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


  • [2024-3] Congratulations to Dr. Artem Moskalev for obtaining the doctorate degree.
  • [2024-2] 5 papers accepted at CVPR.
  • [2024-1] 5 papers accepted at ICLR.
  • [2023-12] Congratulations to VIS-lab alumnus Dr. Zenglin Shi for being promoted to Full Professor at Hefei University of Technology.
  • [2023-12] Congratulations to Dr. Fida Thoker for obtaining the doctorate degree.
  • [2023-11] Piyush Bagad receives KHMW Thesis Prize.
  • [2023-11] Congratulations to Dr. Adeel Pervez for obtaining the doctorate degree.
  • [2023-9] Yuki Asano and Pascal Mettes recognized as outstanding reviewers for ICCV 2023.
  • [2023-9] 7 papers accepted at NeurIPS.
  • [2023-8] Hazel Doughty awarded NWO Veni Grant.
  • [2023-8] Tao Hu and Fida Thoker selected for ICCV Doctoral Consortium.
  • [2023-7] 8 papers accepted at ICCV.
  • [2023-7] Congratulations to Dr. Yunlu Chen, Dr. Tao Hu and Dr. Shuo Chen for obtaining the doctorate degree.
  • [2023-6] Congratulations to Dr. Ivan Sosnovik for obtaining the doctorate degree.
  • [2023-5] Hazel Doughty, Mina Ghadimi Atigh, and Piyush Nitin Bagad recognized as outstanding reviewers for CVPR.
  • [2023-4] 3 papers accepted at ICML.
  • [2023-3] Tao Hu selected for CVPR Doctoral Consortium.
  • [2023-2] 3 papers accepted at CVPR.
  • [2023-2] Congratulations to Dr. Riaan Zoetmulder for obtaining the doctorate degree.
  • [2023-1] 8 papers accepted at ICLR.

Old News

Recent Publications

Quickly discover relevant content by filtering publications.

Any-Shift Prompting for Generalization over Distributions

CVPR 2024

How to Train Neural Field Representations: A Comprehensive Study and Benchmark

CVPR 2024

Learning to Count without Annotations

CVPR 2024

PIN: Positional Insert Unlocks Object Localisation Abilities in VLMs

CVPR 2024