Lightnews — Scholar-powered news

Belongie Lab

@belongielab.org

1.1K followers 41 following 32 posts

Computer Vision & Machine Learning 📍 Pioneer Centre for AI, University of Copenhagen 🌐 https://www.belongielab.org

www.belongielab.org

Posts Media Videos Starter Packs

Pinned

Belongie Lab @belongielab.org · Nov 17

Logging on! 🧑‍💻🦋 We're the Belongie Lab led by @sergebelongie.bsky.social. We study Computer Vision and Machine Learning, located at the University of Copenhagen and Pioneer Centre for AI. Follow along to hear about our research past and present! www.belongielab.org

Belongie Lab - Home

Belongie Lab -- Home.

www.belongielab.org

Belongie Lab @belongielab.org · Aug 13

Thank you for a great talk and interesting discussion Ching Lam!

Belongie Lab @belongielab.org · Aug 13

Today we welcomed @chinglam.bsky.social back to @aicentre.dk for a visit and lunch talk on her latest work as a PhD student at @csail.mit.edu on multimodal learning: “Seeing Beyond the Cave: Asymmetric Views of Representation”

www.aicentre.dk/events/lunch...

Belongie Lab @belongielab.org · Jul 30

Peter Michael, Zekun Hao, Serge Belongie, and Abe Davis, “Noise-Coded Illumination for Forensic and Photometric Video Analysis,” ACM Transactions on Graphics, 2025.

NCI project page: peterfmichael.com/nci (2/2)

Belongie Lab @belongielab.org · Jul 30

Excited to share our new work at @acm.org Transactions on Graphics/@acmsiggraph.bsky.social! We use coded noise to add an invisible watermark to lighting that helps detect fake or manipulated video. (1/2)

Belongie Lab @belongielab.org · Jun 13

Andrew and his coauthors won this test-of-time-prize for their 2015 CVPR paper “Going Deeper with Convolutions” arxiv.org/abs/1409.4842 (2/2)

Going Deeper with Convolutions

We propose a deep convolutional neural network architecture codenamed "Inception", which was responsible for setting the new state of the art for classification and detection in the ImageNet Large-Sca...

Belongie Lab @belongielab.org · Jun 13

Congratulations Andrew Rabinovich (PhD ‘08) on winning the Longuet-Higgins Prize at #CVPR2025! (1/2)

Reposted by Belongie Lab

Srishti @srishtiy.bsky.social · Jun 2

I am excited to announce our latest work 🎉 "Cultural Evaluations of Vision-Language Models Have a Lot to Learn from Cultural Theory". We review recent works on culture in VLMs and argue for deeper grounding in cultural theory to enable more inclusive evaluations.

Paper 🔗: arxiv.org/pdf/2505.22793

Paper title "Cultural Evaluations of Vision-Language Models
Have a Lot to Learn from Cultural Theory"

Reposted by Belongie Lab

Jiaang Li @jiaangli.bsky.social · May 23

🚀New Preprint🚀
Can Multimodal Retrieval Enhance Cultural Awareness in Vision-Language Models?

Excited to introduce RAVENEA, a new benchmark aimed at evaluating cultural understanding in VLMs through RAG.
arxiv.org/abs/2505.14462

More details:👇

Belongie Lab @belongielab.org · May 9

We aspire to cultivate the next generation of AI researchers — those who will be the Keplers and Galileos of artificial intelligence. Researchers who will transform empirical mystery into theoretical clarity, and in doing so, redefine the foundations of intelligence itself. (7/7)

Belongie Lab @belongielab.org · May 9

Like Brahe, we are navigating a universe of patterns, charting phenomena whose significance may only become clear in hindsight. Our ambition is to go beyond observation. (6/7)

Belongie Lab @belongielab.org · May 9

We believe AI today is at a similar juncture. We are observing extraordinary capabilities in large-scale models — emergent behaviors, generalization across modalities, alignment challenges — but we lack an elegant theory to explain what we see. (5/7)

