1 code implementation • 21 Nov 2022 • Arindam Ghosh, Thomas Schaaf, Matthew R. Gormley
In this paper, we propose a calibration-aware adaptive focal loss called AdaFocal that utilizes the calibration properties of focal (and inverse-focal) loss and adaptively modifies $\gamma_t$ for different groups of samples based on $\gamma_{t-1}$ from the previous step and the knowledge of model's under/over-confidence on the validation set.
no code implementations • 6 Jul 2022 • Arindam Ghosh, Mark Fuhs, Deblin Bagchi, Bahman Farahani, Monika Woszczyna
As virtual assistants have become more diverse and specialized, so has the demand for application or brand-specific wake words.
1 code implementation • Findings (EMNLP) 2021 • Longxiang Zhang, Renato Negrinho, Arindam Ghosh, Vasudevan Jagannathan, Hamid Reza Hassanzadeh, Thomas Schaaf, Matthew R. Gormley
We show that fluent and adequate summaries can be generated with limited training data by fine-tuning BART on a specially constructed dataset.
no code implementations • 31 Mar 2020 • Sandip Mondal1, Tathagata Paul, Arindam Ghosh, V. Venkataraman
Gate controllable electronic trap detection method has been demonstrated by regulating the gate potential of MIS devices.
Applied Physics Materials Science
no code implementations • 10 Nov 2017 • Evgeny Stepanov, Stephane Lathuiliere, Shammur Absar Chowdhury, Arindam Ghosh, Radu-Laurentiu Vieriu, Nicu Sebe, Giuseppe Riccardi
In this AVEC challenge we explore different modalities (speech, language and visual features extracted from face) to design and develop automatic methods for the detection of depression.
no code implementations • WS 2016 • Firoj Alam, Fabio Celli, Evgeny A. Stepanov, Arindam Ghosh, Giuseppe Riccardi
In this paper, we address the issue of automatic prediction of readers{'} mood from newspaper articles and comments.