Scholar
Tobias Weyand
Google Scholar ID: US56Kw8AAAAJ
Google Reserach
Citations & Impact
Citations
3,155
H-index
13
i10-index
14
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Published several papers such as 'Minerva: Evaluating Complex Video Reasoning' (2025), 'Neptune: The Long Orbit to Benchmarking Long Video Understanding' (2024), 'Extending Video Masked Autoencoders to 128 frames' (2024), 'VideoPrism: A Foundational Visual Encoder for Video Understanding' (2024), 'VideoGLUE: Video General Understanding Evaluation of Foundation Models' (2024), and 'Google Landmarks Dataset v2 - A Large-Scale Benchmark for Instance-Level Recognition and Retrieval'.
Research Experience
- Works at Google DeepMind on video understanding; previously worked on some Nintendo DS homebrew projects.
Education
- PhD from RWTH Aachen Vision Lab, supervised by Bastian Leibe; Diploma (MS) in Computer Science from RWTH Aachen University.
Background
- A Computer Vision researcher focusing on video understanding, particularly long video representations. Research interests include landmark recognition, image localization, large-scale image retrieval, and clustering.
Miscellany
- Interested in Nintendo DS homebrew projects, which can be found on his GitHub page.
Co-authors