As we wrap up #NDEAM, I wanted to share another example of an innovation built to empower everyone. Eyes First games are designed for people with mobility and speech disabilities to be able to play games using just their eyes. linkedin.com/feed/update/ur…

First tweet😀. #ICCV19 today 10:30-11:30am at Microsoft booth: I will present our recent progress on large-scale object detection with video demos. We won the fifth place in the 2019 Open Images Object Detection challenge without using any external data. Welcome to our booth!

Stop by the Microsoft booth at #ICCV2019 to demo the HoloLens 2 for yourself. Check out all our upcoming sessions and open roles: aka.ms/AA6fa5m

A playground for audio-video-text understanding and generation — a good way to explore problems in multimodal AI without needing a ton of compute and humungous datasets! Paper, data, code, baselines available mugen-org.github.io

Worried about others using your media for #deepfakes? Be proactive protecting it! Details+code in our #CVPR2022 paper: shorturl.at/oxyWZ Super grateful to my amazing collaborators: Vishal Asnani, Xi Yin, Sijia Liu, and Xiaoming Liu #deepfakedetection

To help advance research on AI that works across video, audio, text & more, we are releasing the MUGEN dataset. ai.facebook.com/blog/introduci… It contains 375K samples w/ annotations designed to train AI on complex multimodal tasks without prohibitively large computing resources.

This week, we released the MUGEN dataset. It contains 375K samples with rich annotations specifically designed to train AI on complex multimodal tasks without requiring prohibitively large computing resources. ai.facebook.com/blog/introduci…

To support diversity, equity and inclusion (DEI) at #ECCV2022, we are offering registration waivers and travel grants for students from communities that do not traditionally attend. Apply before Aug. 7th. eccv2022.ecva.net/attend/diversi…

We’re pleased to introduce Make-A-Video, our latest in #GenerativeAI research! With just a few words, this state-of-the-art AI system generates high-quality videos from text prompts. Have an idea you want to see? Reply w/ your prompt using #MetaAI and we’ll share more results.

[1/5] Always wondered what people see when looking at a Rorschach test? SpaText - our recent #CVPR2023 paper from @MetaAI may give you a sneak peek! TL;DR: We extend text-to-image models with region-specific textual controllability. Project Page: omriavrahami.com/spatext/