Rogério Feris — accepted AI-conference papers

2023

C2KD: Cross-Lingual Cross-Modal Knowledge Distillation for Multilingual Text-Video Retrieval

Andrew Rouditchenko, Yung-Sung Chuang, Nina Shvetsova, Samuel Thomas, Rogério Feris, Brian Kingsbury +4

ICASSP 2023accepted

Multilingual text-video retrieval methods have improved significantly in recent years, but the performance for languages other than English still lags. We propose a Cross-Lingual Cross-Modal Knowledge Distillation method to improve multilingual text-video retrieval. Inspired by the fact that English…

Cited by 0 Source ↗Scholar ↗

2022

A Maximal Correlation Approach to Imposing Fairness in Machine Learning

Joshua K. Lee, Yuheng Bu, Prasanna Sattigeri, Rameswar Panda, Gregory W. Wornell, Leonid Karlinsky +1

ICASSP 2022accepted

As machine learning algorithms grow in popularity and diversify to many industries, ethical and legal concerns regarding their fairness have become increasingly relevant. We explore the problem of algorithmic fairness, taking an information-theoretic view. The maximal correlation framework is introd…

Cited by 0 Source ↗Scholar ↗