A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Multilingual Scene Character Recognition System using Sparse Auto-Encoder for Efficient Local Features Representation in Bag of Features
[article]
2018
arXiv
pre-print
Preserved Fulltext
Other Versions
This give birth to Scene Character Recognition (SCR) which is an important step in scene text recognition pipeline. ...
In this paper, we extended the Bag of Features (BoF)-based model using deep learning for representing features for accurate SCR of different languages. ...
ACKNOWLEDGMENT This work is performed in the framework of a thesis MO-BIDOC financed by the EU under the program PASRI. ...
arXiv:1806.07374v4
fatcat:edkrvvarazaurok7cql2aot74a
Deep sparse auto-encoder features learning for Arabic text recognition
2021
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
We propose a novel hybrid network, combining a Bag-of-Feature (BoF) framework for feature extraction based on a deep Sparse Auto-Encoder (SAE), and Hidden Markov Models (HMMs), for sequence recognition ...
In this work, we introduce a new deep learning based system that recognizes Arabic text contained in images. ...
To further fine-tune the visual dictionary and learn the feature codes for each class used for subsequent mid-level patches, we construct a supervised two HL AE. ...
doi:10.1109/access.2021.3053618
fatcat:p7jhbokjsjbunceuq4lu7xnmci
Machine Learning framework for image classification
2018
Advances in Science, Technology and Engineering Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
The purpose of our work is to guess the best machine learning framework techniques to recognize the stop sign images. The trained model will be integrated into a robotic system in a future work. ...
For feature extraction functions we evaluate the use of the classical Speed Up Robust Features technique against global color feature extraction. ...
Learning and Recognition Based on BoW Models Computer vision researchers have developed several learning methods to leverage the BoF model for image related tasks. ...
doi:10.25046/aj030101
fatcat:7u26g3kkjnczdledr33shbs6ge
Machine learning framework for image classification
2017
2017 International Conference on Information and Digital Technologies (IDT)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
The purpose of our work is to guess the best machine learning framework techniques to recognize the stop sign images. The trained model will be integrated into a robotic system in a future work. ...
For feature extraction functions we evaluate the use of the classical Speed Up Robust Features technique against global color feature extraction. ...
Learning and Recognition Based on BoW Models Computer vision researchers have developed several learning methods to leverage the BoF model for image related tasks. ...
doi:10.1109/dt.2017.8012075
fatcat:z4cqcklexraafngh6pzzbzbeo4
Machine learning framework for image classification
2016
2016 7th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
The purpose of our work is to guess the best machine learning framework techniques to recognize the stop sign images. The trained model will be integrated into a robotic system in a future work. ...
For feature extraction functions we evaluate the use of the classical Speed Up Robust Features technique against global color feature extraction. ...
Learning and Recognition Based on BoW Models Computer vision researchers have developed several learning methods to leverage the BoF model for image related tasks. ...
doi:10.1109/setit.2016.7939841
fatcat:wgsrv6ishrecrpldub7thdtefe
Spatial-bag-of-features
2010
2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
The proposed retrieval framework works well in image retrieval task owing to the following three properties: 1) the encoding of geometric information of objects for capturing objects' spatial transformation ...
, 2) the supervised feature selection and combination strategy for enhancing the discriminative power, and 3) the representation of bag-offeatures for effective image matching and indexing for large scale ...
In the future, we are interested in developing a more principled framework of our feature family and applying SBOF in recognition tasks. ...
doi:10.1109/cvpr.2010.5540021
dblp:conf/cvpr/CaoWLZZ10
fatcat:cc3zz5zw5nf6vkzznyokivn5zm
Attention-based Neural Bag-of-Features Learning for Sequence Data
2022
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
for the given learning objective. ...
In this paper, we propose 2D-Attention (2DA), a generic attention formulation for sequence data, which acts as a complementary computation block that can detect and focus on relevant sources of information ...
The European Commission is not responsible for any use that may be made of the information it contains. ...
doi:10.1109/access.2022.3169776
fatcat:2kb6bcbdlva7fp2eeecg4eqcj4
Model Update Strategies about Object Tracking: A State of the Art Review
2019
Electronics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
information can be utilized as a tool for state estimation. ...
