no code implementations • IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024 • Sourabh Vasant Gothe, Vibhav Agarwal, Sourav Ghosh, Jayesh Rajkumar Vachhani, Pranay Kashyap, Barath Raj Kandur Raja
This inquiry drives us to algorithmically harness motion cues for identifying generic event boundaries in videos.
Ranked #1 on Generic Event Boundary Detection on TAPOS
no code implementations • IEEE/ACM Transactions on Audio, Speech, and Language Processing 2024 • Vibhav Agarwal, Sourav Ghosh, Harichandana BSS, Himanshu Arora, Barath Raj Kandur Raja
Data-to-text (D2T) generation is a crucial task in many natural language understanding (NLU) applications and forms the foundation of task-oriented dialog systems.
Ranked #3 on Data-to-Text Generation on E2E NLG Challenge
no code implementations • 26 Apr 2023 • Shuvadeep Masanta, Ramyashree Pramanik, Sourav Ghosh, Tanmay Bhattacharya
In this paper, we have proposed a three-phase system that can guide emergency vehicles and manage traffic based on the degree of congestion.
no code implementations • 11 Jul 2022 • Harshvardhan Anand, Nansi Begam, Richa Verma, Sourav Ghosh, Harichandana B. S. S, Sumit Kumar
In this work, we aim to introduce a lightweight intelligent preprocessor (LIP) that can enhance the readability of a message before being passed downstream to existing TTS systems.
no code implementations • 5 Feb 2022 • Harichandana B S S, Vibhav Agarwal, Sourav Ghosh, Gopi Ramena, Sumit Kumar, Barath Raj Kandur Raja
This motivates us to work towards a solution to generate privacy-conscious cues for raising awareness in smartphone users of any sensitivity in their viewfinder content.
no code implementations • 6 Oct 2021 • Vibhav Agarwal, Sudeep Deepak Shivnikar, Sourav Ghosh, Himanshu Arora, Yashwant Saini
To build high-quality real-world conversational solutions for edge devices, there is a need for deploying intent detection model on device.
Ranked #1 on Intent Detection on SNIPS (model size metric)
no code implementations • 7 Jan 2021 • Sourabh Vasant Gothe, Sourav Ghosh, Sharmila Mani, Guggilla Bhanodai, Ankur Agarwal, Chandramouli Sanchi
This model outperforms fastText by 60. 39% and ML-Kit by 23. 67% in F1 score for European languages.
no code implementations • 7 Jan 2021 • Sharmila Mani, Sourabh Vasant Gothe, Sourav Ghosh, Ajay Kumar Mishra, Prakhar Kulshreshtha, Bhargavi M, Muthu Kumaran
The LM loading time on mobile is linear with respect to model size.
no code implementations • 5 Jan 2021 • Sourav Ghosh, Sourabh Vasant Gothe, Chandramouli Sanchi, Barath Raj Kandur Raja
To this end, we propose a disambiguation algorithm and showcase its usefulness in two novel mutually non-exclusive input methods for languages natively using the abugida writing system: (a) disambiguation of ambiguous input for abugida scripts, and (b) disambiguation of word variants in romanized scripts.
no code implementations • ICON 2020 • Vibhav Agarwal, Sourav Ghosh, Kranti Chalamalasetti, Bharath Challa, Sonal Kumari, Harshavardhana, Barath Raj Kandur Raja
To the best of our knowledge, this work presents the first lightweight deep learning approach for smartphone deployment of emphasis selection.
no code implementations • 15 Dec 2020 • Sonal Kumari, Vibhav Agarwal, Bharath Challa, Kranti Chalamalasetti, Sourav Ghosh, Harshavardhana, Barath Raj Kandur Raja
The proposed LiteMuL not only outperforms the current state of the art results but also surpasses the results of our proposed on-device task-specific models, with accuracy gains of up to 11% and model-size reduction by 50%-56%.