Get the latest tech news

Weak supervision to isolate sign language communicators in crowded news videos

Blog of the Vrroom

It describes our first steps towards creating a large-scale dataset – isl-500 for training bi-directional translation models between English and Indian Sign Language (ISL). This is pretty impressive considering that OpenAI evaluated their models on datasets that, for one weren’t seen during training but secondly, and more importantly, came from a variety of sources and were made by entirely different groups. While over years, the numbers improve, they themselves aren’t indicative of how these SL Translation systems perform in-the-wild and whether they bring meaningful impact to the lives of the hearing-impaired.

Get the Android app