We are excited to share our latest work: "ReSurgSAM2: Referring Segment Anything in Surgical Video via Credible Long-term Tracking", early accepted at MICCAI 2025 (top 9%)🚀
arXiv: https://t.co/G6whZRUNRm
Huggingface: https://t.co/kJhdkqVpis
#SurgicalAI#SugicalDataScience#SAM2
Our work addresses precise interactive segmentation of surgical instruments and tissues in long-duration videos, achieving 14.17% improvement on Ref-EndoVis17 while maintaining real-time performance (61.2 FPS). 🙌
Excited to share our work: "Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning" at the AIM-FM workshop, NeurIPS 2024. We look forward to continuing our exploration and contributions to the research community.
#NeurIPS2024#SurgicalAI
We are excited to share our latest work: “Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning”.
Arxiv: https://t.co/3bODgy4msI
Huggingface: https://t.co/OaPtMNCgzC
#SurgicalAI#SugicalDataScience#SAM#SAM2
@JinYueming@zhang_erli@JundeMorsenWu Excited to share that our paper "Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning" has been featured in HuggingFace Daily Papers Digest! 🚀
Check it out here: https://t.co/3bODgy4msI and https://t.co/OaPtMNCgzC.
#SurgicalAI#SAM#SAM2
We are excited to share our latest work: “Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning”.
Arxiv: https://t.co/3bODgy4msI
Huggingface: https://t.co/OaPtMNCgzC
#SurgicalAI#SugicalDataScience#SAM#SAM2
Excited to share that our paper "Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning" has been featured in HuggingFace Daily Papers Digest! 🚀
Check it out here: https://t.co/3bODgy4msI and https://t.co/OaPtMNCgzC.
#SurgicalAI#SAM#SAM2
We are excited to share our latest work: “Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning”.
Arxiv: https://t.co/3bODgy4msI
Huggingface: https://t.co/OaPtMNCgzC
#SurgicalAI#SugicalDataScience#SAM#SAM2
We are excited to share our latest work: “Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning”.
Arxiv: https://t.co/3bODgy4msI
Huggingface: https://t.co/OaPtMNCgzC
#SurgicalAI#SugicalDataScience#SAM#SAM2
We introduce Surgical SAM 2 integrating SAM2 with an efficient frame pruning mechanism for real-time surgical video segmentation.
- reduces memory usage and computational cost for real-time clinical application;
- achieves superior performance with 3× FPS (86 FPS).