←
Video & Image Sense Lab (VIS Lab)54 posts
Video & Image Sense Lab (VIS Lab) avatar

Video & Image Sense Lab (VIS Lab)

@VISLab_UvA

Computer Vision research group at @UvA_Amsterdam directed by Cees Snoek (@cgmsnoek)

◷ Joined May 2024
Pascal Mettes avatar
⟳ Video & Image Sense Lab (VIS Lab) retweeted
Pascal Mettes@PascalMettes·18 Oct 2024

All vision-language models should have hyperbolic embeddings. Vision and language are incredibly hierarchical in nature! See below our latest work on hyperbolic vision-language models that exploit visual compositions through entailment:

(1/6)🥳 Excited to share my latest research done as part of my MSc AI thesis! We introduced Hyperbolic Compositional CLIP (HyCoCLIP)—a novel framework that leverages the hierarchical nature of hyperbolic space for learning vision-language representations using scene compositions.

Aritra Bhowmik avatar
⟳ Video & Image Sense Lab (VIS Lab) retweeted
Aritra Bhowmik@AritraBhowmik6·21 Oct 2024

🚀 Excited to share LynX! 🦁 🔑 A new method in visual grounding using a Dual Mixture of Experts—LynX enables pretrained VLMs to continuously learn grounding while retaining their image-language capabilities. 📄 Check out the full paper: arxiv.org/pdf/2410.10491

Michael Dorkenwald avatar
⟳ Video & Image Sense Lab (VIS Lab) retweeted
Michael Dorkenwald@mdorkenw·15 Oct 2024

📢 Announcing TVBench: Temporal Video-Language Benchmark 📺 We reveal that widely used Video-Language benchmarks, such as MVBench, fall short in testing temporal understanding and propose an alternative TVBench: huggingface.co/datasets/FunA…

Yuki@y_m_asano15 Oct 2024

Today, we're introducing TVBench! 📹💬 Video-language evaluation is crucial, but are we doing it right? We find that current benchmarks fall short in testing temporal understanding. 🧵👇

1:27
Yuki avatar
⟳ Video & Image Sense Lab (VIS Lab) retweeted
Yuki@y_m_asano·15 Oct 2024

Today, we're introducing TVBench! 📹💬 Video-language evaluation is crucial, but are we doing it right? We find that current benchmarks fall short in testing temporal understanding. 🧵👇

1:27
Yuki avatar
⟳ Video & Image Sense Lab (VIS Lab) retweeted
Yuki@y_m_asano·7 Oct 2024

Excited to announce that today I'm starting my new position at @utn_nuremberg as a full Professor 🎉. I thank everyone who has helped me to get to this point, you're all the best! Our lab is called FunAI Lab, where we strive to put the fun into fundamental research. 😎 Let's go!

FunAI@FunAILab7 Oct 2024

Hello world! fundamentalailab.github.io/

Post attachment
David M. Knigge avatar
⟳ Video & Image Sense Lab (VIS Lab) retweeted
David M. Knigge@davidmknigge·8 Oct 2024

🇨🇦 Deeeelighted to share that this work got into #neurips2024. Many thanks to my dear friend and co-author @Dafidofff, as well as the rest of the team. Solving PDEs in continuous space-time with Neural Fields on cool geometries while respecting their inherent symmetries! 💫💫

🌀 Equivariant Neural Fields (ENFs) for continuous PDE solving! We use ENFs as representation for solving PDEs in continuous space/time on different geometries while respecting their symmetries! (such as this internally heated ball of fluid) More details 👇

Michael Dorkenwald avatar
⟳ Video & Image Sense Lab (VIS Lab) retweeted
Michael Dorkenwald@mdorkenw·9 Oct 2024

The Self-Supervised Learning: What is Next? workshop at @eccvconf had a great turnout with excellent talks. Slides of most talks are available at sslwin.org (soon all 🤞). Thanks to all attendees, speakers, and co-organizers for making it a fantastic event!

Post attachmentPost attachmentPost attachmentPost attachment

Interested in learning about the future of self-supervised learning? Don’t miss our workshop this Sunday at @eccvconf with an incredible lineup of speakers! 🔥 @imisra_ @oriane_simeoni @endernewton @olivierhenaff @y_m_asano @YutongBAI1002 More details at sslwin.org

Post attachment
Sarah Rastegar avatar
⟳ Video & Image Sense Lab (VIS Lab) retweeted
Sarah Rastegar@rastegar_sarah·4 Oct 2024

Stop by today and discuss our @eccvconf paper (SelEx) with me, @doughty_hazel, and @cgmsnoek! 🎉 We present self-expertise—an alternative to self-supervision for learning from unlabelled data with fine-grained distinctions and unknown categories. 📍 Poster #89 🕥 10:30 AM

Mohammad Reza Salehi avatar
⟳ Video & Image Sense Lab (VIS Lab) retweeted
Mohammad Reza Salehi@MrzSalehi·1 Oct 2024

🚀 Excited to present SIGMA at @eccvconf ! 🎉 We upgrade VideoMAE with Sinkhorn-Knopp on patch-level embeddings, pushing reconstruction to more semantic features. With @mdorkenw. Let’s connect at today's poster session at 4:30 PM, poster number 256, or send us a DM.

📢SIGMA: Sinkhorn-Guided Masked Video Modeling got accepted to @eccvconf #ECCV2024 TL;DR: Instead of using pixel targets in Video Masked Modeling, we reconstruct jointly trained features using Sinkhorn guidance, achieving SOTA. 📝Project page: quva-lab.github.io/SIGMA/ 🌐Paper: arxiv.org/abs/2407.15447 Joint work with @MrzSalehi @fmthoker @egavves @cgmsnoek @y_m_asano

Post attachment
UvA AMLab avatar
⟳ Video & Image Sense Lab (VIS Lab) retweeted
UvA AMLab@AmlabUva·30 Aug 2024

We are hiring a postdoc! Come work with us in the booming AI ecosystem of beautiful Amsterdam on generative AI and/or uncertainty quantification 🤗 🎇vacatures.uva.nl/UvA/job/Pos…

Post attachment

I’m hiring a postdoc to work with me on exciting projects in generative modelling (AI) and/or uncertainty quantification. You'll be part of a great team, embedded in @AmlabUva and the UvA-Bosch Delta Lab. Apply here: vacatures.uva.nl/UvA/job/Pos… RT appreciated! #ML #GenAI