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
Demo Data from EDBT 2026 / reviewers in the wild / expert

Hector Bernal

dblp:22/8610 · DBLP profile ↗
← Back
2ranked-venue papers
1as first author
0since 2021 · last 2010
—ORCID · none

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

Artificial intelligence and machine learning · 2 · 1 first-authorGraphics, computer vision, multimedia, augmented reality and games · 1

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.

Artificial intelligence
1 paper
Image recognition and object detection · 87% Transfer learning and domain adaptation · 13%

Topics — the 2 heaviest of 3, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Computer vision › Image recognition and object detection
image classification		 0.112010
Semantic Label Sharing for Learning with Many Categories · ECCV (1) 2010
Computer vision › Image recognition and object detection › image classification
many-class classification		 0.112010
Semantic Label Sharing for Learning with Many Categories · ECCV (1) 2010

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

label sharing · 0.1
YearPublicationVenuePosition
2010 Semantic Label Sharing for Learning with Many Categories
Rob Fergus, Hector Bernal, Yair Weiss, Antonio Torralba 0001
 ECCV (1)2
2008 A comparative study between two algorithms for computing the generalized centroid of an interval type-2 fuzzy set
abstract
this paper presents a comparative study between two iterative algorithms for computing the generalized centroid of an interval type-2 fuzzy set. The first procedure is the so called Enhanced Karnik-Mendel (EKM) algorithm. The latter, introduced here as a Recursive Algorithm with Unique Loop (RAUL), is a modification of a previously reported procedure. The study compares the computing time of both algorithms for three prototype Footprints of Uncertainty and several discretizations of the universe of discourse. Results point out that RAUL is faster than the EKM algorithm when less than 100 discretization points are used to describe the footprint of uncertainty.
Hector Bernal, L. Karina Duran, Miguel A. Melgarejo
 FUZZ-IEEE1