3 papers
cs.CV2026
Diagnosis-Conditioned Spatial Gating and Decoder-Level Supervised Contrastive Learning for Radiology Report Generation
Md Mustafizur Rahman, Mylene C. Q. Farias
Radiology report generation models can produce fluent text while still containing finding-level inaccuracies. Diagnosis-driven methods improve generation by conditioning on predict…
cs.CV2025
Deep Hybrid Model for Region of Interest Detection in Omnidirectional Videos
Sana Alamgeer, Mylene Farias, Marcelo Carvalho
The main goal of the project is to design a new model that predicts regions of interest in 360 videos. The region of interest (ROI) plays an important role in 360$^{\circ…
eess.IV2024
Additional Tests for TV 3.0
Eduardo Peixoto, Pedro Garcia Freitas, Mylene Christine Queiroz Farias +3
In 2023 we have conducted extensive experiments on subjective video quality for the TV 3.0 project at University of Brasília. A full report on these tests is available at the Fórum…