Related papers: Linking Geographic Vocabularies through WordNet
The Linked Open Data practice has led to a significant growth of structured data on the Web in the last decade. Such structured data describe real-world entities in a machine-readable way, and have created an unprecedented opportunity for…
Text-to-point-cloud (T2P) localization aims to infer precise spatial positions within 3D point cloud maps from natural language descriptions, reflecting how humans perceive and communicate spatial layouts through language. However, existing…
Object Navigation (ObjectNav) has made great progress with large language models (LLMs), but still faces challenges in memory management, especially in long-horizon tasks and dynamic scenes. To address this, we propose TopoNav, a new…
We demonstrate that a character-level recurrent neural network is able to learn out-of-vocabulary (OOV) words under federated learning settings, for the purpose of expanding the vocabulary of a virtual keyboard for smartphones without…
We introduce TopoNets, end-to-end probabilistic deep networks for modeling semantic maps with structure reflecting the topology of large-scale environments. TopoNets build a unified deep network spanning multiple levels of abstraction and…
Geological modeling currently uses various computer-based applications. Data harmonization at the semantic level by means of ontologies is essential for making these applications interoperable. Since geo-modeling is currently part of…
Reconstructing semantic 3D building models at the level of detail (LoD) 3 is a long-standing challenge. Unlike mesh-based models, they require watertight geometry and object-wise semantics at the fa\c{c}ade level. The principal challenge of…
Large language models hallucinate factual claims and struggle to ground their outputs in retrievable evidence, particularly in non-English languages. Existing resources impose a trade-off: structured knowledge bases lack textual grounding,…
We tackle the problem of 3D point cloud localization based on a few natural linguistic descriptions and introduce a novel neural network, Text2Loc, that fully interprets the semantic relationship between points and text. Text2Loc follows a…
While the biomedical community has published several "open data" sources in the last decade, most researchers still endure severe logistical and technical challenges to discover, query, and integrate heterogeneous data and knowledge from…
This paper presents an Open-Vocabulary Online 3D semantic mapping pipeline, that we denote by its acronym OVO. Given a sequence of posed RGB-D frames, we detect and track 3D segments, which we describe using CLIP vectors. These are computed…
Sentence semantic matching is one of the fundamental tasks in natural language processing, which requires an agent to determine the semantic relation among input sentences. Recently, deep neural networks have achieved impressive performance…
The goal in word spotting is to retrieve parts of document images which are relevant with respect to a certain user-defined query. The recent past has seen attribute-based Convolutional Neural Networks take over this field of research. As…
Word vector representations open up new opportunities to extract useful information from unstructured text. Defining a word as a vector made it easy for the machine learning algorithms to understand a text and extract information from. Word…
Ontologies represent the conceptual knowledge of a domain. At the core of an ontology is the taxonomy of concepts and subconcepts that represent specific entities, which can be complex to build. In many cases, information is available in…
In this work, we investigate the use of OpenStreetMap data for semantic labeling of Earth Observation images. Deep neural networks have been used in the past for remote sensing data classification from various sensors, including…
Recent advances in neural word embedding provide significant benefit to various information retrieval tasks. However as shown by recent studies, adapting the embedding models for the needs of IR tasks can bring considerable further…
Progress on deep language understanding is inhibited by the lack of a broad coverage lexicon that connects linguistic behavior to ontological concepts and axioms. We have developed COLLIE-V, a deep lexical resource for verbs, with the…
Vision-Language Models (VLMs) have shown significant progress in open-set challenges. However, the limited availability of 3D datasets hinders their effective application in 3D scene understanding. We propose LOC, a general language-guided…
We face a unprecedented amount of geospatial data, describing directly or indirectly the Earth Surface at multiple spatial, temporal, and semantic scales, and stemming from numerous contributors, from satellites to citizens. The main…