Latent-Action-Guided Video-Language Feature Learning for Surgical Instrument-Tissue Interaction Recognition
TL;DR
This work introduces \the authors', which compresses frame-to-frame changes into latent actions and predicts next-frame features during end-to-end video--language alignment and achieves competitive recognition with faster inference and smaller INT4 accuracy drops than V-JEPA2/2.1.
Abstract
Recognizing instrument--tissue interactions is essential for context-aware surgical AI. Vision-language models offer a natural way to inject semantic structure into surgical representations by aligning video features with textual action descriptions. However, pretrained encoders may lack spatial coherence, while global semantic alignment does not ensure precise spatial and temporal representations. By analyzing frame-to-frame feature changes, we find that semantic alignment increases their dimensionality, but larger increases do not necessarily improve recognition; encoders also differ in how strongly dominant changes localize to interaction regions. Motivated by these findings, we introduce \ours{}, which compresses frame-to-frame changes into latent actions and predicts next-frame features during end-to-end video--language alignment. Without additional spatial or motion annotations, \ours{} improves the interaction grounding of leading feature changes and temporal-direction sensitivity in our evaluated settings. We further characterize how action capacity and prediction strength affect recognition across encoders and triplet components. Using image encoders without large-scale video pretraining, \ours{} achieves competitive recognition with faster inference and smaller INT4 accuracy drops than V-JEPA2/2.1.