Call for Papers
DeLTA
is sponsored by
INSTICC
– Institute for Systems and Technologies of Information, Control and Communication
SCOPE
Deep Learning and Big Data Analytics are two major topics of data science, nowadays. Big Data has become important in practice, as many organizations have been collecting massive amounts of data that can contain useful information for business analysis and decisions, impacting existing and future technology. A key benefit of Deep Learning is the ability to process these data and extract high-level complex abstractions as data representations, making it a valuable tool for Big Data Analytics where raw data is largely unlabeled.
Machine-learning and artificial intelligence are pervasive in most real-world applications scenarios such as computer vision, information retrieval and summarization from structured and unstructured multimodal data sources, natural language understanding and translation, and many other application domains. Deep learning approaches, leveraging on big data, are outperforming state-of-the-art more “classical” supervised and unsupervised approaches, directly learning relevant features and data representations without requiring explicit domain knowledge or human feature engineering. These approaches are currently highly important in IoT applications.
CONFERENCE AREAS
Each of these topic areas is expanded below but the sub-topics list is not exhaustive. Papers may address one or more of the listed sub-topics, although authors should not feel limited by them. Unlisted but related sub-topics are also acceptable, provided they fit in one of the following main topic areas:
1. MODELS AND ALGORITHMS
2. MACHINE LEARNING
3. BIG DATA ANALYTICS
4. COMPUTER VISION APPLICATIONS
5. NATURAL LANGUAGE UNDERSTANDING
AREA 1: MODELS AND ALGORITHMS
- Recurrent Neural Network (RNN)
- Evolutionary Methods
- Convolutional Neural Networks (CNN)
- Deep Hierarchical Networks (DHN)
- Dimensionality Reduction
- Unsupervised Feature Learning
- Generative Adversarial Networks (GAN)
- Autoencoders
AREA 2: MACHINE LEARNING
- Active Learning
- Meta-Learning and Deep Networks
- Deep Metric Learning Methods
- Deep Reinforcement Learning
- Learning Deep Generative Models
- Deep Kernel Learning
- Graph Representation Learning
- Gaussian Processes for Machine Learning
- Clustering, Classification and Regression
- Classification Explainability
AREA 3: BIG DATA ANALYTICS
- Extracting Complex Patterns
- IoT and Smart Devices
- Security Threat Detection
- Semantic Indexing
- Fast Information Retrieval
- Scalability of Models
- Data Integration and Fusion
- High-Dimensional Data
- Streaming Data
AREA 4: COMPUTER VISION APPLICATIONS
- Image Classification
- Object Detection
- Face Recognition
- Human Pose Estimation
- Image Retrieval
- Semantic Segmentation
AREA 5: NATURAL LANGUAGE UNDERSTANDING
- Sentiment Analysis
- Question Answering Applications
- Language Translation
- Document Summarization
- Content Filtering on Social Networks
- Recommender Systems
KEYNOTE SPEAKERS
DeLTA 2022 will have several invited keynote speakers, who are internationally recognized experts in their areas. Their names are not yet confirmed.
PAPER SUBMISSION
Authors can submit their work in the form of a complete paper or an abstract, but please note that accepted abstracts are presented but not published in the proceedings of the conference. Complete papers can be submitted as a Regular Paper, representing completed and validated research, or as a Position Paper, portraying a short report of work in progress or an arguable opinion about an issue discussing ideas, facts, situations, methods, procedures or results of scientific research focused on one of the conference topic areas.
Authors should submit a paper in English, carefully checked for correct grammar and spelling, addressing one or several of the conference areas or topics. Each paper should clearly indicate the nature of its technical/scientific contribution, and the problems, domains or environments to which it is applicable. To facilitate the double-blind paper evaluation method, authors are kindly requested to produce and provide the paper WITHOUT any reference to any of the authors, including the authors’ personal details, the acknowledgments section of the paper and any other reference that may disclose the authors’ identity.
When submitting a complete paper please note that only original papers should be submitted. Authors are advised to read INSTICC's ethical norms regarding plagiarism and self-plagiarism thoroughly before submitting and must make sure that their submissions do not substantially overlap work which has been published elsewhere or simultaneously submitted to a journal or another conference with proceedings. Papers that contain any form of plagiarism will be rejected without reviews.
All papers must be submitted through the online submission platform PRIMORIS and should follow the instructions and templates that can be found under Guidelines and Templates. After the paper submission has been successfully completed, authors will receive an automatic confirmation e-mail.
PUBLICATIONS
All accepted complete papers will be published in the conference proceedings, under an ISBN reference, on paper and on digital support.
SCITEPRESS is a member of CrossRef (http://www.crossref.org/) and every paper on our digital library is given a DOI (Digital Object Identifier).
The proceedings will be submitted for indexation by SCOPUS, Google Scholar, The DBLP Computer Science Bibliography, Semantic Scholar, Microsoft Academic, Engineering Index (EI) and Web of Science / Conference Proceedings Citation Index.
CONFERENCE CHAIR
Available soon.
PROGRAM CHAIR
Carlo Sansone, University of Naples Federico II, Italy
PROGRAM COMMITTEE MEMBERS