Moacir A. Ponti

Main Research fields: Machine Learning/Representation Learning; Signal, Image and Video Processing

In search for fair and explainable ways to apply machine learning and computer vision to improve people's life.

Recent/highlighted papers (see Publication for more details):

• Sketchformer: Transformer-based representation for sketched structure. (CVPR 2020)

• Learning image features with fewer labels using a semi-supervised deep convolutional network. (Neural Networks 2020).

• Combining clustering and active learning for the detection and learning of new image classes. (Neurocomputing 2019)

• Sketching out the Details: Sketch-based Image Retrieval using Convolutional Neural Networks with Multi-stage Regression (Computers and Graphics 2018)

• Everything you wanted to know about Deep Learning for Computer Vision but were afraid to ask (SIBGRAPI Tutorials 2017: papers, slides, code)

• A Decision Cognizant Kullback-Leibler Divergence (Pattern Recognition 2017)

Check out my Book on Machine Learning (Theory and Practice), details below!

I am recipient of a Google Latin America Research Award (2017-2018).

At USP I have 10 years experience in teaching, as a principal investigator of many research projects and grants, and leadership, by chairing a Science Outreach committee, bridging the gap between acacemia, individuals, organizations and industry.

Previous experiences/education:
Academic visitor (2016-2017); Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK.
PhD (2008) and MSc (2004) at the Universidade Federal de São Carlos (UFSCar), Brazil.
PhD internship (2007) at IEETA, Universidade de Aveiro, Portugal.

CV: Lattes Platform CV (in Portuguese) -- 4-page CV in English [pdf]