TY - GEN
T1 - Where It Moves, It Matters
T2 - 40th AAAI Conference on Artificial Intelligence, AAAI 2026
AU - Wei, Meng
AU - Yuan, Kun
AU - Li, Shi
AU - Zhou, Yue
AU - Bai, Long
AU - Navab, Nassir
AU - Ren, Hongliang
AU - Lee, Hong Joo
AU - Vercauteren, Tom
AU - Padoy, Nicolas
N1 - Publisher Copyright:
© 2026, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2026
Y1 - 2026
N2 - Enabling intuitive, language-driven interaction with surgical scenes is a critical step toward intelligent operating rooms and autonomous surgical robotic assistance. However, the task of referring segmentation, localizing surgical instruments based on natural language descriptions, remains underexplored in surgical videos, with existing approaches struggling to generalize due to reliance on static visual cues and predefined instrument names. In this work, we introduce SurgRef, a novel motion-guided framework that grounds free-form language expressions in instrument motion, capturing how tools move and interact across time, rather than what they look like. This allows models to understand and segment instruments even under occlusion, ambiguity, or unfamiliar terminology. To train and evaluate SurgRef, we present Ref-IMotion, a diverse, multi-institutional video dataset with dense spatiotemporal masks and rich motion-centric expressions. SurgRef achieves state-of-the-art accuracy and generalization across surgical procedures, setting a new benchmark for robust, language-driven surgical video segmentation.
AB - Enabling intuitive, language-driven interaction with surgical scenes is a critical step toward intelligent operating rooms and autonomous surgical robotic assistance. However, the task of referring segmentation, localizing surgical instruments based on natural language descriptions, remains underexplored in surgical videos, with existing approaches struggling to generalize due to reliance on static visual cues and predefined instrument names. In this work, we introduce SurgRef, a novel motion-guided framework that grounds free-form language expressions in instrument motion, capturing how tools move and interact across time, rather than what they look like. This allows models to understand and segment instruments even under occlusion, ambiguity, or unfamiliar terminology. To train and evaluate SurgRef, we present Ref-IMotion, a diverse, multi-institutional video dataset with dense spatiotemporal masks and rich motion-centric expressions. SurgRef achieves state-of-the-art accuracy and generalization across surgical procedures, setting a new benchmark for robust, language-driven surgical video segmentation.
UR - https://www.scopus.com/pages/publications/105040174393
U2 - 10.1609/aaai.v40i13.38027
DO - 10.1609/aaai.v40i13.38027
M3 - Conference contribution
AN - SCOPUS:105040174393
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
SN - 9781577359067
T3 - Proceedings of the AAAI Conference on Artificial Intelligence
SP - 10548
EP - 10556
BT - Proceedings of the AAAI Conference on Artificial Intelligence
A2 - Koenig, Sven
A2 - Jenkins, Chad
A2 - Taylor, Matthew E.
PB - Association for the Advancement of Artificial Intelligence
Y2 - 20 January 2026 through 27 January 2026
ER -