PeopleofSuperintelligence

Researcher

João F. Henriques

Also known as João Henriques, Joao Henriques, Joao F. Henriques

João Henriques is a computer vision researcher at the University of Oxford whose KCF and SiameseFC trackers run in consumer hardware, from Facebook apps to commercial drones. After a master's degree in electrical engineering at the University of Coimbra in 2009, he coauthored the first tracker based on circulant matrices in 2012, and the Kernelized Correlation Filter followed in 2014 while he was a doctoral student at Coimbra's Institute of Systems and Robotics. In 2016 he coauthored the SiamFC tracker with Luca Bertinetto, Jack Valmadre, Andrea Vedaldi and Philip Torr, and in 2018 and 2019 he presented MapNet and CurveBall. The Royal Academy of Engineering announced his Research Fellowship for the one-shot learning project MEMO in August 2019, and in 2021 he helped organize the NeurIPS pre-registration workshop. He is a Research Fellow of the Royal Academy of Engineering in Oxford's Visual Geometry Group, where his research also covers robot mapping, multi-agent cooperation and "friendly" AI.

Timeline

  1. 2009

    Electrical engineering at Coimbra

    He earns a master's degree in electrical engineering from the University of Coimbra in 2009. He goes on to doctoral studies at the university's Institute of Systems and Robotics, with research on Fourier analysis and machine learning for detection and tracking.

  2. 2012–2014

    From circulant trackers to KCF

    In 2012, he coauthors "Exploiting the Circulant Structure of Tracking-by-Detection with Kernels" at ECCV with Rui Caseiro, Pedro Martins and Jorge Batista, the first tracker based on circulant matrices. Its successor, the Kernelized Correlation Filter (KCF), appears on arXiv in 2014 and outperforms trackers such as Struck and TLD on a 50-video benchmark while running at hundreds of frames per second.

  3. 2016

    The SiamFC tracker

    In 2016, he coauthors "Fully-Convolutional Siamese Networks for Object Tracking" with Luca Bertinetto, Jack Valmadre, Andrea Vedaldi and Philip H. S. Torr. The SiamFC tracker uses a fully-convolutional Siamese network trained end-to-end on the ILSVRC15 video detection data and operates at frame-rates beyond real-time.

  4. 2018–2019

    MapNet and CurveBall

    At CVPR in 2018, he and Andrea Vedaldi present MapNet, an end-to-end learnable deep network that solves the full SLAM problem with a spatial memory. In 2019 at ICCV, he and coauthors introduce CurveBall, a second-order optimizer for deep networks that needs no hyper-parameter tuning.

  5. 2019

    Royal Academy of Engineering fellowship

    In August 2019, the Royal Academy of Engineering announces 18 new Research Fellowships, including one for Dr Joao Henriques of the University of Oxford for the project MEMO, Meta-learning Enhanced Memorization in One-shot. Each awardee receives five years of funding and mentorship.

  6. 2021

    A pre-registration workshop

    In 2021, he helps organize the NeurIPS pre-registration workshop with Samuel Albanie, Luca Bertinetto, Alex Hernandez-Garcia, Hazel Doughty and Gul Varol. Papers in this publication model go to peer review without experimental results, and the experimental protocol is followed after acceptance.

  7. 2024

    A talk on safe agents

    In 2024, he gives the first invited talk at the NeurIPS workshop Towards Safe & Trustworthy Agents.

  8. As of October 2026

    Research Fellow at Oxford's VGG

    He is a Research Fellow of the Royal Academy of Engineering in the Visual Geometry Group at the University of Oxford, an associate member of faculty in Engineering Science and a principal investigator. His research spans computer vision, deep learning, robot mapping and navigation, and multi-agent cooperation and "friendly" AI. The KCF and SiameseFC trackers he created won the VOT Challenge twice and are widely deployed in consumer hardware, from Facebook apps to commercial drones.

Career

  1. NowUniversity of OxfordResearch Fellow and Principal Investigator

Education

  1. 2009University of CoimbraMaster's degree in electrical engineering

From the biography.

  1. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes University of Oxford. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  2. The median h-index is 48 at universities and 14 at frontier AI labsIncludes University of Oxford. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  3. Companies supply the most prior-work hires at 7 of the 9 frontier AI labsIncludes University of Oxford. Our estimates of the organizations where 550 people worked directly before joining 9 frontier AI labs across 620 career transitions, comparing the main feeder organizations per lab.
  4. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorateIncludes University of Oxford. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorate. Across 2,116 people with both an undergraduate degree and a doctorate recorded, we trace which undergraduate schools feed which doctoral programs, how often students stay at the same school, and how paths differ by birth-country region.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of João F. Henriques yet. Send us a free-licensed photo.

  1. High-Speed Tracking with Kernelized Correlation Filters (ar5iv HTML version) ar5iv.labs.arxiv.org. Checked 21 October 2026.
  2. João F. Henriques robots.ox.ac.uk. Checked 21 October 2026.
  3. High-Speed Tracking with Kernelized Correlation Filters arxiv.org. Checked 21 October 2026.
  4. Fully-Convolutional Siamese Networks for Object Tracking arxiv.org. Checked 21 October 2026.
  5. Academy supports engineering excellence with 18 new Research Fellowships raeng.org.uk. Checked 21 October 2026.
  6. The pre-registration workshop: an alternative publication model for machine learning research nips.cc. Checked 21 October 2026.
  7. Invited talk 1: João F. Henriques (Research Fellow, Royal Academy of Engineering) neurips.cc. Checked 21 October 2026.
  8. João Henriques - People - Department of Engineering Science eng.ox.ac.uk. Checked 21 October 2026.
  9. People - Visual Geometry Group - University of Oxford robots.ox.ac.uk. Checked 21 October 2026.