| 1 |
MEduKG: A Deep-Learning-Based Approach for Multi-Modal Educational Knowledge Graph Construction
|
|
|
|
In: Information; Volume 13; Issue 2; Pages: 91 (2022)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Recognition of the Mental Workloads of Pilots in the Cockpit Using EEG Signals
|
|
|
|
In: Applied Sciences; Volume 12; Issue 5; Pages: 2298 (2022)
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Prediction and Visual Intelligence for Security Information: The PREVISION H2020 Project
|
|
|
|
In: CIRCLE 2020 ; https://hal.archives-ouvertes.fr/hal-02877780 ; CIRCLE 2020, Iván Cantador; Max Chevalier; Massimo Melucci; Josiane Mothe, Jul 2020, Samatan, France ; http://ceur-ws.org/Vol-2621/ (2020)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Multimodal deep networks for text and image-based document classification ; Réseau de neurones multimodal pour la classification de documents image/texte
|
|
|
|
In: Conférence Nationale sur les Applications Pratiques de l'Intelligence Artificielle (APIA) ; https://hal.archives-ouvertes.fr/hal-02163257 ; Conférence Nationale sur les Applications Pratiques de l'Intelligence Artificielle (APIA), Jul 2019, Toulouse, France (2019)
|
|
Abstract:
International audience ; Classification of document images is a critical step for archival of old manuscripts, online subscription and administrative procedures. Computer vision and deep learning have been suggested as a first solution to classify documents based on their visual appearance. However, achieving the fine-grained classification that is required in real-world setting cannot be achieved by visual analysis alone. Often, the relevant information is in the actual text content of the document. We design a multimodal neural network that is able to learn from word embeddings, computed on text extracted by OCR, and from the image. We show that this approach boosts pure image accuracy by 3% on Tobacco3482 and RVL-CDIP augmented by our new QS-OCR text dataset (https://github.com/Quicksign/ocrized-text-dataset), even without clean text information. ; La classification automatique de documents numérisés est im-portante pour la dématérialisation de documents historiques comme de procédures administratives. De premières ap-proches ont été suggérées en appliquant des réseaux con-volutifs aux images de documents en exploitant leur aspect visuel. Toutefois, la précision des classes demandée dans un contexte réel dépend souvent de l'information réellement contenue dans le texte, et pas seulement dans l'image. Nous introduisons un réseau de neurones multimodal capable d'apprendre à partir d'un plongement lexical du texte ex-trait par reconnaissance de caractères et des caractéris-tiques visuelles de l'image. Nous démontrons la pertinence de cette approche sur Tobacco3482 et RVL-CDIP, augmen-tés de notre jeu de données textuel QS-OCR (https://github.com/Quicksign/ocrized-text-dataset), sur lesquels nous améliorons les performances d'un modèle image de 3% grâce à l'information sémantique textuelle.
|
|
Keyword:
[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]; [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE]; [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]; apprentissage multimodal; apprentissage profond; classification de documents; data fusion; deep learning; Document classification; fusion de données; multimodal learning
|
|
URL: https://hal.archives-ouvertes.fr/hal-02163257
https://hal.archives-ouvertes.fr/hal-02163257/document
https://hal.archives-ouvertes.fr/hal-02163257/file/article_apia.pdf
|
|
BASE
|
|
Hide details
|
|
|
| 6 |
Data Fusion through Fuzzy-Bayesian Networks for Belief Generation in Cognitive Agents
|
|
|
|
In: Revista de Informática Teórica e Aplicada; v. 26, n. 2 (2019); 69-80 ; 21752745 ; 01034308 (2019)
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Methodology for automatic bioacoustic classification of anurans based on feature fusion
|
|
|
|
In: Expert Systems With Applications[ISSN 0957-4174],v. 50, p. 100-106 (2016)
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Disambiguation of Named Entities in Cultural Heritage Texts Using Linked Data Sets
|
|
|
|
In: New Trends in Databases and Information Systems ; First International Workshop on Semantic Web for Cultural Heritage, SW4CH 2015 ; https://hal.archives-ouvertes.fr/hal-01203784 ; First International Workshop on Semantic Web for Cultural Heritage, SW4CH 2015, Sep 2015, Poitiers, France. pp.505-514, ⟨10.1007/978-3-319-23201-0_51⟩ (2015)
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Mobile Active Authentication via Linguistic Modalities
|
|
|
|
In: DTIC (2015)
|
|
BASE
|
|
Show details
|
|
|
| 10 |
A MapReduce Approach to Address Big Data Classification Problems Based on the Fusion of Linguistic Fuzzy Rules
|
|
|
|
BASE
|
|
Show details
|
|
|
| 11 |
Aging time and brand determination of pasteurized milk using a multisensor e-nose combined with a voltammetric e-tongue
|
|
|
|
In: ISSN: 0928-4931 ; Materials Science and Engineering: C ; https://hal.archives-ouvertes.fr/hal-01073780 ; Materials Science and Engineering: C, Elsevier, 2014, 45, pp.348-358. ⟨10.1016/j.msec.2014.09.030⟩ (2014)
|
|
BASE
|
|
Show details
|
|
|
| 12 |
Data fusion with computational intelligence techniques: a case study of fuzzy inference for terrain assessment
|
|
|
|
BASE
|
|
Show details
|
|
|
| 13 |
Face Recognition and Event Detection in Video: An Overview of PROVE-IT Projects
|
|
|
|
BASE
|
|
Show details
|
|
|
| 14 |
Towards a Simple and Efficient Web Search Framework
|
|
|
|
In: DTIC (2014)
|
|
BASE
|
|
Show details
|
|
|
| 15 |
On the Design of an Intelligent Sensor Network for Flash Flood Monitoring, Diagnosis and Management in Urban Areas
|
|
|
|
BASE
|
|
Show details
|
|
|
| 16 |
Applying query formulation and fusion techniques for cross language news story search
|
|
|
|
In: Arora, Piyush orcid:0000-0002-4261-2860 , Foster, Jennifer orcid:0000-0002-7789-4853 and Jones, Gareth J.F. orcid:0000-0003-2923-8365 (2013) Applying query formulation and fusion techniques for cross language news story search. In: 5th Forum on Information Retrieval Evaluation (FIRE'13), 4 -6 Dec 2013, New Delhi, India. ISBN 978-1-4503- 2830-2 (2013)
|
|
BASE
|
|
Show details
|
|
|
| 17 |
Combining multiple types of intelligence to generate probability maps of moving targets
|
|
|
|
BASE
|
|
Show details
|
|
|
| 18 |
Employing the Intelligence Cycle Process Model Within the Homeland Security Enterprise
|
|
|
|
In: DTIC (2013)
|
|
BASE
|
|
Show details
|
|
|
| 19 |
Better Equipping Reserve Military Intelligence Analyst to Meet the Needs of the Commander by Championing a Process-Driven Training Model
|
|
|
|
In: DTIC (2013)
|
|
BASE
|
|
Show details
|
|
|
| 20 |
Combining Multiple Types of Intelligence to Generate Probability Maps of Moving Targets
|
|
|
|
In: DTIC (2013)
|
|
BASE
|
|
Show details
|
|
|
|
|
