M
Manuel J. Marín-Jiménez
Researcher at University of Córdoba (Spain)
Publications - 86
Citations - 5250
Manuel J. Marín-Jiménez is an academic researcher from University of Córdoba (Spain). The author has contributed to research in topics: Gait (human) & Pose. The author has an hindex of 22, co-authored 77 publications receiving 3832 citations. Previous affiliations of Manuel J. Marín-Jiménez include Cordoba University & University of Granada.
Papers
More filters
Journal ArticleDOI
Automatic generation and detection of highly reliable fiducial markers under occlusion
TL;DR: A fiducial marker system specially appropriated for camera pose estimation in applications such as augmented reality and robot localization is presented and an algorithm for generating configurable marker dictionaries following a criterion to maximize the inter-marker distance and the number of bit transitions is proposed.
Proceedings ArticleDOI
Progressive search space reduction for human pose estimation
TL;DR: An approach that progressively reduces the search space for body parts, to greatly improve the chances that pose estimation will succeed, and an integrated spatio- temporal model covering multiple frames to refine pose estimates from individual frames, with inference using belief propagation.
Book ChapterDOI
End-to-End Incremental Learning
TL;DR: In this article, a loss composed of a distillation measure to retain the knowledge acquired from the old classes and a cross-entropy loss to learn the new classes is proposed.
Posted Content
End-to-End Incremental Learning
TL;DR: This work proposes an approach to learn deep neural networks incrementally, using new data and only a small exemplar set corresponding to samples from the old classes, based on a loss composed of a distillation measure to retain the knowledge acquired from theold classes, and a cross-entropy loss to learn the new classes.
Journal ArticleDOI
2D Articulated Human Pose Estimation and Retrieval in (Almost) Unconstrained Still Images
TL;DR: This work proposes and proposes and evaluates techniques for searching a video dataset for people in a specific pose, and develops three new pose descriptors and compares their classification and retrieval performance to two baselines built on state-of-the-art object detection models.