相关论文: GeoWINE: Geolocation based Wiki, Image,News and Ev…

The growing volume of video-based news content has heightened the need for transparent and reliable methods to extract on-screen information. Yet the variability of graphical layouts, typographic conventions, and platform-specific design…

Recently, fake news with text and images have achieved more effective diffusion than text-only fake news, raising a severe issue of multimodal fake news detection. Current studies on this issue have made significant contributions to…

This paper considers the task of matching images and sentences by learning a visual-textual embedding space for cross-modal retrieval. Finding such a space is a challenging task since the features and representations of text and image are…

Event cameras are bio-inspired sensors with some notable features, including high dynamic range and low latency, which makes them exceptionally suitable for perception in challenging scenarios such as high-speed motion and extreme lighting…

Citizens are actively interacting with their surroundings, especially through social media. Not only do shared posts give important information about what is happening (from the users' perspective), but also the metadata linked to these…

MultiGrain is a network architecture producing compact vector representations that are suited both for image classification and particular object retrieval. It builds on a standard classification trunk. The top of the network produces an…

We provide a dataset for enabling Deep Generative Models (DGMs) in engineering design and propose methods to automate data labeling by utilizing large-scale foundation models. GeoBiked is curated to contain 4 355 bicycle images, annotated…

In many Twitter studies, it is important to know where a tweet came from in order to use the tweet content to study regional user behavior. However, researchers using Twitter to understand user behavior often lack sufficient geo-tagged…

In this paper we propose to learn a multimodal image and text embedding from Web and Social Media data, aiming to leverage the semantic knowledge learnt in the text domain and transfer it to a visual model for semantic image retrieval. We…

Geotagged data can be used to describe regions in the world and discover local themes. However, not all data produced within a region is necessarily specifically descriptive of that area. To surface the content that is characteristic for a…

How many crimes occurred in the city center? And exactly which part of town is the 'city center'? While location is at the heart of many data questions, geographic location can be difficult to specify in natural language (NL) queries. This…

Despite advances in multimodal learning, challenging benchmarks for mixed-modal image retrieval that combines visual and textual information are lacking. This paper introduces a novel benchmark to rigorously evaluate image retrieval that…

Visual document retrieval has become essential for accessing information in visually rich documents. Existing approaches fall into two camps. Late-interaction retrievers achieve strong quality through fine-grained token-level matching but…

In this paper, we present a method for localizing a query image with respect to a precomputed 3D Gaussian Splatting (3DGS) scene representation. First, the method uses 3DGS to render a synthetic RGBD image at some initial pose estimate.…

We propose a label propagation approach to geolocation prediction based on Modified Adsorption, with two enhancements:(1) the removal of "celebrity" nodes to increase location homophily and boost tractability, and (2) he incorporation of…

This paper describes PinView, a content-based image retrieval system that exploits implicit relevance feedback collected during a search session. PinView contains several novel methods to infer the intent of the user. From relevance…

Despite recent progress in computer vision, fine-grained interpretation of satellite images remains challenging because of a lack of labeled training data. To overcome this limitation, we propose using Wikipedia as a previously untapped…

Building upon recent Deep Neural Network architectures, current approaches lying in the intersection of computer vision and natural language processing have achieved unprecedented breakthroughs in tasks like automatic captioning or image…

Geocoding involves automatic extraction of location coordinates of incidents reported in news articles, and can be used for epidemic intelligence or disaster management. This paper introduces Retrieval-Augmented Coordinate Capture Of Online…

The problem visual place recognition is commonly used strategy for localization. Most successful appearance based methods typically rely on a large database of views endowed with local or global image descriptors and strive to retrieve the…