XWXiao Wang

Xiao Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xiao Wang has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Multimodal Prompt Learning for Spatial Reasoning in Remote Sensing Image Scene

    by Yan Ren, Haizhong Qian, Bingchuan Jiang, Tingting Li, Xiao Wang, Long Sun, Li Yang

    A remote sensing scene graph (RSSG) enables machines to interpret interactions among ground objects in remote sensing images and supports semantic reasoning and description, thus making it a fundamental technique in the field. However, most existing scene reasoning approaches cannot fully utilize multimodal information, resulting in limited performance when inferring spatial relationships among ground objects. To this end, we propose a Unified Visual-Semantic Triple Prompt Learning (UVSTPL) framework, which integrates visual features with matched geospatial object labels, leverages a prompt learning module for multimodal feature extraction, and employs a refined UVTransE model to predict spatial relationships. The core principle of UVSTPL is to enhance semantic feature extraction and improve relationship prediction performance via the collaborative fusion of visual and linguistic modalities. To strengthen the model’s ability to reason about the spatial relationships among ground objects in images, a novel Geo-RSSG dataset is constructed, which includes precise annotations of geographic entities, spatial relationships, and attributes. Extensive experiments demonstrate that the proposed UVSTPL method outperforms benchmark models on the spatial relationship prediction task. In comparison with the best baseline method, our approach improves prediction precision by 1.85%, mean precision by 8.49%, mean recall by 17.46%, and mean F1-score by 12.97%. This study offers valuable insights for advancing the understanding and cognitive capabilities of remote sensing scenes.

  • Open Access

    StreetViewGPT: A Street View Image Scene Perception and Reasoning Method Based on Multimodal Large Language Model

    by Zhuoheng Song, Bingchuan Jiang, Xiao Wang, Yong Sun, Ru Yu, Tingting Li

    Multimodal large language models (MLLMs) have demonstrated promising potential in addressing real-world vision-language tasks. However, existing MLLMs exhibit relatively limited capabilities in understanding street view images, struggling to achieve multi-level semantic understanding and spatial reasoning for region-level fine-grained inference in street view images, which to some extent limits their potential in geospatial artificial intelligence (GeoAI). This study constructs an instruction fine-tuning dataset to guide MLLMs in learning spatial knowledge and scene features from street-view images, called SVGPT-Instruct. This large-scale dataset for street view understanding encompasses 430K instruction samples and 110K street view images. Ultimately, we propose the StreetViewGPT, an MLLM-based method for street view image scene perception and reasoning. The StreetViewGPT is capable of uniformly handling various street view image tasks, including time estimation (TE), weather recognition (WR), scene classification (SC), spatial distance estimation (SDE), and scene graph generation (SGG). The experimental results show that in the TE, WR, and SC tasks, the accuracy of StreetViewGPT improved by 1.33%, 21.68%, and 18.83% respectively compared to the suboptimal model. In the SDE task, the accuracy of predictions falling within the three error tolerance intervals of [75%, 125%], [50%, 150%], and [25%, 175%] reached 88.3%, 97.7%, and 99.5%, respectively, which improved by 78.2%, 78.7%, and 58.6%. In the SGG task, Recall and Mean Recall reached 16.09% and 6.84%, respectively, which improved by 12.49% and 5.4% compared to Qwen2-VL. It demonstrates that StreetViewGPT possesses multi-level semantic understanding and spatial reasoning capabilities, ranging from global semantic perception at the image level to fine-grained reasoning at the region level. The proposed method enhances the recognition and cognition capabilities for spatial scenes in street view images, offering positive implications for smart city perception and autonomous driving navigation research.


  • LLM ‐ GeoTextCog : A Cognitive Enhancement Framework for Geospatial Scene Understanding in Geographic Texts Using Large Language Models

