We present CONSENT, a simple yet effective CONtext SENsitive Transformer framework for context-dependent object classification within a fully-trainable end-to-end deep learning pipeline. We exemplify the proposed framework on the task of bold words detection proving state-of-the-art results. Given an image containing text of unknown font-types (e.g. Arial, Calibri, Helvetica), unknown language, taken under various degrees of illumination, angle distortion and scale variation, we extract all the words and learn a context-dependent binary classification (i.e. bold versus non-bold) using an end-to-end transformer-based neural network ensemble. To prove the extensibility of our framework, we demonstrate competitive results against state-of-the-art for the game of rock-paper-scissors by training the model to determine the winner given a sequence with 2 pictures depicting hand poses.
@article{arxiv.2205.07683,
title = {CONSENT: Context Sensitive Transformer for Bold Words Classification},
author = {Ionut-Catalin Sandu and Daniel Voinea and Alin-Ionut Popa},
journal= {arXiv preprint arXiv:2205.07683},
year = {2022}
}