PhD Student in Machine Learning and Computer Vision

VGG, University of Oxford

Max Bain

Final year Phd student in computer vision and machine learning at the Visual Geometry Group, University of Oxford, supervised by Prof. A Zisserman. My primary research areas are video understanding and vision+language.

Interests
  • Vision+Language
  • Video Understanding
  • Speech and Multimodal learning
  • AI applications, Fairness, Wildlife, Accessibility.
Education

  • DPhil in Computer Vision, 2019 -

    University of Oxford

  • MEng in Engineering Science, 2015 - 19

    University of Oxford

Publications

WhisperX: Time-Accurate Speech Transcription of Long-Form Audio
Time-Accurate and Efficient Speech Transcription of Long-Form Audio.
Max Bain, Jaesung Huh, Tengda Han, Andrew Zisserman
PDF Cite Code
WhisperX: Time-Accurate Speech Transcription of Long-Form Audio
A CLIP-Hitchhiker's Guide to Long Video Retrieval
Text-to-video retrieval with CLIP via per-frame attention scoring.
Max Bain, Arsha Nagrani, Gül Varol, Andrew Zisserman
PDF Cite
A CLIP-Hitchhiker's Guide to Long Video Retrieval
A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning [AACL'22]
Debiasing Pretrained Vision-Language Models with Adversarial Learning.
Hugo Berg, Siobhan Mackenzie Hall, Yash Bhalgat, Wonsuk Yang, Hannah Rose Kirk, Aleksandar Shtedritski, Max Bain
PDF Cite Code
A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning [AACL'22]
Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval [ICCV'21]
Text-to-video retrieval using a dual encoder architecture of text and video transformers, which trains and test on videos and images jointly.
Max Bain, Arsha Nagrani, Gül Varol, Andrew Zisserman
PDF Cite Code Dataset Project Demo
Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval [ICCV'21]
Automated Audiovisual Behaviour Recognition in Wild Primates [Science Adv.'21]
Deep learning using audio-visual data from chimpanzee percussive behaviours enables action recognition in the wild.
Max Bain, Arsha Nagrani, Daniel Schofield, Sophie Berdugo, Joana Bessa, Jake Owens, Kimberley J. Hockings, Tetsuro Matsuzawa, Misato Hayashi, Dora Biro, Susana Carvalho, Andrew Zisserman
PDF Cite DOI News
Automated Audiovisual Behaviour Recognition in Wild Primates [Science Adv.'21]
See all publications

Contact