_-_T_-_

Visual speech recognition (VSR) aims to recognise the content of speech based on the lip movements without relying on the audio stream. Advances in deep learning and the availability of large audio-visual datasets have led to the development of much more accurate and robust VSR models than ever before. However, these advances are usually due to larger training sets rather than the model design. In this work, we demonstrate that designing better models is equally important to using larger training sets. We propose the addition of prediction-based auxiliary tasks to a VSR model and highlight the importance of hyper-parameter optimisation and appropriate data augmentations. We show that such model works for different languages (English, Mandarin, Spanish, French, Portuguese and Italian) and outperforms all previous methods trained on publicly available datasets by a large margin. It even outperforms models that were trained on non-publicly available datasets containing up to to 21 times more data. We show furthermore that using additional training data, even in other languages or with automatically generated transcriptions, results in further improvement.

"Adopt, adapt, invent"

>The system, developed by Apple and Google, transmits a signal from your phone allowing it to swap 'randomised keys' with other phones

>These 'randomised keys' don't include any personal information or location data.

>The app has been endorsed by the Privacy Commissioner, with the Ministry of Health committing to releasing the source code of the app

Pants

The coalition arranged a purchase of the masks in China, which were flown back to Massachusetts Thursday aboard a New England Patriots private plane.

There are several virtual whiteboards to choose from

Are we pretending there is no longer porn on Tumblr?

Cool, TIL - thank you

HN users find circumventing WaPo paywall is child's play

The item you requested cannot be found. The item may have been deleted or you may have entered an incorrect URL.