R
Renato Martins
Researcher at French Institute for Research in Computer Science and Automation
Publications - 27
Citations - 188
Renato Martins is an academic researcher from French Institute for Research in Computer Science and Automation. The author has contributed to research in topics: Computer science & Graph (abstract data type). The author has an hindex of 5, co-authored 22 publications receiving 95 citations. Previous affiliations of Renato Martins include PSL Research University & University of Burgundy.
Papers
More filters
Proceedings ArticleDOI
A New Metric for Evaluating Semantic Segmentation: Leveraging Global and Contour Accuracy
TL;DR: In this article, a new metric is proposed to leverage global and contour accuracy in a simple formulation, which is validated with the evaluation of several semantic segmentation solutions that exploit RGB-D images to rank these solutions taking into account the quality of the segmented contours.
Journal ArticleDOI
Learning to dance: A graph convolutional adversarial network to generate realistic dance motions from audio
João Pedro Moreira Ferreira,Thiago M. Coutinho,Thiago L. Gomes,Thiago L. Gomes,José Fernandes Bezerra Neto,Rafael Alves de Azevedo,Renato Martins,Erickson R. Nascimento +7 more
TL;DR: A novel method based on graph convolutional networks to tackle the problem of automatic dance generation from audio information using an adversarial learning scheme conditioned on the input music audios to create natural motions preserving the key movements of different music styles.
A new metric for evaluating semantic segmentation: leveraging global and contour accuracy
TL;DR: In this paper, the authors proposed a new metric which accounts for both global and contour accuracy in a simple formulation to overcome the weaknesses of previous metrics, and presented a comparative analysis of several commonly used metrics for semantic segmentation together with a statistical analysis of their correlation.
Journal ArticleDOI
A Shape-Aware Retargeting Approach to Transfer Human Motion and Appearance in Monocular Videos
Thiago L. Gomes,Renato Martins,João Pedro Moreira Ferreira,Rafael Alves de Azevedo,Guilherme Torres,Erickson R. Nascimento +5 more
TL;DR: This work proposes a shape-aware approach based on a hybrid image-based rendering technique that exhibits competitive visual retargeting quality compared to state-of-the-art neural rendering approaches and presents a new video retargeted benchmark dataset to evaluate the task of synthesizing people’s videos.
Proceedings ArticleDOI
Semantic Map Augmentation for Robot Navigation: A Learning Approach Based on Visual and Depth Data
TL;DR: A CNN-based object detector and a 3D model-based segmentation technique are used to localize and identify different classes of objects in the scene and the output is a map of the environment extended with semantic object classes and their positioning.