no code implementations • 15 Jan 2024 • Darshan Singh S, Zeeshan Khan, Makarand Tapaswi
We use the SRL and verb information to create rule-based detailed captions, making sure they capture most of the visual concepts.
no code implementations • 19 Oct 2022 • Zeeshan Khan, C. V. Jawahar, Makarand Tapaswi
Recently, Video Situation Recognition (VidSitu) is framed as a task for structured prediction of multiple events, their relationships, and actions and various verb-role pairs attached to descriptive entities.
no code implementations • 10 Oct 2022 • Zeeshan Khan, Parth Shettiwar, Mukul Khanna, Shanmuganathan Raman
Previous works in high dynamic range (HDR) video reconstruction uses sequence of alternating exposure LDR frames as input, and align the neighbouring frames using optical flow based networks.
1 code implementation • Findings (ACL) 2021 • Zeeshan Khan, Kartheek Akella, Vinay P. Namboodiri, C V Jawahar
We propose a novel adaptation strategy, where we iteratively prune and retrain the redundant parameters of an MNMT to improve bilingual representations while retaining the multilinguality.
no code implementations • ICON 2020 • Kartheek Akella, Sai Himal Allu, Sridhar Suresh Ragupathi, Aman Singhal, Zeeshan Khan, Vinay P. Namboodiri, C V Jawahar
In this paper, we address the task of improving pair-wise machine translation for specific low resource Indian languages.
1 code implementation • 24 Dec 2019 • Zeeshan Khan, Mukul Khanna, Shanmuganathan Raman
High dynamic range (HDR) image generation from a single exposure low dynamic range (LDR) image has been made possible due to the recent advances in Deep Learning.