Interested in Language Grounding in Videos but don't know where to start? 🤷‍♂️ Well, start from a comprehensive and well-curated list of papers: github.com/Soldelli/Aweso… Pro: - Link to available code - Link to the text of all papers #computervision #papers_roadmap

Attending #CVPR2022 #CVPR2026 ? under this thread , we share summaries of the 7 papers from our KAUST Computer Vision Lab (IVUL) . 1/n

Michael Bronstein Yi Ma IMO part of the problem is that current review systems don't scale well or offer good incentives Just shared PeerXiv, our vision for how reviewing could look like. Hoping to shape it together with the community and would appreciate your feedback 😊 x.com/EladRichardson…

#popular opinion. #CVPR2026 European Conference on Computer Vision #ECCV2026 British Machine Vision Conference (BMVC) ACCV let's ban reviewers writing ➡️ "There is NO novelty" IMHO it's like using the N word. Reviewers who use that statement without 300 words of lengthy arguments should be blacklisted. #ComputerVision #MachineLearning #AI 1/2

Our CVPR 22 (Oral) paper presents a novel benchmark, which measures catastrophic forgetting of DNNs that continuously learn to recognize diverse actions in videos. Come see us on Friday, June 24 at #CVPR2022! 1. Oral session 4.2.3 (13:30) 2. Poster #1348 (14:30-17:00) 1/6

Excited to share that we are organizing a tutorial on Graph Machine Learning for Visual Computing on 6/20 PM this #CVPR2025. We have amazing speakers taking about Geometric DL, PyG and Graph ML applications in Videos, 3D, physical reasoning and Robotics! Don’t miss it! CVPR News

Pleasure today to host 3 KAUST Computer Vision Lab (IVUL) members visiting us @BristolUniEng : Humam, Mattia and Frost. We had a 3-in-1 talk on their fantastic efforts to achieve multi-modal learning, TAL and new MAD dataset of movies. Thanks for visiting us... Hope we can host Bernard Ghanem soon!

Big congrats for Kevin Lin who pulled a stunt a got a great paper accepted to #NeurIPS2022. EgoVLP opens the race to the best video and language pretraining scheme in egocentric data. Let’s see how the community will answer! 🔥

😥 Why are leaders behaving so irrationally when it's time to go back to enjoy the taste of life again after a sour & dark #COVID19 pandemia? It's all across the glove 🌐 . 🕯️ Let's #pray for our brothers ✊🏼

The countdown started! In less than 24 hours Creative Visual Generation Editing Understanding will take place as the first workshop European Conference on Computer Vision #ECCV2026. It will be one week before all the other workshops and will happen fully virtually. Every ECCV attendee is welcome to join! #ECCV2022 #CVEU

Visit us in our booth number 415 NeurIPS Conference KAUST @cemseKAUST #Artificial_Intelligence #NeurIPS2022 #KAUST

Comments compilation from reviewer 2. 🧵 #AcademicTwitter

My lab is looking to hire several postdoc researchers to work on high-impact AI4Science applications relevant to the challenges facing our world, from greener energy to material discovery for CO2 capture. More details here: bernardghanem.com/openings

I am still interviewing postdoc candidates for these openings that should start ASAP. There is still time for those interested to apply. Spread the word! Lots of exciting projects cooking at Artificial Intelligence @ KAUST KAUST in core #AI and #ai4science 💪💪💪

Exciting news! Our research group at KAUST is making waves at #ICCV 2023. We're thrilled to announce that NINE of our papers have been accepted. Congratulations to all the authors and our amazing collaborators!

We are thrilled to announce the 3rd "Rising Stars in AI" at KAUST! Apply to be a speaker: Inspire our global audience with your groundbreaking research! All expenses are covered for selected speakers. Deadline: Nov 30, 2023 cemse.kaust.edu.sa/ai/aii-symp-20… @cemseKAUST

Very exciting news!! Our most recent paper is out! We train a llama model on a folder with jpeg files. 🦙➡️📂 We found very exciting potential when doing this! If you are interested see the thread, and check our paper!

Ever noticed how one scene seamlessly transitions into another in films? That’s a match-cut—a subtle yet powerful cinematic trick. Our MatchDiffusion, generates two videos from text prompts, designed to form a seamless match-cut—effortlessly and training-free. 🎥✨ 1/n

🎓 Just defended my PhD in Electrical and Computer Engineering at KAUST! My thesis, Scalable and Efficient Semantic Video Search, explores deep learning methods for efficient video understanding. Ready to turn research into impact beyond academia. #PhDDefense #KAUST