相关论文: GeoDecoder: Empowering Multimodal Map Understandin…

Geospatial models must adapt to the diversity of Earth observation data in terms of resolutions, scales, and modalities. However, existing approaches expect fixed input configurations, which limits their practical applicability. We propose…

Online social networks convey rich information about geospatial facets of reality. However in most cases, geographic information is not explicit and structured, thus preventing its exploitation in real-time applications. We address this…

In human reading and communication, individuals tend to engage in geospatial reasoning, which involves recognizing geographic entities and making informed inferences about their interrelationships. To mimic such cognitive process, current…

Large-scale pretraining on Earth observation imagery has yielded powerful representations of the natural and built environment. However, most existing geospatial foundation models do not directly model the structured socioeconomic…

Geolocation, the task of identifying the geographic location of an image, requires abundant world knowledge and complex reasoning abilities. Though advanced large multimodal models (LMMs) have shown superior aforementioned capabilities,…

Document intelligence as a relatively new research topic supports many business applications. Its main task is to automatically read, understand, and analyze documents. However, due to the diversity of formats (invoices, reports, forms,…

Multimodal geometry reasoning requires models to jointly understand visual diagrams and perform structured symbolic inference, yet current vision--language models struggle with complex geometric constructions due to limited training data…

In recent years, molecular representation learning has emerged as a key area of focus in various chemical tasks. However, many existing models fail to fully consider the geometric information of molecular structures, resulting in less…

Surface sensing is widely employed in health diagnostics, manufacturing and safety monitoring. Advances in mobile sensing affords this potential for context awareness in mobile computing, typically with a single sensing modality. Emerging…

Learning dense correspondences across deformable 3D shapes remains a long-standing challenge due to structural variability, non-isometric deformation, and inconsistent topology. Existing methods typically trade off generalization, geometric…

Fine-grained high-resolution remote sensing mapping typically relies on localized visual features, which restricts cross-domain generalizability and often leads to fragmented predictions of large-scale land covers. While global geospatial…

We introduce GeoBuildBench, a benchmark designed to evaluate whether large language models and multimodal agents can ground informal natural-language plane geometry problems into executable geometric constructions. Unlike existing geometry…

Chinese geographic re-ranking task aims to find the most relevant addresses among retrieved candidates, which is crucial for location-related services such as navigation maps. Unlike the general sentences, geographic contexts are closely…

Multi-modal large language models (MLLMs) have achieved remarkable success in image- and region-level remote sensing (RS) image understanding tasks, such as image captioning, visual question answering, and visual grounding. However,…

Program code serves as a bridge linking vision and logic, providing a feasible supervisory approach for enhancing the multimodal reasoning capability of large models through geometric operations such as auxiliary line construction and…

Learned local descriptors based on Convolutional Neural Networks (CNNs) have achieved significant improvements on patch-based benchmarks, whereas not having demonstrated strong generalization ability on recent benchmarks of image-based 3D…

We present a texture network called Deep Encoding Pooling Network (DEP) for the task of ground terrain recognition. Recognition of ground terrain is an important task in establishing robot or vehicular control parameters, as well as for…

We introduce a Multi-modal Neural Machine Translation model in which a doubly-attentive decoder naturally incorporates spatial visual features obtained using pre-trained convolutional neural networks, bridging the gap between image…

The remarkable success of GPT models across various tasks, including toponymy recognition motivates us to assess the performance of the GPT-3 model in the geocoding address parsing task. To ensure that the evaluation more accurately mirrors…

Humans subconsciously engage in geospatial reasoning when reading articles. We recognize place names and their spatial relations in text and mentally associate them with their physical locations on Earth. Although pretrained language models…