# From visual words to a visual grammar: using language modelling for image classification

Source: [From visual words to a visual grammar: using language modelling for image classification](<https://www.sota2.com/research/paper/68fa63311e209131ce9fd398>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:35:17.063Z

Authors: Antonio Foncubierta-Rodr\\'iguez, Henning M\\"uller, Adrien Depeursinge

Published: 2017-03-16T11:46:57.000Z

## Abstract

The Bag--of--Visual--Words (BoVW) is a visual description technique that aims at shortening the semantic gap by partitioning a low--level feature space into regions of the feature space that potentially correspond to visual concepts and by giving more value to this space. In this paper we present a conceptual analysis of three major properties of language grammar and how they can be adapted to the computer vision and image understanding domain based on the bag of visual words paradigm. Evaluation of the visual grammar shows that a positive impact on classification accuracy and/or descriptor size is obtained when the technique are applied when the proposed techniques are applied.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1703.05571>)

[PDF](<https://arxiv.org/pdf/1703.05571.pdf>)