improves the detection accuracy by nearly 10%. At the same time, the southbound interface load and CPU overhead brought by our detection and defense process are much lower than the classic methods.

Microwave remote sensing is an important substitute for rice growth monitoring in cloudy area. Fields identification is the most basic task for tracking rice crop cultivation. A series of sophisticated classification methods such as machine learning techniques have been applied to mapping crop planting area. However, these methods are weak in interpreting the physical mechanism of identifying crop fields, and hardly illustrate the backscattering difference between rice fields and other ground objects. Besides, enormous training samples and computational expense are demanded to achieve high recognition accuracy, which limited their application to rapid and large-area agricultural monitoring. In this study, C-band quad-pol backscattering coefficients of different land cover types were extracted from RADARSAT-2 PolSAR (Polarimetric Synthetic Aperture Radar) data during the reproductive period of rice fields. The backscatter statistical characteristics of rice fields and other ground types in different polarimetric bands were visualized and analyzed using boxplots. Based on the scatter performance of the five interested ground objects, a simple decision tree scheme was proposed to identify rice paddy fields. The overall accuracy is 88.65% and Kappa coefficient is 0.77. Meanwhile, a land cover classification map of the study area was obtained though the hierarchical judgement of decision tree strategy.

Recent satellite missions have provided a variety of high spatial resolution, multi-spectral, and high-frequency revisit remote sensing datasets. The collaborative use of optical and synthetic aperture radar (SAR) imagery in remote sensing applications attracts considerable attention. The purpose of this paper is to investigate the contribution of both data to the rice planting area mapping. In particular, the red-edge band was introduced to construct a red-edge vegetation index based on Sentinel-2 data. C-band quad-pol Radarsat-2 data was also used. We finally used the random forest algorithm, collaborating with optical and radar data to map rice planting area. We found that the red-edge band and red-edge vegetation index can improve the classification accuracy compared to the classifier using NIR (near-infrared) band and NDVI (Normalized Difference Vegetation Index). The result shows that the jointly use of optical and radar data is feasible to map rice planting area. The overall accuracy, recall and F-measure are 0.9441, 0.9598 and 0.9680, respectively. Index Terms - red edge, SAR, rice mapping, random forest, Sentinel-2, Radarsat-2

Accurate mapping of paddy rice planting area is important for rice yield prediction. Polarimetric synthetic aperture radar (PolSAR) data is suitable for rice growth monitoring in cloudy and foggy weather. The potential of using quad-pol PolSAR parameters for rice area mapping needs exploration in detail. In this study, multi-temporal C-band quad-pol RADARSAT-2 datasets and random forest classification algorithm were used to identify the rice planting area in Meishan City, China in 2016. The backscatter coefficients, polarimetric variables and decomposition parameters were extracted and divided into groups as the inputs of random forest classifier. The decomposition parameters derived from single-day PolSAR data during the rice reproductive period were found the most practicable for rice area mapping, with the overall accuracy of 95.94% and kappa coefficient of 0.92.