SSGVS: Semantic Scene Graph-to-Video Synthesis.
Yuren CongJinhui YiBodo RosenhahnMichael Ying YangPublished in: CoRR (2022)
Keyphrases
- video sequences
- dynamic scenes
- video images
- semantic context
- video annotation
- video event
- video scene
- scene change detection
- video data
- input video
- object motion
- space time
- live video
- semantic concepts
- moving camera
- d scene
- stationary camera
- visual data
- video content
- image sequences
- natural language
- graph model
- semantic information
- sports video
- video frames
- surveillance videos
- graph structure
- real time
- image mosaics
- video analysis
- spatial and temporal
- video streams
- complex scenes
- crowded scenes
- scene analysis
- multimedia
- single frame
- virtual view
- object detection and tracking
- dynamic textures
- weighted graph
- semantic web
- single image
- directed graph
- motion features
- raw image
- moving objects
- image frames
- multimedia data
- low level features
- key frames
- image regions
- outdoor scenes
- scene classification
- visual concepts
- random walk
- semantic labels
- video clips
- video retrieval
- video surveillance
- human motion
- semantic similarity