An application of residual network and faster - RCNN for Medico: Multimedia task at MediaEval 2018

Hoang, Trung-Hieu; Nguyen, Hai-Dang; Nguyen, Thanh-An; Nguyen, Vinh-Tiep; Tran, Minh-Triet
MEDIAEVAL 2018, MediaEval Benchmarking Initiative for Multimedia Evaluation Workshop, 29-31 October 2018, Sophia-Antipolis, France

The Medico: Multimedia Task focuses on developing an efficient framework for predicting and classifying abnormalities in endoscopic images of gastrointestinal (GI) tract. We present the HCMUS Team's approach, which employs a combination of Residual Neural Network and Faster R - CNN model to classify endoscopic images. We submit multiple runs with different modifications of the parameters in our combined model. Our methods show potential results through experiments.


Type:
Conference
City:
Sophia-Antipolis
Date:
2018-10-19
Department:
Data Science
Eurecom Ref:
5759
Copyright:
CEUR

PERMALINK : https://www.eurecom.fr/publication/5759