Anita Rau

prof_pic.jpg

Hi! I am a Postdoc at MARVL, the Medical AI and Computer Vision Lab at Stanford University, where I am advised by Serena Yeung-Levy.

My research is at the intersection of AI and computer vision, with a focus on automating the spatial and semantic understanding of video. I am particularly interested in highly dynamic, high-stakes environments—such as surgery—that involve fine-grained actions, complex visual scenes, and decision processes that are difficult to capture exhaustively in standard datasets. By integrating multi-modal data, I aim to develop generalizable models that can interpret and act on real-world scenarios, with the goal of supporting decision-making, enhancing training, and improving safety in critical applications.

Before joining MARVL, I earned my PhD from University College London, where I was part of the Surgical Robot Vision Group advised by Dan Stoyanov. During my PhD, I also interned at Niantic Research in London. Prior to that, I received an MSc in Computational Statistics and Machine Learning from UCL and a BSc in Mathematics and Economics from the University of Mannheim.

news

Mar 23, 2025 Our Video Action Differencing project page is online.
Mar 01, 2025 BIOMEDICA has been accepted to CVPR 2025!
Feb 16, 2025 Our GitHub repo for EMD-NeRF is now online.
Jan 27, 2025 Our work Video Action Differencing was accepted at ICLR 2025! Preprint coming soon.
Jan 16, 2025 The preprint for our latest work, BIOMEDICA, is now online! Find > 24 million image-text pairs for VLM training!

highlighted publications

  1. biomedica.png
    BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature
    Alejandro Lozano, Min Woo Sun, James Burgess, and 8 more authors
    CVPR , 2025
  2. vidactdiff.jpg
    Video Action Differencing
    James Burgess, Xiaohan Wang, Yuhui Zhang, and 5 more authors
    ICLR , 2025
  3. emd2.png
    Depth-guided nerf training via earth mover’s distance
    Anita Rau, Josiah Aklilu, F Christopher Holsinger, and 1 more author
    In ECCV , 2024
  4. hands.jpg
    Robust Semi-supervised Detection of Hands in Diverse Open Surgery Environments
    Pranav Vaid, Serena Yeung, and Anita Rau
    In Machine Learning for Healthcare Conference , 2023
  5. box.png
    Predicting visual overlap of images through interpretable non-metric box embeddings
    Anita Rau, Guillermo Garcia-Hernando, Danail Stoyanov, and 2 more authors
    In ECCV , 2020 (Spotlight presentation)
  6. implicit.png
    Implicit domain adaptation with conditional generative adversarial networks for depth prediction in endoscopy
    Anita Rau, PJ Eddie Edwards, Omer F Ahmad, and 4 more authors
    International journal of computer assisted radiology and surgery , 2019