Belongie Lab @belongielab.org · May 9

Brahe didn’t formulate the laws of planetary motion, nor did he have the mathematical tools to do so. But through relentless observation and accurate measurement, he assembled a foundation of data that enabled the breakthroughs of Kepler and Galileo. (4/7)

Belongie Lab @belongielab.org · May 9

In front of our building stands a statue of Tycho Brahe — a tribute not just to Denmark’s scientific heritage, but to the spirit of inquiry that defines our field today (3/7)

Belongie Lab @belongielab.org · May 9

You can read more about the old observatory (the current home of P1) in this Wikipedia article (2/7)

Østervold Observatory - Wikipedia

en.m.wikipedia.org

Belongie Lab @belongielab.org · May 9

This morning at P1 a handful of lucky of lab members got to see the telescope while centre secretary Björg had the dome open for a building tour 🔭 (1/7)

Belongie Lab @belongielab.org · May 8

Menglin is now a research scientist at Meta in NYC (5/5)

Belongie Lab @belongielab.org · May 8

Joint work with Luming Tang, Bor-Chun Chen, Claire Cardie, Serge Belongie, Bharath Hariharan, Ser-Nam Lim. Link to code & paper: github.com/KMnP/vpt

GitHub - KMnP/vpt: ❄️🔥 Visual Prompt Tuning [ECCV 2022] https://arxiv.org/abs/2203.12119

❄️🔥 Visual Prompt Tuning [ECCV 2022] https://arxiv.org/abs/2203.12119 - KMnP/vpt

Belongie Lab @belongielab.org · May 8

On 24 downstream tasks spanning different domains, VPT beat all other transfer learning baselines, even surpassing full fine-tuning in 20 cases, while maintaining the advantage of storing significantly fewer parameters (less than 1% of backbone parameters) for each task. (3/5)

Belongie Lab @belongielab.org · May 8

What is the best way to adapt large pre-trained vision models to downstream tasks in terms of effectiveness and efficiency? Drawing inspiration from the recent advances on prompting in NLP, Menglin and colleagues proposed a simple and efficient method: Visual Prompt Tuning (VPT) (2/5)

Belongie Lab @belongielab.org · May 8

Time to revive the Belongie Lab Throwback Thursday tradition we had started in the before times 🙌 Today's #tbt is Jia et al. "Visual Prompt Tuning," from ECCV 2022 (1/5)

Belongie Lab @belongielab.org · May 7

Thank you Prof. Derpanis!

Kosta Derpanis @csprofkgd.bsky.social · May 7

Feels like @belongielab.org just hit 100k citations yesterday, but that curve’s still climbing strong and now they’re barreling toward 200k. Let’s go! 💪🫡

Belongie Lab @belongielab.org · Apr 7

New study with @iaugenstein.bsky.social’s group analyzing the interplay between photos and text in the news

Arnav Arora @rnv.bsky.social · Apr 7

🚨New pre-print 🚨

News articles often convey different things in text vs. image. Recent work in computational framing analysis has analysed the article text but the corresponding images in those articles have been overlooked.
We propose multi-modal framing analysis of news: arxiv.org/abs/2503.20960

Reposted by Belongie Lab

Zhaochong An @zhaochongan.bsky.social · Feb 11

Thrilled to announce "Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation" is accepted as a Spotlight (5%) at #ICLR2025!

Our model MM-FSS leverages 3D, 2D, & text modalities for robust few-shot 3D segmentation—all without extra labeling cost. 🤩

arxiv.org/pdf/2410.22489

More details👇

Reposted by Belongie Lab

Nico Lang @nicolang.bsky.social · Jan 24

Recordings of the SSL4EO-2024 summer school are now released!

This blog post summarizes what has been covered:
langnico.github.io/posts/SSL4EO...

Recordings: www.youtube.com/playlist?lis...

Course website: ankitkariryaa.github.io/ssl4eo/
[1/3]

Screenshot of the course website for "SSL4EO: Self-Supervised Learning for Earth Observation"

Belongie Lab @belongielab.org · Jan 24

SCIA 2025 submission deadline extended to Feb. 17

Scandinavian Conference on Image Analysis 2025