minicurso_deep_learning_para_multimidia

Material do minicurso "Desenvolvendo Modelos de Deep Learning para Aplicações Multimídia no Tensorflow", apresentado no Webmedia2018. O capítulo de livro esta disponível na SBC Open Library.

Conteúdo

1. Introdução a redes neurais profundas
2. Redes neurais convolucionais para classificação de imagens
3. Reconhecimento facial com o modelo FaceNet
4. Detecção de objetos com o modelo YOLO
5. Classificação de multi-etiquetas de vídeo no dataset Youtube8M

bibtex

@article{santos_metodos_2019,
	title = {Métodos baseados em Deep Learning para Análise de Vídeo},
	rights = {\#\#submission.{copyrightStatement}\#\#},
	url = {https://sol.sbc.org.br/livros/index.php/sbc/catalog/view/32/127/307-1},
	abstract = {Methods based on Deep Learning became state-of-the-art in several multimedia chal-lenges. However, there is a gap of professionals to perform Deep Learning in the industry. This chapter focuses on presenting the fundamentals and technologies for developing such {DL} methods for video analyses.  In particular, we seek to enable the reader to:  (1) understand key {DL}-based models, more specifically Convolutional Neural Networks ({CNN}); (2) apply {DL} models to solve video tasks such as video classification, multi-label video classification, object detection, and pose estimation. The Python programming language is presented in conjunction with the {TensorFlow} library for implementing {DL} models},
	journaltitle = {Sociedade Brasileira de Computação},
	author = {Santos, Gabriel N. P. dos and Freitas, Pedro V. A. de and Busson, Antonio José G. and Guedes, Álan L. V. and Colcher, Sérgio and Milidiú, Ruy L.},
	urldate = {2020-04-27},
	date = {2019-10-11},
	langid = {portuguese}
}