1 code implementation • 26 Mar 2024 • Paramita Mirza, Viju Sudhi, Soumya Ranjan Sahoo, Sinchana Ramakanth Bhat
State-of-the-art intent classification (IC) and slot filling (SF) methods often rely on data-intensive deep learning models, limiting their practicality for industry applications.
no code implementations • 13 Nov 2023 • Ken E. Friedl, Abbas Goher Khan, Soumya Ranjan Sahoo, Md Rashad Al Hasan Rony, Jana Germies, Christian Süß
To address these challenges, this paper introduces a set of KPIs tailored for evaluating the performance of in-car ConvQA systems, along with datasets specifically designed for these KPIs.
no code implementations • 12 Jul 2023 • Milind Fernandes, Soumya Ranjan Sahoo, Mangal Kothari
Cooperative localization is an important technique in environments devoid of GPS-based localization, more so in underwater scenarios, where none of the terrestrial localization techniques based on radio frequency or optics are suitable due to severe attenuation.
no code implementations • 23 Apr 2023 • Anamika Tiwari, Abheejeet Mohapatra, Soumya Ranjan Sahoo
A computationally time-efficient, economical, and robust solution is essential for ACOPF with short-term injection uncertainties.
no code implementations • 28 Sep 2022 • Khushboo Mehra, Hassan Soliman, Soumya Ranjan Sahoo
Deep Learning models, in particular, show promising results on image segmentation and classification problems, but they require very large datasets for training.
no code implementations • 1 Oct 2021 • Sarupa Debnath, Soumya Ranjan Sahoo, Benjamin Decardi-Nelson, Jinfeng Liu
In this work, we propose a subsystem decomposition approach and a distributed estimation scheme for a class of implicit two-time-scale nonlinear systems.
1 code implementation • ACCV2018 - Springer 2019 • Ramavtar Malav, Ayoung Kim, Soumya Ranjan Sahoo, Gaurav Pandey
In this paper we propose a novel end-to-end convolution dehazing architecture, called De-Haze and Smoke GAN (DHSGAN).