Comprehensive linguistic-visual composition network for image retrieval

H Wen, X Song, X Yang, Y Zhan, L Nie - Proceedings of the 44th …, 2021 - dl.acm.org
Composing text and image for image retrieval (CTI-IR) is a new yet challenging task, for
which the input query is not the conventional image or text but a composition, ie, a reference …

Using machine learning for cognitive Robotic Process Automation (RPA)

P Martins, F Sá, F Morgado… - 2020 15th Iberian …, 2020 - ieeexplore.ieee.org
There are many business routine tasks and processes which are performed by qualified
resources which can be reallocated, allowing qualified workers to dedicate their effort to …

Large-scale instance-level image retrieval

G Amato, F Carrara, F Falchi, C Gennaro… - Information Processing & …, 2020 - Elsevier
The great success of visual features learned from deep neural networks has led to a
significant effort to develop efficient and scalable technologies for image retrieval …

Detailed investigation of deep features with sparse representation and dimensionality reduction in cbir: A comparative study

AS Tarawneh, C Celik, AB Hassanat… - Intelligent Data …, 2020 - content.iospress.com
Research on content-based image retrieval (CBIR) has been under development for
decades, and numerous methods have been competing to extract the most discriminative …

OntoKnowNHS: ontology driven knowledge centric novel hybridised semantic scheme for image recommendation using knowledge graph

N Roopak, G Deepak - Knowledge Graphs and Semantic Web: Third …, 2021 - Springer
Multimedia content is increasing immensely as there are various websites available to
upload images. Image retrieval is a method of searching for, viewing, and retrieving images …

Reproducible experiments with learned metric index framework

T Slanináková, M Antol, J Ol'ha, V Dohnal, S Ladra… - Information Systems, 2023 - Elsevier
This work is a companion reproducible paper of a previous paper (Antol et al., 2021) in
which we presented an alternative to the traditional paradigm of similarity searching in …

Data-driven learned metric index: an unsupervised approach

T Slanináková, M Antol, J OǏha, V Kaňa… - Similarity Search and …, 2021 - Springer
Metric indexes are traditionally used for organizing unstructured or complex data to speed
up similarity queries. The most widely-used indexes cluster data or divide space using hyper …

Deep permutations: deep convolutional neural networks and permutation-based indexing

G Amato, F Falchi, C Gennaro, L Vadicamo - Similarity Search and …, 2016 - Springer
The activation of the Deep Convolutional Neural Networks hidden layers can be
successfully used as features, often referred as Deep Features, in generic visual similarity …

PPP-codes for large-scale similarity searching

D Novak, P Zezula - Transactions on Large-Scale Data-and Knowledge …, 2016 - Springer
Many current applications need to organize data with respect to mutual similarity between
data objects. A typical general strategy to retrieve objects similar to a given sample is to …

Metric hull as similarity-aware operator for representing unstructured data

M Antol, M Jánošová, V Dohnal - Pattern Recognition Letters, 2021 - Elsevier
Similarity searching has become widely utilized in many online services processing
unstructured and complex data, eg, Google Images. Metric spaces are often applied to …