paper-with-me

홈 › Papers

Multimodal Semantic Transfer from Text to Image. Fine-Grained Image Classification by Distributional Semantics

2020-01-07 · Simon Donig, Maria Christoforaki, Bernhard Bermeitinger, Siegfried Handschuh

In the last years, image classification processes like neural networks in the area of art-history and Heritage Informatics have experienced a broad distribution (Lang and Ommer 2018). These methods face several challenges, including the handling of comparatively small amounts of data as well as high-dimensional data in the Digital Humanities. Here, a Convolutional Neural Network (CNN) is used that output is not, as usual, a series of flat text labels but a series of semantically loaded vectors. These vectors result from a Distributional Semantic Model (DSM) which is generated from an in-domain text corpus. ----- In den letzten Jahren hat die Verwendung von Bildklassifizierungsverfahren wie neuronalen Netzwerken auch im Bereich der historischen Bildwissenschaften und der Heritage Informatics weite Verbreitung gefunden (Lang und Ommer 2018). Diese Verfahren stehen dabei vor einer Reihe von Herausforderungen, darunter dem Umgangmit den vergleichsweise kleinen Datenmengen sowie zugleich hochdimensionalen Da-tenr\"aumen in den digitalen Geisteswissenschaften. Meist bilden diese Methoden dieKlassifizierung auf einen vergleichsweise flachen Raum ab. Dieser flache Zugang verliert im Bem\"uhen um ontologische Eindeutigkeit eine Reihe von relevanten Dimensionen, darunter taxonomische, mereologische und assoziative Beziehungen zwischenden Klassen beziehungsweise dem nicht formalisierten Kontext. Dabei wird ein Convolutional Neural Network (CNN) genutzt, dessen Ausgabe im Trainingsprozess, anders als herk\"ommlich, nicht auf einer Serie flacher Textlabel beruht, sondern auf einer Serie von Vektoren. Diese Vektoren resultieren aus einem Distributional Semantic Model (DSM), welches aus einem Dom\"ane-Textkorpus generiert wird.

📄 PDF Abstract BibTeX arXiv:2001.02372

Code (0)

등록된 구현이 없습니다.

Tasks

Fine-Grained Image ClassificationGeneral Classificationimage-classificationImage Classification

Similar Papers 제목 키워드 기반

Images Don't Lie: Transferring Deep Visual Semantic Features to Large-Scale Multimodal Learning to Rank

2015-11-20 · Corey Lynch, Kamelia Aryafar, Josh Attenberg

Search is at the heart of modern e-commerce. As a result, the task of ranking search results automatically (learning to rank) is a multibillion dollar machine learning problem. Traditional models optimize over a few hand…

Learning-To-Rank

Embedding Arithmetic of Multimodal Queries for Image Retrieval

2021-12-06 · Guillaume Couairon, Matthieu Cord, Matthijs Douze, Holger Schwenk

Latent text representations exhibit geometric regularities, such as the famous analogy: queen is to king what woman is to man. Such structured semantic relations were not demonstrated on image representations. Recent wor…

Image RetrievalImage-text matchingRetrievalSentence+1

FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning

2026-06-30 · Zekai Chen, Kairui Yang, Xuaner Chen, Xunkai Li 외 arxiv

Multimodal graph foundation models aim to learn reusable knowledge from graphs enriched with text, images, attributes, and relational topology, thereby supporting diverse graph-centric and modality-centric tasks. In prac…

Representation Learning

CarbonCLIP: Enhance Carbon Prediction from Satellite Imagery via Integrated Street-View Semantics and Temporal Context Training

2026-07-08 · Zeru Yang, Fang-Ying Gong, Steve H. L. Yim, Chau Yuen arxiv

Accurately estimating urban carbon emissions is critical for sustainable urban planning, yet many existing approaches remain difficult to apply consistently across cities due to data-source heterogeneity and the lack of …

Contrastive Learning

Contrastive Parameter Disentanglement for Multi-modal Remote Sensing Image Generation

2026-07-26 · Yu Zhang, Wenda Zhao, Haojun Tang, Haipeng Wang arxiv

Existing remote sensing image generation methods are largely confined to single-modality synthesis and therefore fail to exploit the complementary information inherent in multimodal imagery. To address this limitation, w…

Image Generation