8 Hits in 2.0 sec

Deep learning based retrieval system for gigapixel histopathology cases and open access literature [article]

Sebastian Otalora, Roger Schaer, Manfredo Atzori, Oscar Alfonso Jimenez del Toro, Henning Muller
2018 bioRxiv   pre-print
similar areas using deep learning representations.  ...  The back-end similarity computation algorithms are based on a multimodal approach, thus allowing to exploit both text information and content-based image features.  ...  backend code, a set of python scripts were developed for deep feature extracion using a previously-trained model using the Keras framework 3 .  ... 
doi:10.1101/408237 fatcat:nnlbgydgcrdizng2wp2rnc3fwq

Extraction of Feature Words with the Same Generality Level as Query using Restricted Bootstrapping

Jun Zeng, Toshihiko Sakai, Brendan Flanagan, Sachio Hirokawa
2012 2012 IEEE 14th International Conference on Commerce and Enterprise Computing  
This paper proposes a method to extract feature words with the same level as user's query using restricted bootstrap.  ...  Both the base and visual feature in a web page are used to calculate the weight of each candidate phrase.  ...  The system extracts top p% key-phrases for each web page based on these two features and then generates a term set using union operators.  ... 
doi:10.1109/cec.2012.40 dblp:conf/wecwis/ZengSFH12 fatcat:beybp7vlkbe2zkdvzdyw4ocge4

Dynamic web page authoring by example using ontology-based domain knowledge

José A. Macías, Pablo Castells
2003 Proceedings of the 8th international conference on Intelligent user interfaces - IUI '03  
Authoring dynamic web pages is an inherently difficult task.  ...  Our approach consists of combining Programming By Example (PBE) techniques with an ontology-based representation of knowledge displayed in web pages.  ...  Web data is copied directly from Netscape Navigator using APIs of those browsers.  ... 
doi:10.1145/604050.604068 fatcat:v3atyvcwijb6pcpfkypvb4t6nu

Graph Representation Integrating Signals for Emotion Recognition and Analysis

Teresa Zawadzka, Tomasz Wierciński, Grzegorz Meller, Mateusz Rock, Robert Zwierzycki, Michał R. Wróbel
2021 Sensors  
Data reusability is an important feature of current research, just in every field of science.  ...  Therefore, it is extremely important to provide solutions allowing one to (re)use data from a variety of sources, which usually demands data integration.  ...  The analysis was performed using Tableau with the use of an existing web data connector. The Cypher queries used to extract the data in a tabular form-fit for further analysis-are shown in Listing 9.  ... 
doi:10.3390/s21124035 fatcat:52cgb7nw3ncnfmyhocjrpcqpr4

Optical Flow in Driver Assistance Systems

Naveen Onkarappa
2014 ELCVIA Electronic Letters on Computer Vision and Image Analysis  
A feature based five-point algorithm that is regarded as a classical in visual odometry is proposed by Nister [68] .  ...  Feature-based methods seek correspondences for sparse image features such as edges or corners (e.g., [28, 101] ).  ... 
doi:10.5565/rev/elcvia.593 fatcat:hjr5d4inkfeezdri7vyavlj27i

User-centric knowledge extraction and maintenance [article]

Steffen Metzger, Universität Des Saarlandes, Universität Des Saarlandes
Data and Query Model While the proposed framework could be based on any data model or query language, we focus on RDF and SPARQL as these are the de facto standards used in the Semantic Web.  ...  SPARQL endpoints, RDF dumps, dereferenceable URIs, annotated web pages, web services, etc. Some approaches offer a way to query the data on the Web without the need for a local component, e.g.  ... 
doi:10.22028/d291-26563 fatcat:7eznlxojjvge5hyzfxhdgb4uny

Design and analysis of a content-based image retrieval system

Pilar Hernández Mesa
Methods for the detection and extraction of regions and for the extraction and comparison of color, shape, and texture features are also investigated.  ...  Figure 8 . 8 21 Overview of the characteristics used to measure the quality of the extracion.  ...  Marques et al. propose in [93, 94] the extraction of regions of interest in images using visual attention models.  ... 
doi:10.5445/ksp/1000071866 fatcat:wmjtciruvnei3ibkhunbrmmcii


Serena Fabbrocino
So this work has allowed us to achieve several goals.  ...  The data were acquired and processed using the Xcalibur TM software, version 1.3, from ThermoElectron.  ...  The data were acquired and processed using the Xcalibur TM software, version 1.3, from ThermoElectron.  ... 
doi:10.6092/unina/fedoa/10132 fatcat:5pm7c6eo3zaa7c6bq4tutgqime