Jianxin Li

Extracting roads accurately from remote sensing images is important for map updates, traffic analysis, and infrastructure monitoring. Medium-resolution multispectral images can provide useful surface and background information, but when used alone, the spatial details are limited for retaining narrow roads, intersection structures, and fine road topologies. To address this problem, this paper proposes GeoRoad-UPerNet, a Geo-1-centered weakly supervised multispectral framework for road extraction. In this framework, Geo-1 serves as the primary 16-band multispectral source, Sentinel-2 Level-2A imagery serves as auxiliary contextual support, and OpenStreetMap (OSM) road information is converted into proxy supervision rather than dense manual ground truth. GeoRoad-UPerNet contains three modules: a Geo Spectral Semantic Stem (GSSS), a Geo-Auxiliary Gated Fusion module (GAGF), and a Road Semantic Multi-Task Head (RSMH). GSSS strengthens road-sensitive multispectral responses in the Geo-1 branch. GAGF injects Sentinel-2 context through a Geo-centered gate instead of symmetric channel concatenation. RSMH imposes restrained hierarchy- and material-aware semantic regularization on the shared decoder representation during training. On the fixed source-domain benchmark, the complete model achieves an IoU of 0.7204, an F1-score of 0.8375, a Precision of 0.8092, and a Recall of 0.8678 against OSM-derived proxy masks. Relative to the UPerNet-MiT-B3 early-fusion baseline, IoU, F1-score, and Precision increase by 6.29%, 3.65%, and 12.58%, respectively. These results indicate that role-aware multisource organization improves road extraction under proxy supervision and reduces boundary noise and background false positives.

Social network simulation enables controlled study of information dynamics and collective behavior on social graphs, yet the literature remains fragmented across disciplines. This survey provides a unified treatment of the field, organizing 97 papers from the past seven decades into five paradigms: network structure models, information diffusion, opinion dynamics, rule-based agentbased models, and large language model (LLM)-based agentic simulation. We bridge classical and generative approaches by mapping the progression from analytical update rules to language-grounded agents with semantic memory and platform-native actions, and present the first systematic architectural comparison of LLM-based simulation systems. We analyze the literature across five application domains—misinformation, political discourse, platform design, information diffusion, and user behavior—tracing a shift from descriptive analysis toward prescriptive policy prototyping. We outline seven research frontiers spanning representational alignment, multi-level validation, scalability, and responsible use. An accompanying online repository at https://github.com/tamlhp/awesome-sns catalogs 48 implementations (42 open-source), 21 benchmarks and datasets, and 22 evaluation metrics.

Recommender systems (RSs) are widely adopted due to their effectiveness in modeling user preferences and generating personalized recommendations. However, data poisoning attacks (PAs) manipulate recommendation results by injecting fake user profiles, thereby affecting the quality and accuracy of RSs. Moreover, emerging high-concealed PAs (HCPAs) achieve greater evasion of detection by controlling the cost of the attack, simulating the behavior patterns of benign users, and carrying out the attack with less prior knowledge. The HCPAs bring challenges: (1) the very low cost of attacks not only leads to an imbalance in data distribution but also introduces a large amount of accidental co-occurrence noise; (2) the behavioral patterns similar to benign users make it difficult to describe the characteristics of HCPAs; and (3) the prior knowledge for detecting HCPAs in real scenarios is very limited. To address these challenges, we propose STOP, an orthogonal projection bi-hypersphere detection method built on multi-view relational disentanglement and information-consistent fusion. First, we model the distributional preferences of user ratings to eliminate rating and popularity bias, and construct a co-occurrence association graph to suppress accidental overlaps. To address data imbalance caused by HCPAs, second, we introduce a distributional-consensus importance screening method that filters out benign users weakly associated with potential attackers. To address the issues of noise and the difficulty in feature characterization, third, we propose a multi-view relational disentanglement and information-consistent fusion method, which can eliminate redundant relationships, separate key relations into sequence-varying and sequence-stable components over rating sequences, and retain task-related relationships. Finally, inspired by the “convergence theorem”, we design an orthogonal projection bi-hypersphere boundary learning detection method to reduce the high false alarm rate (FAR). We extensively evaluate STOP under various HCPA scenarios, demonstrating its superiority over existing methods with an average 12.34% improvement in detection rate and an average 2.75% reduction in FAR. Furthermore, forensic analysis on real-world unlabeled data reveals distinct attacker “fingerprints”, such as extreme ratings, contradictory review styles, and analysis of target items, validating STOP's reliability in practical applications.