Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page

Luís Coelho

dblp:09/3054 · DBLP profile ↗
← Back
2ranked-venue papers
1as first author
2since 2021 · last 2025
—ORCID · conflict

Domains — the database's venue-derived domains; a paper can count in several

Graphics, computer vision, multimedia, augmented reality and games · 1 · 1 since 2021Human-computer interaction and ubiquitous computing · 1 · 1 first-author · 1 since 2021Applied, interdisciplinary, general and emerging computing · 1 · 1 first-author · 1 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Computer graphics and multimedia
1 paper
Image and video coding · 54% Image and video processing · 46%

Topics — the 4 heaviest of 5, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Image and video coding › point cloud compression
learned point cloud compression
0.912025
Deep Learning-Based Point Cloud Coding and Super-Resolution: A Joint Geometry and Color Approach · IEEE Trans. Multim. 2025
Image and video coding
point cloud compression
0.912025
Deep Learning-Based Point Cloud Coding and Super-Resolution: A Joint Geometry and Color Approach · IEEE Trans. Multim. 2025
Image and video processing › super-resolution
point cloud super-resolution
0.912025
Deep Learning-Based Point Cloud Coding and Super-Resolution: A Joint Geometry and Color Approach · IEEE Trans. Multim. 2025
Image and video processing
super-resolution
0.912025
Deep Learning-Based Point Cloud Coding and Super-Resolution: A Joint Geometry and Color Approach · IEEE Trans. Multim. 2025

Methods — techniques the papers use, named apart from their topics

super-resolution · 0.9downsampling · 0.9deep learning · 0.9
YearPublicationVenuePosition
2025 Deep Learning-Based Point Cloud Coding and Super-Resolution: A Joint Geometry and Color Approach
abstract
In this golden age of multimedia, realistic content is in high demand with users seeking more immersive and interactive experiences. As a result, new image modalities for 3D representations have emerged in recent years, among which point clouds have deserved especial attention. Naturally, with this increase in demand, efficient storage and transmission became a must, with standardization groups such as MPEG and JPEG entering the scene, as it happened before with other types of visual media. In a surprising development, JPEG issued a Call for Proposals on point cloud coding targeting exclusively learning-based solutions, in parallel to a similar call for image coding. This is a natural consequence of the growing popularity of deep learning, which due to its excellent performances is currently dominant in the multimedia processing field, including coding. This paper presents the coding solution selected by JPEG as the best-performing response to the Call for Proposals and adopted as the first version of the JPEG Pleno Point Cloud Coding Verification Model, in practice the first step for developing a standard. The proposed solution offers a novel joint geometry and color approach for point cloud coding, in which a single deep learning model processes both geometry and color simultaneously. To maximize the RD performance for a large range of point clouds, the proposed solution uses down-sampling and learning-based super-resolution as pre- and post-processing steps. Compared to the MPEG point cloud coding standards, the proposed coding solution comfortably outperforms G-PCC, for both geometry, color, and joint quality metrics.
André F. R. Guarda, Manuel Ruivo, Luís Coelho, Abdelrahman Seleem, Nuno M. M. Rodrigues, Fernando Pereira 0001
IEEE Trans. Multim.3
2021 Preferences for Teaching Materials: A Survey on a Multimodal World
abstract
In an age of mass teaching, student-teacher contact time is not always enough to ensure an effective teaching-learning process. For the assimilation of concepts it is necessary that, outside the classroom, without the presence and support of the teacher, the student uses materials that allow to remember and eventually complement the learning during the class and simultaneously facilitate and guide, leading to the achievement of the defined objectives. As technology evolves, study materials and support platforms are increasingly diverse and it is important for the teacher to know which means students use and their motivations. A survey was conducted with a group of students from an undergraduate degree in biomedical engineering from a Portuguese higher education institution in order to understand their study habits and the materials they use when out of the classroom. From the analysis of the answers it was possible to infer that the students show preference for studying in a family environment, alone and using as materials the class notes provided by the teachers. Despite the growing use of videos and other multimodal media, the written, personalized notes and orientations set by the teacher are still the most preferred.
Luís Coelho, Sara S. Reis, Fátima G. Coelho
EDUCON1