Distributional semantics of objects in visual scenes in comparison to text
2019 | journal article. A publication with affiliation to the University of Göttingen.
Jump to: Cite & Linked | Documents & Media | Details | Version history
Documents & Media
Details
- Authors
- Lüddecke, Timo ; Agostini, Alejandro ; Fauth, Michael ; Tamosiunaite, Minija ; Wörgötter, Florentin
- Abstract
- The distributional hypothesis states that the meaning of a concept is defined through the contexts it occurs in. In practice, often word co-occurrence and proximity are analyzed in text corpora for a given word to obtain a real-valued semantic word vector, which is taken to (at least partially) encode the meaning of this word. Here we transfer this idea from text to images, where pre-assigned labels of other objects or activations of convolutional neural networks serve as context. We propose a simple algorithm that extracts and processes object contexts from an image database and yields semantic vectors for objects. We show empirically that these representations exhibit on par performance with state-of-the-art distributional models over a set of conventional objects. For this we employ well-known word benchmarks in addition to a newly proposed object-centric benchmark.
- Issue Date
- 2019
- Journal
- Artificial Intelligence
- Project
- info:eu-repo/grantAgreement/EC/H2020/731761/EU//IMAGINE
- Organization
- Fakultät für Physik
- ISSN
- 0004-3702
- Language
- English