Scholar
Tengda Han
Google Scholar ID: SbAuWREAAAAJ
Google DeepMind | VGG, University of Oxford
Computer Vision
Machine Learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
8,763
H-index
17
i10-index
17
Publications
20
Co-authors
18
list available
Contact
Email
tengda@google.com
Twitter
Open ↗
GitHub
Open ↗
Publications
10 items
KilometerVision: A New Frontier for Large-Scale Spatial Intelligence in VLMs
2026
Cited
0
GMOS: Grounding Moving Object Segmentation in 3D Space and Time
2026
Cited
0
Unique Lives, Shared World: Learning from Single-Life Videos
2025
Cited
0
Seeing without Pixels: Perception from Camera Trajectories
2025
Cited
0
Dynamic Reflections: Probing Video Representations with Text Alignment
2025
Cited
0
More than a Moment: Towards Coherent Sequences of Audio Descriptions
2025
Cited
0
Character-Centric Understanding of Animated Movies
2025
Cited
0
Learning from Streaming Video with Orthogonal Gradients
2025
Cited
0
Load more
Resume
Academic Achievements
- Publications: Multiple papers accepted at top conferences such as ACMMM, ICCV, CVPR, NeurIPS, etc.
- Awards: Best Paper Award at ACCV, Best Poster Award at BMVC2023, BMVA Sullivan Doctoral Thesis Prize Runner-up
- Organized Workshops: SLoMo, Self-Supervised Learning workshop, BigMAC, Self-Supervised Learning - Theory and Practice, etc.
Research Experience
- Research Scientist at Google DeepMind (since March 2024)
- Post-doctoral Research Fellow in VGG at the University of Oxford
- Collaborated on deep learning projects with Basura Fernando, Anoop Cherian, Mehrtash Harandi, Stephen Gould, and Richard Hartley
- Intern at DeepMind (August 2021 - December 2021), working on the Flamingo project
Education
- PhD: University of Oxford, supervised by Andrew Zisserman
- Bachelor's Degree: Australian National University, major in Mechanical & Material Engineering
- Studied Business Administration and Law for one year at Renmin University of China
- Originally from the suburbs of Hangzhou, China
Background
- Research Interest: Training neural networks to understand videos
- Professional Field: Computer Vision, Deep Learning
- Brief Introduction: Currently a research scientist at Google DeepMind, previously a post-doctoral research fellow in VGG at the University of Oxford
Miscellany
- Personal interests not mentioned
Co-authors
16 total
Andrew Zisserman
University of Oxford
Weidi Xie
Shanghai Jiao Tong University | VGG, University of Oxford
Max Bain
Google DeepMind
Arsha Nagrani
Research Scientist, Google
Gul Varol
Ecole des Ponts ParisTech (ENPC)
Yuki M. Asano
Full Professor, Head of FunAI Lab, University of Technology Nuremberg
Stephen Gould
Professor at Australian National University
Anoop Cherian
Mitsubishi Electric Research Labs (MERL), Adj. Assoc. Prof. Australian National University