Video captioning: can neural networks describe a video?
AI/Machine Learning • March 2021
Video captioning: can neural networks describe a video?
About
Video captioning: can neural networks describe a video?
About

Parlare di video captioning significa inserirsi in un dibattito ancora aperto nell’ambito dell’Intelligenza Artificiale, che ha come obiettivo la creazione di un sistema capace di interpretare un video e generare una descrizione di quanto viene mostrato attraverso il linguaggio naturale. Le applicazioni di tale campo sono diverse: si passa dall’assistenza agli ipovedenti al perfezionamento dei robot chirurgici fino ai sistemi di video sorveglianza. In questo talk verranno esposte le tecniche dello stato dell’arte e le tematiche legate alla computer vision e al NLP.

Language
Italian
Level
Intermediate
Length
38 minutes
Type
online conference
About the speaker
About the speaker
Silvio Olivastri
Senior Data ScientistBPER Banca
Silvio is a Senior Data Scientist at BPER Banca, specialised in deep learning applied to computer vision and natural language processing applications. Artificial intelligence enthusiast, with 4+ years of experience in intelligent system prototyping in different scenarios such as industrial automation, entertainment, research and banking. He has a Master Degree in Computer Engineering and a patent with Datalogic. He worked at Musixmatch, AI Labs, and collaborated with Oxford Brookes University with which he published a study on Video Captioning.
Details
Language
Italian
Level
Intermediate
Length
38 minutes
Type
online conference