Feeling thankful to be selected as an Outstanding Reviewer for ICCV 2025. ☺️
Honored to be part of such a talented and inspiring research community.
https://t.co/gff8OPiFOd
🎓PhD defense!
🎉Huge congratulations to @MereyRamazanova from the IVUL family on successfully defending her PhD thesis, “Towards Robust Multimodal Egocentric Video Understanding”, advised by Prof. @BernardSGhanem
Wishing you all the best in your next chapter, Dr. Merey!🚀
🚀 Our MatchDiffusion was accepted to ICCV 2025 in Hawaii! 🌺
We generate two synchronized videos from text prompts—designed for match-cuts.
Results: https://t.co/xD00qpxNW0
Paper: https://t.co/w3MxDrFZXU
#MatchDiffusion#ICCV2025#DiffusionModels#TextToVideo#GenerativeAI
🎉Thrilled to share that our paper, "Test-Time Adaptation for Combating Missing Modalities in Egocentric Videos", has been accepted to #ICLR2025!
Grateful to my amazing collaborators @PardoAlejo@BernardSGhanem@MotassimF
📜Paper: https://t.co/HboGwSf7dZ
🌏See you in Singapore!
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
📢 Open Call: Fully funded #PhD student positions starting in 2025 at IVUL @KAUSTVision Lab with Prof. @BernardSGhanem
If you are passionate about computer vision and machine learning, contact us now and apply to #JoinOurTeam.
🔗 Our lab: https://t.co/5OgVVYOLJa
Can a language model understand JPEGs 💾? We trained ours 🦙 on raw byte streams, and it learned to speak JPEG-ese! We find the model's can understand file properties, fix anomalies, and generate new JPEGs 🖼️, all while bypassing the decompression step 🚀.
A thread 🧵
Exciting news! Our latest paper on multimodal egocentric recognition, tackling the challenge of missing modalities, is now available on ArXiv! Discover our simple yet effective approach to overcome these obstacles during both training and testing phases. Check it out! 📄🔍 (1/4)
Today, we announce Ego-Exo4D, the largest and most diverse multi-view dataset, showing human experts around the world performing a core set of skilled activities, w/ unprecedented multi-modality, novel new video-language resources, and rich annotations
The countdown started! In less than 24 hours @cveu_workshop will take place as the first workshop @eccvconf. It will be one week before all the other workshops and will happen fully virtually. Every ECCV attendee is welcome to join! #ECCV2022#CVEU
Thread:
1/. As the death toll rises to 41 today, four women you should know who were deliberately and unlawfully killed in Iran when protesting gender apartheid and the killing of #Masha_Amini:
Hadis Najafi, aged 20, shot six times when security forces opened fire on her.
Pleasure today to host 3 @KaustVision 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 @BernardSGhanem soon!
Excited to share that our paper MovieCuts was accepted to #ECCV2022@eccvconf.
The very same day I passed my Ph.D. Proposal Defense.
I'm officially a Ph.D. candidate! What a day!
Stay tuned for the camera-ready version of MovieCuts.
Kudos to the rest of the authors.
My husband reading with 6 yo and explaining “Miss, Mrs, Ms”: “Isn’t it wild that we created all these different words to tell the world whether or not a woman is married, but not for a man?”