A survey on learning to reject
Learning to reject is a special kind of self-awareness (the ability to know what you do not
know), which is an essential factor for humans to become smarter. Although machine …
know), which is an essential factor for humans to become smarter. Although machine …
Document understanding dataset and evaluation (dude)
J Van Landeghem, R Tito… - Proceedings of the …, 2023 - openaccess.thecvf.com
We call on the Document AI (DocAI) community to re-evaluate current methodologies and
embrace the challenge of creating more practically-oriented benchmarks. Document …
embrace the challenge of creating more practically-oriented benchmarks. Document …
Training uncertainty-aware classifiers with conformalized deep learning
Deep neural networks are powerful tools to detect hidden patterns in data and leverage
them to make predictions, but they are not designed to understand uncertainty and estimate …
them to make predictions, but they are not designed to understand uncertainty and estimate …
Out-of-vocabulary challenge report
This paper presents final results of the Out-Of-Vocabulary 2022 (OOV) challenge. The OOV
contest introduces an important aspect that is not commonly studied by Optical Character …
contest introduces an important aspect that is not commonly studied by Optical Character …
Clipter: Looking at the bigger picture in scene text recognition
Reading text in real-world scenarios often requires understanding the context surrounding it,
especially when dealing with poor-quality text. However, current scene text recognizers are …
especially when dealing with poor-quality text. However, current scene text recognizers are …
Textual alchemy: Coformer for scene text understanding
G Deshmukh, O Susladkar… - Proceedings of the …, 2024 - openaccess.thecvf.com
Abstract The paper presents CoFormer (Convolutional Fourier Transformer), a robust and
adaptable transformer architecture designed for a range of scene text tasks. CoFormer …
adaptable transformer architecture designed for a range of scene text tasks. CoFormer …
[图书][B] Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XX
The 39-volume set, comprising the LNCS books 13661 until 13699, constitutes the refereed
proceedings of the 17th European Conference on Computer Vision, ECCV 2022, held in Tel …
proceedings of the 17th European Conference on Computer Vision, ECCV 2022, held in Tel …
Context-aware selective label smoothing for calibrating sequence recognition model
S Huang, Y Luo, Z Zhuang, JG Yu, M He… - Proceedings of the 29th …, 2021 - dl.acm.org
Despite the success of deep neural network (DNN) on sequential data (ie, scene text and
speech) recognition, it suffers from the over-confidence problem mainly due to overfitting in …
speech) recognition, it suffers from the over-confidence problem mainly due to overfitting in …
Textadain: Paying attention to shortcut learning in text recognizers
Leveraging the characteristics of convolutional layers, neural networks are extremely
effective for pattern recognition tasks. However in some cases, their decisions are based on …
effective for pattern recognition tasks. However in some cases, their decisions are based on …
Perception and Semantic Aware Regularization for Sequential Confidence Calibration
Deep sequence recognition (DSR) models receive increasing attention due to their superior
application to various applications. Most DSR models use merely the target sequences as …
application to various applications. Most DSR models use merely the target sequences as …