Q Jiang, J Wang, D Peng, C Liu… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
This paper aims to re-assess scene text recognition (STR) from a data-oriented perspective. We begin by revisiting the six commonly used benchmarks in STR and observe a trend of …
Knowledge graph embedding (KGE) aims at learning powerful representations to benefit various artificial intelligence applications. Meanwhile, contrastive learning has been widely …
M Yang, M Liao, P Lu, J Wang, S Zhu, H Luo… - Proceedings of the 30th …, 2022 - dl.acm.org
Existing text recognition methods usually need large-scale training data. Most of them rely on synthetic training data due to the lack of annotated real images. However, there is a …
Contrastive learning (CL) is widely known to require many negative samples, 65536 in MoCo for instance, for which the performance of a dictionary-free framework is often inferior …
Pursuing accurate and robust recognizers has been a long-lasting goal for scene text recognition (STR) researchers. Recently, attention-based methods have demonstrated their …
X Shen, D Sun, S Pan, X Zhou, LT Yang - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Recent years, graph contrastive learning (GCL), which aims to learn representations from unlabeled graphs, has made great progress. However, the existing GCL methods mostly …
Abstract We introduce Perceiving Stroke-Semantic Context (PerSec), a new approach to self- supervised representation learning tailored for Scene Text Recognition (STR) task …
P Lyu, C Zhang, S Liu, M Qiao, Y Xu, L Wu… - arXiv preprint arXiv …, 2022 - arxiv.org
Text images contain both visual and linguistic information. However, existing pre-training techniques for text recognition mainly focus on either visual representation learning or …
W Wei, L Xia, C Huang - Proceedings of the 17th ACM Conference on …, 2023 - dl.acm.org
Personalized recommender systems play a crucial role in capturing users' evolving preferences over time to provide accurate and effective recommendations on various online …