Filters








206,555 Hits in 3.6 sec

A Supervised Approach for Text Illustration

Harsh Jhamtani, Shubham Varma, Midhun Gundapuneni, Siddhartha Kumar Dutta
2016 Proceedings of the 2016 ACM on Multimedia Conference - MM '16  
In this paper we propose a novel method to illustrate text articles with pictures from a tagged repository.  ...  We propose a supervised model based on features like readability, picturability, sentiment polarity, and presence of important phrases, to identify and rank key sentences.  ...  We propose a novel method for text illustration which uses supervised learning to score and rank sentences.  ... 
doi:10.1145/2964284.2967214 dblp:conf/mm/JhamtaniVGD16 fatcat:2ptj3qzrgfcelhw6q663s2vi5i

WordSup: Exploiting Word Annotations for Character based Text Detection [article]

Han Hu, Chengquan Zhang, Yuxuan Luo, Yuzhuo Wang, Junyu Han, Errui Ding
2017 arXiv   pre-print
To remedy this dilemma, we propose a weakly supervised framework that can utilize word annotations, either in tight quadrangles or the more loose bounding boxes, for character detector training.  ...  Imagery texts are usually organized as a hierarchy of several visual elements, i.e. characters, words, text lines and text blocks.  ...  Figure 2 : 2 Figure 2: Illustration of our word supervision training approach for a character model.  ... 
arXiv:1708.06720v1 fatcat:nijhnpasujghtfxytdbbbi5hvi

Feature Selection Optimization for Highlighting Opinions Using Supervised and Unsupervised Learning on Arabic Language

2021 International Journal of Advanced Trends in Computer Science and Engineering  
Opinion mining (OM) is one of the promised text mining fields, which are used for polarity discovering via text and has terminus benefits for business.  ...  ML techniques are divided into two approaches: supervised and unsupervised learning, since we herein testified an OM feature selection(FS)using four ML techniques.  ...  Machine learning sentiment analysis (MLSA) MLSA is intended for supervised learning approaches that need pre-annotated text data set in order to train and test some selected features.  ... 
doi:10.30534/ijatcse/2021/251022021 fatcat:xetlwfwmmrddxkcdtzlknv3nm4

Self-Supervised Visual Representations for Cross-Modal Retrieval [article]

Yash Patel, Lluis Gomez, Marçal Rusiñol, Dimosthenis Karatzas, C.V. Jawahar
2019 arXiv   pre-print
In this paper, we present a self-supervised cross-modal retrieval framework that leverages as training data the correlations between images and text on the entire set of Wikipedia articles.  ...  the learned representations are better for cross-modal retrieval when compared to supervised pre-training of the network on the ImageNet dataset.  ...  In this paper we present a self-supervised cross-modal retrieval framework that leverages as supervisory signal the correlations found between images and text on a large collection of illustrated articles  ... 
arXiv:1902.00378v1 fatcat:ksha6zs7u5a53cclm2xjrozu7i

Self-Supervised Learning of Visual Features through Embedding Images into Text Topic Spaces

Lluis Gomez, Yash Patel, Marcal Rusinol, Dimosthenis Karatzas, C. V. Jawahar
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
For this we leverage the hidden semantic structures discovered in the text corpus with a well-known topic modeling technique.  ...  We put forward the idea of performing self-supervised learning of visual features by mining a large scale corpus of multimodal (text and image) documents.  ...  Acknowledgment We gratefully acknowledge the support of the NVIDIA Corporation with the donation of the Titan X Pascal GPU used for this research.  ... 
doi:10.1109/cvpr.2017.218 dblp:conf/cvpr/Gomez-BigordaPR17 fatcat:paymsbngcbfblfp5ehxgnk3gpm

Self-supervised learning of visual features through embedding images into text topic spaces [article]

Lluis Gomez, Yash Patel, Marçal Rusiñol, Dimosthenis Karatzas, C.V. Jawahar
2017 arXiv   pre-print
For this we leverage the hidden semantic structures discovered in the text corpus with a well-known topic modeling technique.  ...  We put forward the idea of performing self-supervised learning of visual features by mining a large scale corpus of multi-modal (text and image) documents.  ...  Acknowledgment We gratefully acknowledge the support of the NVIDIA Corporation with the donation of the Titan X Pascal GPU used for this research.  ... 
arXiv:1705.08631v1 fatcat:c7pu7heiobcexhftqemuuye6pi

TextTopicNet - Self-Supervised Learning of Visual Features Through Embedding Images on Semantic Text Spaces [article]

Yash Patel, Lluis Gomez, Raul Gomez, Marçal Rusiñol, Dimosthenis Karatzas, C.V. Jawahar
2018 arXiv   pre-print
More specifically we use popular text embedding techniques to provide the self-supervision for the training of deep CNN.  ...  We show that adequate visual features can be learned efficiently by training a CNN to predict the semantic textual context in which a particular image is more probable to appear as an illustration.  ...  Business Competitiveness of the Government of Catalonia (ACCIO), CEFIPRA Project 5302-1 and the project "aB-SINTHE -AYUDAS FUNDACIÓN BBVA A EQUIPOS DE INVES-TIGACION CIENTIFICA 2017.  ... 
arXiv:1807.02110v1 fatcat:3qe3xgsuzfem5j5doiak5bexeq

Semi-supervised Text Categorization Using Recursive K-means Clustering [chapter]

