Aligning Actions and Walking to LLM-Generated Textual Descriptions

1 code implementation • 18 Apr 2024 • Radu Chivereanu, Adrian Cosma, Andy Catruna, Razvan Rughinis, Emilian Radoi

For action recognition, we employ LLMs to generate textual descriptions of actions in the BABEL-60 dataset, facilitating the alignment of motion sequences with linguistic representations.

Action Recognition Data Augmentation +1

Patterns of protection, infection, and detection: Country-level effectiveness of COVID 19 vaccination in reducing mortality worldwide

no code implementations • 8 Jul 2022 • Cosima Rughinis, Mihai Dima, Simona-Nicoleta Vulpe, Razvan Rughinis, Sorina Vasile

As suggested by previous estimates at country level, a strong, significant, negative relationship between cumulative mortality and vaccination was highlighted through segmentation analysis for countries positioned at the higher end of the social development spectrum.