Result Number | Material Type | Add to My Shelf Action | Record Details and Options |
---|---|---|---|
1 |
Material Type: Article
|
Redefining Binarization and the Visual ArchetypearXiv.org, 2016-092016. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;http://arxiv.org/licenses/nonexclusive-distrib/1.0 ;EISSN: 2331-8422 ;DOI: 10.48550/arxiv.1609.09451Full text available |
|
2 |
Material Type: Web Resources
|
A Generic Framework for Information Segmentation in Document Images: A part-based ApproachDigital Resources/Online E-Resources |
|
3 |
Material Type: Article
|
Scene analysis by mid-level attribute learning using 2D LSTM networks and an application to web-image taggingPattern recognition letters, 2015-10, Vol.63, p.23 [Peer Reviewed Journal]ISSN: 0167-8655 ;ISSN: 1872-7344 ;EISSN: 1872-7344 ;DOI: 10.1016/j.patrec.2015.06.003Digital Resources/Online E-Resources |
|
4 |
Material Type: Article
|
Multilevel Context Representation for Improving Object RecognitionarXiv.org, 2017-032017. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;http://arxiv.org/licenses/nonexclusive-distrib/1.0 ;EISSN: 2331-8422 ;DOI: 10.48550/arxiv.1703.06408Full text available |
|
5 |
Material Type: Conference Proceeding
|
Recognition of Historical Greek Polytonic Scripts Using LSTM Networks13th International Conference on Document Analysis and Recognition, 2015, p.766DOI: 10.1109/ICDAR.2015.7333865Digital Resources/Online E-Resources |
|
6 |
Material Type: Article
|
A Pitfall of Unsupervised Pre-TrainingarXiv.org, 2017-122017. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;http://arxiv.org/licenses/nonexclusive-distrib/1.0 ;EISSN: 2331-8422 ;DOI: 10.48550/arxiv.1703.04332Full text available |
|
7 |
Material Type: Article
|
A Pitfall of Unsupervised Pre-TrainingarXiv.org, 2017-122017. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;http://arxiv.org/licenses/nonexclusive-distrib/1.0 ;EISSN: 2331-8422 ;DOI: 10.48550/arxiv.1712.01655Full text available |
|
8 |
Material Type: Article
|
Symbol Grounding Association in Multimodal Sequences with Missing ElementsarXiv.org, 2017-122017. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;http://arxiv.org/licenses/nonexclusive-distrib/1.0 ;EISSN: 2331-8422 ;DOI: 10.48550/arxiv.1511.04401Full text available |
|
9 |
Material Type: Article
|
Open Evaluation Tool for Layout Analysis of Document ImagesarXiv.org, 2017-112017. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;http://arxiv.org/licenses/nonexclusive-distrib/1.0 ;EISSN: 2331-8422 ;DOI: 10.48550/arxiv.1712.01656Full text available |
|
10 |
Material Type: Article
|
Real-Time Document Image Classification using Deep CNN and Extreme Learning MachinesarXiv.org, 2017-112017. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;http://arxiv.org/licenses/nonexclusive-distrib/1.0 ;EISSN: 2331-8422 ;DOI: 10.48550/arxiv.1711.05862Full text available |
|
11 |
Material Type: Article
|
Historical Document Image Segmentation with LDA-Initialized Deep Neural NetworksarXiv.org, 2017-102017. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;http://arxiv.org/licenses/nonexclusive-distrib/1.0 ;EISSN: 2331-8422 ;DOI: 10.48550/arxiv.1710.07363Full text available |
|
12 |
Material Type: Conference Proceeding
|
Scale and Rotation Invariant OCR for Pashto Cursive Script using MDLSTM Network13th International Conference on Document Analysis and Recognition, 2015, p.1101DOI: 10.1109/ICDAR.2015.7333931Digital Resources/Online E-Resources |
|
13 |
Material Type: Article
|
Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image ClassificationarXiv.org, 2017-042017. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;http://arxiv.org/licenses/nonexclusive-distrib/1.0 ;EISSN: 2331-8422 ;DOI: 10.48550/arxiv.1704.03557Full text available |
|
14 |
Material Type: Article
|
PCA-Initialized Deep Neural Networks Applied To Document Image AnalysisarXiv.org, 2017-022017. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;http://arxiv.org/licenses/nonexclusive-distrib/1.0 ;EISSN: 2331-8422 ;DOI: 10.48550/arxiv.1702.00177Full text available |
|
15 |
Material Type: Conference Proceeding
|
Selecting Autoencoder Features for Layout Analysis of Historical DocumentsThird International Workshop on Historical Document Imaging and Processing, 2015, p.55DOI: 10.1145/2809544.2809548Digital Resources/Online E-Resources |
|
16 |
Material Type: Conference Proceeding
|
Recognizable units in Pashto language for OCR13th International Conference on Document Analysis and Recognition, 2015, p.1246DOI: 10.1109/ICDAR.2015.7333963Digital Resources/Online E-Resources |
|
17 |
Material Type: Article
|
Transforming Sensor Data to the Image Domain for Deep Learning - an Application to Footstep DetectionarXiv.org, 2017-072017. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;http://arxiv.org/licenses/nonexclusive-distrib/1.0 ;EISSN: 2331-8422 ;DOI: 10.48550/arxiv.1701.01077Full text available |
|
18 |
Material Type: Article
|
Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image SegmentationarXiv.org, 2015-062015. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;http://arxiv.org/licenses/nonexclusive-distrib/1.0 ;EISSN: 2331-8422 ;DOI: 10.48550/arxiv.1506.07452Full text available |
|
19 |
Material Type: Conference Proceeding
|
Combination of Multiple Aligned Recognition Outputs using WFST and LSTM13th International Conference on Document Analysis and Recognition, 2015, p.31DOI: 10.1109/ICDAR.2015.7333720Digital Resources/Online E-Resources |
|
20 |
Material Type: Article
|
Sparse Radial Sampling LBP for Writer IdentificationarXiv.org, 2015-042015. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;http://arxiv.org/licenses/nonexclusive-distrib/1.0 ;EISSN: 2331-8422 ;DOI: 10.48550/arxiv.1504.06133Full text available |