Chandrashekhar Lavania

Jul 31, 2024 | amazon.science | Lucas Brandão Gonçalves |Prashant Mathur |Chandrashekhar Lavania |Metehan Cekic

Recent advancements in audio-visual generative modeling have been propelled by progress in deep learning and the availability of data-rich benchmarks. However, the growth is not attributed solely to models and benchmarks. Universally accepted evaluation metrics also play an important role in advancing the field.

Jul 29, 2024 | amazon.science | Lucas Brandão Gonçalves |Prashant Mathur |Chandrashekhar Lavania |Metehan Cekic

Recent advancements in audio-visual generative modeling have been propelled by progress in deep learning and the availability of data-rich benchmarks. However, the growth is not attributed solely to models and benchmarks. Universally accepted evaluation metrics also play an important role in advancing the field.

Jul 19, 2024 | amazon.science | Chandrashekhar Lavania |Prashant Mathur |Kyu S. Han |Georgios Chochlakis

Audio-visual representations leverage information from both modalities to produce joint representations. Such representations have demonstrated their usefulness in a variety of tasks. However, both modalities incorporated in the learned model might not necessarily be present all the time during inference. In this work, we study whether and how we can make exist- ing models, trained under pristine conditions, robust to partial modality loss without retraining them.

Apr 10, 2024 | arxiv.org | Prashant Mathur |Chandrashekhar Lavania |Marcello Federico |Metehan Cekic