Video & Image Sense Lab

We make sense of video and images with artificial and human intelligence. The lab studies computer vision, deep learning and cognitive science. We are based at the Informatics Institute of the University of Amsterdam.

The VIS Lab embeds four public-private AI labs. QUVA Lab with Qualcomm, Atlas Lab with TomTom, AIM Lab with the Inception Institute of Artificial Intelligence and POP-AART with the Netherlands Cancer Institute and Elekta Oncology Systems. Spin-off's from the lab include Kepler Vision Technologies and Ellogon.ai.

News

  • [2025-10] Iris Groen and Pascal Mettes awarded NWO Vidi Grant.
  • [2025-9] 5 papers accepted at NeurIPS.
  • [2025-7] Congratulations to Yingjun Du for being awarded a ‘2024 Chinese Government Award for Outstanding Self-Financed Students Abroad’.
  • [2025-6] 5 papers accepted at ICCV.
  • [2025-6] Congratulations to Dr. Zehao Xiao for obtaining the doctorate degree.
  • [2025-5] 3 papers accepted at ICML.
  • [2025-2] 6 papers accepted at CVPR.
  • [2025-2] Congratulations to Dr. Phillip Lippe for obtaining the doctorate degree, cum laude.
  • [2025-1] 13 papers accepted at ICLR.
  • [2024-11] Congratulations to Dr. Yunhua Zhang for obtaining the doctorate degree.
  • [2024-10] Congratulations to former VIS-lab staff member Dr. Yuki Asano for being promoted to Full Professor at University of Technology Nuremberg.

Old News

Recent Publications

Quickly discover relevant content by filtering publications.

Union-over-Intersections: Object Detection beyond Winner-Takes-All

ICLR 2025
Aritra Bhowmik, Pascal Mettes, Martin R. Oswald, Cees G. M. Snoek
PDF
Union-over-Intersections: Object Detection beyond Winner-Takes-All

BrainACTIV: Identifying visuo-semantic properties driving cortical selectivity using diffusion-based image manipulation

ICLR 2025
Diego Garcia Cerdas, Christina Sartzetaki, Magnus Petersen, Gemma Roig, Pascal Mettes, Iris I.A. Groen
PDF Code
BrainACTIV: Identifying visuo-semantic properties driving cortical selectivity using diffusion-based image manipulation

CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation

ICLR 2025
Jie Liu, Pan Zhou, Yinjun Du, Ah-Hwee Tan, Cees G.M. Snoek, Jan-Jakob Sonke, Efstratios Gavves
PDF Code
CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation

Compositional entailment learning for hyperbolic vision-language models

ICLR 2025
Avik Pal, Max van Spengler, Guido Maria D'Amely di Melendugno, Alessandro Flaborea, Fabio Galasso, Pascal Mettes
PDF Code
Compositional entailment learning for hyperbolic vision-language models

Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination

ICLR 2025
Leonardo Barcellona, Andrii Zadaianchuk, Davide Allegro, Samuele Papa, Stefano Ghidoni, Efstratios Gavves
PDF
Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination
See all publications

Topics

3D computer vision Action and behavior recognition action localization action recognition AI for Health Causal Representation Learning Continual Learning few-shot learning generative model Image retrieval low-shot Motion and tracking Multi-modal learning Recognition (object detection, categorization) Self-supervised learning semi- and un-supervised learning Transfer Transfer, low-shot, semi- and un-supervised learning Video analysis and understanding Visual reasoning and logical representation

Contact