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


  • [2022-9] 6 papers accepted at NeurIPS.
  • [2022-9] Congratulations to Dr. William Thong for obtaining the doctorate degree.
  • [2022-8] VIS Lab moved to Lab42.
  • [2022-7] 6 papers accepted at ECCV.
  • [2022-6] Michael Dorkenwald joins the VIS lab as a PhD student.
  • [2022-5] 3 papers accepted at ICML.
  • [2022-4] Congratulations to Dr. Jiaojiao Zhao and Dr. Zenglin Shi for obtaining their doctorate degree.
  • [2022-3] 9 papers accepted at CVPR.
  • [2022-1] 6 papers accepted at ICLR.
  • [2021-11] BMVC best paper award for Ivan, Artem & Arnold.
  • [2021-10] 6 papers accepted at BMVC.
  • [2021-10] 4 papers accepted at NeurIPS.
  • [2021-10] Subhransu Maji spends a sabbatical at VIS lab.

Old News

Recent Publications

Quickly discover relevant content by filtering publications.

3D Equivariant Graph Implicit Functions

ECCV 2022

Contrasting quadratic assignments for set-based representation learning

ECCV 2022

Delta Distillation for Efficient Video Processing

ECCV 2022

How Severe is Benchmark-Sensitivity in Video Self-Supervised Learning?

ECCV 2022

Less than Few: Self-Shot Video Instance Segmentation

ECCV 2022