A surgical-video multimodal LLM with instrument-centric masked pretraining and interleaved temporal embeddings beats general video LLMs on a new CholecT50-derived benchmark.
See- through vision with unsupervised scene occlusion reconstruction
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
-
SurgLLM: A Versatile Large Multimodal Model with Spatial Focus and Temporal Awareness for Surgical Video Understanding
A surgical-video multimodal LLM with instrument-centric masked pretraining and interleaved temporal embeddings beats general video LLMs on a new CholecT50-derived benchmark.