Harsha S. Gowda, Mahamad Suhil, D. S. Guru, Lavanya Narayana Raju
2017 Communications in Computer and Information Science  
In this paper, we present a semi-supervised learning algorithm for classification of text documents. A method of labeling unlabeled text documents is presented.  ...  Once the desired clusters are obtained, the respective cluster centroids are considered as representatives of the clusters and the nearest neighbor rule is used for classifying an unknown text document  ...  Acknowledgements The second author of this paper acknowledges the financial support rendered by the University of Mysore under UPE grants for the High Performance Computing laboratory.  ... 
doi:10.1007/978-981-10-4859-3_20 fatcat:36nbz76wh5h5tdtpjblmlzv4je

Page 111 of Journal of Nursing Management Vol. 6, Issue 2 [page]

1998 Journal of Nursing Management  
Table 5 Selection from the answers to the metaphore question Students’ illustrations Effects of group supervision Students’ comments on the illustrations 3 Text: The supervision programme has been a source  ...  AAG 1993 a eee Soe a + > Text: It (the supervision programme) has helped me realize that | will soon be a nurse.  ... 

Construction of supervised and unsupervised learning systems for multilingual text categorization

Chung-Hong Lee, Hsin-Chang Yang
2009 Expert systems with applications  
In this work, we implemented and measured the performance of the leading supervised and unsupervised approaches for multilingual text categorization.  ...  The preliminary results show that our platform models including both supervised and unsupervised learning methods have the potentials for multilingual text categorization.  ...  Implementation of supervised methods for MTC In our previous work, we employed a supervised text mining technique based on support vector machines (SVMs) for training text classifiers in a combined platform  ... 
doi:10.1016/j.eswa.2007.12.052 fatcat:rwqnbwz2lra33o4nwvpge6peqi

Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer [article]

Yair Kittenplon, Inbal Lavi, Sharon Fogel, Yarin Bar, R. Manmatha, Pietro Perona
2022 arXiv   pre-print
We introduce TextTranSpotter (TTS), a transformer-based approach for text spotting and the first text spotting framework which may be trained with both fully- and weakly-supervised settings.  ...  When trained in a fully-supervised manner, TextTranSpotter shows state-of-the-art results on multiple benchmarks.  ...  [42] suggest a weakly-supervised approach for arbitrary text detection, by using an Expectation-Maximization based method, and provide an extensive study of the annotation time under different supervision  ... 
arXiv:2202.05508v2 fatcat:cswkyka4ajetjizoygf32vvatm

Harvesting Information from Captions for Weakly Supervised Semantic Segmentation [article]

Johann Sawatzky, Debayan Banerjee, Juergen Gall
2019 arXiv   pre-print
Since acquiring pixel-wise annotations for training convolutional neural networks for semantic image segmentation is time-consuming, weakly supervised approaches that only require class tags have been  ...  They do not require additional curation as it is the case for the clean class tags used by current weakly supervised approaches and they provide textual context for the classes present in an image.  ...  A popular approach for weakly supervised learning from image tags [21, 52, 1] Figure 1.  ... 
arXiv:1905.06784v1 fatcat:5w23vfamzbeifoq7ef7gsg3yr4

Weakly Supervised Video Moment Retrieval From Text Queries [article]

Niluthpol Chowdhury Mithun, Sujoy Paul, Amit K. Roy-Chowdhury
2019 arXiv   pre-print
However, acquiring a large number of training videos with temporal boundary annotations for each text description is extremely time-consuming and often not scalable.  ...  There have been a few recent methods proposed in text to video moment retrieval using natural language queries, but requiring full supervision during training.  ...  This work was partially supported by NSF grant 1544969 and ONR contract N00014-15-C5113 through a sub-contract from Mayachitra Inc.  ... 
arXiv:1904.03282v2 fatcat:5qithwolavfwpofawe232b6pzi

Weakly Supervised Video Moment Retrieval From Text Queries

Niluthpol Chowdhury Mithun, Sujoy Paul, Amit K. Roy-Chowdhury
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
However, acquiring a large number of training videos with temporal boundary annotations for each text description is extremely timeconsuming and often not scalable.  ...  There have been a few recent methods proposed in text to video moment retrieval using natural language queries, but requiring full supervision during training.  ...  This work was partially supported by NSF grant 1544969 and ONR contract N00014-15-C5113 through a sub-contract from Mayachitra Inc.  ... 
doi:10.1109/cvpr.2019.01186 dblp:conf/cvpr/MithunPR19 fatcat:fv7y4dhnxrhvjdrf4c2w7mm5nm

Text as Data for Conflict Research: A Literature Survey [chapter]

Seraphine F. Maerz, Cornelius Puschmann
2019 Computational Social Sciences  
Computer-aided text analysis (CATA) offers exciting new possibilities for conflict research that this contribution describes using a range of exemplary studies from a variety of disciplines including sociology  ...  Finally, crossvalidation is highlighted as a crucial step in CATA, in order to make the method as useful as possible to scholars interested in enlisting text mining for conflict research.  ...  Supervised text mining is a more sophisticated approach than dictionary applications because it is not limited to a fixed list of keywords.  ... 
doi:10.1007/978-3-030-29333-8_3 fatcat:kxn7lfjrkvcr7nsscbjyem2vse
« Previous Showing results 1 — 15 out of 206,555 results