Giving surgical-tool keypoint detection to Qwen2.5-VL via LoRA fine-tuning reaches MPJPE 0.0627 on SurgeoNet, comparable with or better than dedicated YOLOv8-Pose and SurgeoNet baselines.
arXiv preprint arXiv:2407.12138 (2024)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Estimating 2D Keypoints of Surgical Tools Using Vision-Language Models with Low-Rank Adaptation
Giving surgical-tool keypoint detection to Qwen2.5-VL via LoRA fine-tuning reaches MPJPE 0.0627 on SurgeoNet, comparable with or better than dedicated YOLOv8-Pose and SurgeoNet baselines.