    by Xiao Wang, Bingchuan Jiang, Yan Ren, Daozhu Xu, Yong Sun, Ru Yu, Tingting Li

    Geographic texts (geo‐texts) play an indispensable role in preserving and transmitting geospatial knowledge. The spatial scene understanding capability of large language models (LLMs) in processing textual information is primarily demonstrated in two key steps: the accurate identification of geographical entities and spatial relationships, and the ability to perform relative position reasoning and spatial scene reconstruction. However, current LLMs are primarily limited to extracting surface‐level information and establishing shallow semantic connections from text, which restricts their capacity for deeper spatial cognition and reasoning. Inspired by the mechanisms underlying human mental map and spatial reasoning, this paper proposes a cognitive enhancement framework LLM‐GeoTextCog. It aims to achieve a transformation from descriptive text to a structured “spatial scene sketch”. The development of this framework involves two key methodological efforts: (1) The first effort focuses on enhancing LLMs' recognition capabilities for geographical entities and spatial relationships. To achieve this, two specialized datasets are constructed: GeoBase, a domain knowledge fine‐tuning dataset, and GeoRel, a scene cognition fine‐tuning dataset. Through a two‐stage LoRA fine‐tuning process, a dedicated geo‐texts cognition model, Qwen3‐8B‐GeoMine, is developed. (2) The second effort is focused on transforming spatial scene reconstruction into a practical 2D sketch generation capability for LLMs. This is realized through a novel paradigm of expert‐guided prompt engineering. The process follows three key steps: core entity anchoring, local coordinate system construction, and spatial relationship mapping, which together convert fragmented textual information into structured and interpretable geographical spatial scenes. Experimental results demonstrate that: (1) Through testing on the GeoRel dataset, Qwen3‐8B‐GeoMine achieves an F 1 score improvement of 9% to 13% in geographical entity recognition and spatial relationship extraction compared to the baseline model; (2) Through expert evaluation testing, the 2D scene sketch generation evaluation is conducted on the sample dataset. The results show improvements of 46.0% in core entity recognition accuracy and over 50% in spatial relationship reasoning accuracy. It enables both large‐scale regional spatial association reconstruction across cities and small‐scale restoration of entity spatial layouts within cities, demonstrating substantial potential for advancing geospatial intelligence in LLMs.


  • Open Access

    Cyber Potential Metaphorical Map Method Based on GMap

    by Dongyu Si, Bingchuan Jiang, Qing Xia, Tingting Li, Xiao Wang, Jingxu Liu

    Cyberspace maps facilitate the understanding of complex, abstract cyberspace. Due to the exponential growth of the Internet, the complexity of cyberspace has escalated dramatically. Traditional cyberspace maps are primarily for professionals and thus remain challenging for non-professionals to interpret. Ordinary users often find themselves overwhelmed by the vast amount of information and the complexity of cyberspace. This renders traditional visualization tools inadequate for the general public, thereby highlighting the urgent need for more intuitive and accessible representations. This study uses the metaphor of cyberspace as a familiar geographical space to simplify the understanding of its internal relationships. Based on Autonomous System (AS) connectivity data, a “node-link” model is created to illustrate cyber interactions and dependencies, forming a foundation for analysis. The GMap algorithm visualizes AS connectivity data of countries, converting it into an intuitive map that clearly illustrates the cyber composition and dynamics. Cyber potential and national influence are considered to enhance map practicality and accuracy. A cyber-geography metaphor model integrates scientific and geographical elements, improving readability. The optimized GMap algorithm includes a holisticcyberspace strength index, showing both connectivity and relative country strength in cyberspace. This metaphorical approach aims to reduce information complexity, making cyberspace more comprehensible to the general public.


  • Open Access

    Research on the Metaphorical Map Method of Cyber Potential Based on GMap

    by Dongyu Si, Bingchuan Jiang, Qing Xia, Xiao Wang, Jingxu Liu

    Cyberspace maps aid in understanding complex, abstract cyberspace. With rapid Internet growth, cyberspace complexity has significantly increased. Traditional cyberspace maps are designed for professionals and remain challenging for non-professionals to interpret. Ordinary users often struggle with vast information and complex networks, making traditional visualization tools insufficient for public needs and calling for more intuitive representations. This study uses the metaphor of cyberspace as a familiar geographical space to simplify the understanding of internal relationships. Based on autonomous system (AS) connectivity data, a "node-link" model is created to illustrate network interactions and dependencies, forming a foundation for analysis. The GMap algorithm visualizes AS connectivity data of countries, converting them into an intuitive map for clear visualization of network composition and dynamics. Network potential and national influence in network space are considered to enhance map practicality and accuracy. A web-geography metaphor model integrates scientific and geographical elements, improving readability. The optimized GMap algorithm includes a comprehensive network strength index, displaying both connectivity and relative country strength in cyberspace. This metaphorical approach aims to simplify information complexity, making cyberspace more accessible to the general public.