, and the background update frameworks are discussed afterwards. ...
For instance, in [42] , the "words" are classified in a supervised way while using SVM. ...
doi:10.3390/electronics8111207
fatcat:7od3ec2zm5h7hiu66ydppkt4xi
Johnny: An Autonomous Service Robot for Domestic Environments
2011
Journal of Intelligent and Robotic Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
The results and lessons learned of these benchmarks are explained in more detail. ...
In this article we describe the architecture, algorithms and real-world benchmarks performed by Johnny Jackanapes, an autonomous service robot for domestic environments. ...
CC classification using supervised machine learning based becomes cumbersome because of the need for labeled CCs to prepare training datasets for CC classification. ...
doi:10.1007/s10846-011-9608-y
fatcat:caa3tvz53nagvdso5l7lajbteq
Attention-based Neural Bag-of-Features Learning for Sequence Data
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
for the given learning objective. ...
In this paper, we propose 2D-Attention (2DA), a generic attention formulation for sequence data, which acts as a complementary computation block that can detect and focus on relevant sources of information ...
Learning BoF representations consists of two steps: dictionary learning and feature quantization and encoding. ...
arXiv:2005.12250v1
fatcat:mbm4frdyobexxno7fzcxxhk6du
Action Representations in Robotics: A Taxonomy and Systematic Classification
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Given this definition we then introduce a taxonomy for categorizing action representations in robotics along various dimensions. ...
Unfortunately, to this day we still lack both a clear understanding of the concept of an action and a set of established criteria that ultimately characterize an action. ...
attributing them a primary role in shaping a virtuous character. ...
arXiv:1809.04317v1
fatcat:lr27hdjjurh2bj6q5ly23mocte
Partially supervised learning of models for visual scene and object recognition
2018
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In the field of semi-supervised learning, a novel approach for learning annotations in large image collections of natural scene images has been proposed. ...
The contributions are three-fold and range from feature augmentation, over semi-supervised learning for natural scene classification to zero-shot object recognition. ...
Semi-Supervised Learning for Character Recognition in Historical Archive Documents. ...
doi:10.17877/de290r-19113
fatcat:qpogtdzehzgujnwn2dpwuyp4iq
Instance search retrospective with focus on TRECVID
2017
International Journal of Multimedia Information Retrieval
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The Instance Search (INS) benchmark worked with a variety of large collections of data including Sound & Vision, Flickr, BBC (British Broadcasting Corporation) Rushes for the first 3 pilot years and with ...
the small world of the BBC Eastenders series for the last 3 years. ...
For example, earlier studies experimented with object and scene retrieval in two feature-length movies [64] , with person-spotting and automatic face recognition for film characters [63] , [1] , with ...
doi:10.1007/s13735-017-0121-3
pmid:28758054
pmcid:PMC5531298
fatcat:3khp2cscmbhohipfx246gspqlq
Application of Prior Information to Discriminative Feature Learning
2018
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
To this end, we present a support discrimination dictionary learning method, which finds a dictionary under which the feature representation of images from the same class have a common sparse structure ...
priors and verify their effectiveness in the discriminant feature learning. ...
In the context of dictionary learning, the dictionary D D D is not fixed, and the task involves learning the dictionary from the data in a supervised learning step. ...
doi:10.17863/cam.32915
fatcat:gto4zcwzgnhk5hjidq5k5uwf3u
Issues on Retrieval of Sound Effects in Large Collaborative Databases
2008
Zenodo
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The context in which these sites are growing and many of their important aspects are presented and discussed in this work. ...
The collaborative sound database Freesound.org has been chosen for the experiments. ...
The learning task is based on a supervised multiclass labeling model, with a multinomial distribution of words over a predefined vocabulary. ...
doi:10.5281/zenodo.3744728
fatcat:taqgakq5z5dp5n6d4rpjj7nrte
« Previous
Showing results 1 — 15 out of 38 results