相关论文: Zero-Shot Satellite Image Retrieval through Joint …

A phrase grounding system localizes a particular object in an image referred to by a natural language query. In previous work, the phrases were restricted to have nouns that were encountered in training, we extend the task to Zero-Shot…

The goal of cross-view image based geo-localization is to determine the location of a given street view image by matching it against a collection of geo-tagged satellite images. This task is notoriously challenging due to the drastic…

Data-driven landslide susceptibility mapping (LSM) typically relies on landslide conditioning factors (LCFs), whose availability, heterogeneity, and preprocessing-related uncertainties can constrain mapping reliability. Recently, Google…

Semantic Embeddings are a popular way to represent knowledge in the field of zero-shot learning. We observe their interpretability and discuss their potential utility in a safety-critical context. Concretely, we propose to use them to add…

We present a network architecture which compares RGB images and untextured 3D models by the similarity of the represented shape. Our system is optimised for zero-shot retrieval, meaning it can recognise shapes never shown in training. We…

Deep learning has significantly advanced building segmentation in remote sensing, yet models struggle to generalize on data of diverse geographic regions due to variations in city layouts and the distribution of building types, sizes and…

Researchers often spend weeks sifting through decades of unlabeled satellite imagery(on NASA Worldview) in order to develop datasets on which they can start conducting research. We developed an interactive, scalable and fast image…

Zero-shot learning, which aims to recognize new categories that are not included in the training set, has gained popularity owing to its potential ability in the real-word applications. Zero-shot learning models rely on learning an…

The frequency of extreme flood events is increasing throughout the world. Daily, high-resolution (30m) Flood Inundation Maps (FIM) observed from space play a key role in informing mitigation and preparedness efforts to counter these extreme…

Pre-trained vision-language models, e.g., CLIP, have been successfully applied to zero-shot semantic segmentation. Existing CLIP-based approaches primarily utilize visual features from the last layer to align with text embeddings, while…

Modern cameras are equipped with a wide array of sensors that enable recording the geospatial context of an image. Taking advantage of this, we explore depth estimation under the assumption that the camera is geocalibrated, a problem we…

Natural disasters usually affect vast areas and devastate infrastructures. Performing a timely and efficient response is crucial to minimize the impact on affected communities, and data-driven approaches are the best choice. Visual question…

Recently, 3D Gaussian Splatting has been introduced as a compelling alternative to NeRF for Earth observation, offering competitive reconstruction quality with significantly reduced training times. In this work, we extend the Earth…

CLIP has demonstrated exceptional image-text matching capabilities due to its training on contrastive learning tasks. Past research has suggested that whereas CLIP effectively matches text to images when the matching can be achieved just by…

Visual querying is essential for interactively exploring massive trajectory data. However, the data uncertainty imposes profound challenges to fulfill advanced analytics requirements. On the one hand, many underlying data does not contain…

Zero-shot image classification using auxiliary information, such as attributes describing discriminative object properties, requires time-consuming annotation by domain experts. We instead propose a method that relies on human gaze as…

Composed Image Retrieval (CIR) is the task of retrieving images matching a reference image augmented with a text, where the text describes changes to the reference image in natural language. Traditionally, models designed for CIR have…

Geoscience intelligence is expected to understand, reason about, and predict earth system changes to support human decision-making in critical domains such as disaster response, climate adaptation and environmental protection. Although…

The rapid advancement of generative models, particularly diffusion-based methods, has significantly improved the realism of synthetic images. As new generative models continuously emerge, detecting generated images remains a critical…

Several recent publications have proposed methods for mapping images into continuous semantic embedding spaces. In some cases the embedding space is trained jointly with the image transformation. In other cases the semantic embedding space…