With the emergence of huge amounts of heterogeneous multi-modal data, including images, videos, texts/languages, audios, and multi-sensor data, deep learning-based methods have shown promising ...

A new brain decoding method called mind captioning can generate accurate text descriptions of what a person is seeing or recalling—without relying on the brain's language system.

The human visual system provides us with a rich and meaningful percept of the world, transforming retinal signals into visuo-semantic representations. For a model of these representations, here we ...

The excitement was palpable in an online class. A group of 35 students of Choithram School in Indore waited for their new teachers — the artist couple Manish V Ratnaparakhe and wife Gargi — to ...

After completing a BSc in Computer Science, I had developed an interest in AI and wanted to take it further. My AI journey began with an internship at The Hartree Centre, where I researched speech ...