Zero-shot prompt-based video encoder for surgical gesture recognition
Bridge-prompt and similar pre-trained + prompt-tuned video encoder models present significant visual representation for surgical robotics, especially in gesture recognition tasks. Given the diverse range of surgical tasks (gestures), the ability of these models to zero-shot transfer without the need for any task (gesture) specific retraining makes them invaluable.
Authors
- Soheil Kolouri (ORCID: https://orcid.org/0000-0001-8495-5362)
- Daniel Moyer (ORCID: https://orcid.org/0000-0003-4428-5012)
- Jie Ying Wu (ORCID: https://orcid.org/0000-0002-7306-8140)
- M. Subba Rao (ORCID: https://orcid.org/0009-0006-6582-4598)
- Yinhong Qin (ORCID: https://orcid.org/0009-0000-4526-4139)
Institutions
- Vanderbilt University (US)
- Vanderbilt Health (US)
Publication Details
- Journal
- International Journal of Computer Assisted Radiology and Surgery
- Published
- 2024-09-17
- DOI
- https://doi.org/10.1007/s11548-024-03257-1
- Citations
- 5
- Primary Topic
- Human Pose and Action Recognition
- Type
- article
- Field-Weighted Citation Impact
- 1.25
Funders
- National Science Foundation