CfP for the workshop on Advances in Language and Vision Research (ALVR) at #ACL2020! We're excited for papers exploring active perception, real language, and photo-realistic simulation (or even real world) action spaces. Submission deadline April 6. alvr-workshop.github.io

Even the best multimodal algorithms today struggle to read and reason about text in natural images. To advance text-based Image Captioning and VQA, we are hosting two challenges: textvqa.org/challenge and textvqa.org/textcaps/chall…. Enter by 5/15!

I try to avoid politics on my academic Twitter but this time I will make an exception. I stand in solidarity with #BlackLivesMatter to fight racism. I have a selfish reason: if Asians and Latinos are not supporting the blacks, racism will come to every one of us (it did already).

I thought I could focus on my thesis writing during the final months of my PhD, but I instead become more and more stressed out. International students are not to be blamed for the increasing unemployment rate under this apocalypse. Please support. #OPTforUandMe

MMF is a modular framework for vision & language multimodal research. This tutorial walks through how to use a pretrained model or build a custom model with MMF to participate in the Hateful Memes Challenge. bit.ly/a-multimodal-f…

We are organizing the 𝟐𝐧𝐝 𝐖𝐨𝐫𝐤𝐬𝐡𝐨𝐩 𝐨𝐧 𝐀𝐝𝐯𝐚𝐧𝐜𝐞𝐬 𝐢𝐧 𝐋𝐚𝐧𝐠𝐮𝐚𝐠𝐞 𝐚𝐧𝐝 𝐕𝐢𝐬𝐢𝐨𝐧 𝐑𝐞𝐬𝐞𝐚𝐫𝐜𝐡 (𝐀𝐋𝐕𝐑 𝟐𝟎𝟐𝟏) and have a Stella list of confirmed speakers: alvr-workshop.github.io. Vote if you are interested!

So much relief all around. So much hope. So much positivity. It's been a while :) It's crazy how inspiring just basic decency and coherence in thought feels...

Excited to share Worldsheet, a method to synthesize novel views with large camera changes from a *single* image. Turns out, simply shrink-wrapping a mesh sheet onto the image captures 3D well enough to render photorealistic far-away views. w/ Ronghang Hu worldsheet.github.io

Facebook AI Research is looking for Research Engineers to join our Embodied AI team in Menlo Park. More about what we do in the thread below. If this sounds exciting, DM me or apply here: facebook.com/careers/v2/job… 1/6

The @NAACLHLT ALVR 2021 workshop is happening tomorrow (June 11th) at 8:30am PDT!!! We have an amazing lineup of speakers to talk about recent advances in language and vision research! Talk information also provided in the program. alvr-workshop.github.io

We are presenting Worldsheet at #ICCV2021 this week as Oral. Join QnA Wed & Fri. We updated the arXiv since v1: *Multi-layered* Worldsheets to autonomously handle sharp depth discontinuities/occlusions which a single sheet may fail to capture (Sec 3.5): worldsheet.github.io/resources/worl…

Today, we’re sharing a roundup of Meta AI’s recent cutting-edge multimodal research, which we believe will collectively lead to more interactive, immersive, and smarter AI systems of the future: ai.facebook.com/blog/advances-…

We are excited to release SAM 2, to segment anything in images and videos Check out the code at github.com/facebookresear… and demo at sam2.metademolab.com

Quite a cool demo of Segment Anything 2 (even if Mbappe shoots the ball too fast for it! ;) ) sam2.metademolab.com/demo

🚀 Excited to announce new SAM 2.1 model checkpoints & the SAM 2 Developer Suite: 🤖 We’re releasing full training/fine tuning code for SAM 2 so you can customize it for your use case. 💻For the first time we’re publishing the frontend & backend code for our SAM 2 web demo!