A spatio-temporal network for video semantic segmentation in surgical videos.
Maria GrammatikopoulouRicardo Sanchez-MatillaFelix J. S. BragmanDavid OwenLucy CulshawKaren KerrDanail StoyanovImanol LuengoPublished in: CoRR (2023)
Keyphrases
- spatio temporal
- semantic segmentation
- video sequences
- human actions
- video frames
- video content
- video data
- space time
- dynamic textures
- key frames
- moving objects
- video surveillance
- superpixels
- dynamic scenes
- scene classification
- object categories
- weakly supervised
- label transfer
- human motion
- moving camera
- three dimensional
- conditional random fields
- image sequences