SCTF: an efficient neural network based on local spatial compression and full temporal fusion for video violence detection.
Zhenhua TanZhenche XiaPengfei WangDanke WuLi LiPublished in: Multim. Tools Appl. (2024)
Keyphrases
- temporal redundancy
- spatial and temporal
- temporal correlation
- space time
- video coding
- video frames
- multi modal fusion
- spatial temporal
- spatio temporal
- temporal segmentation
- temporal domain
- temporal resolution
- temporal information
- video compression
- face detection and tracking
- temporal continuity
- video sequences
- neural network
- inter frame
- temporal relationships
- motion estimation
- spatio temporally
- video data
- spatial correlation
- compression algorithm
- temporal dimension
- image compression
- temporal dependencies
- data compression
- temporal structure
- temporal aspects
- multimedia
- video content
- spatial information
- temporal data
- dynamic textures
- temporal consistency
- temporal events
- combining information from multiple
- temporal analysis
- spatial features
- temporal coherence
- soccer video
- spatio temporal data
- video indexing
- dynamic scenes
- compression ratio
- event detection
- video streams
- detection algorithm
- motion vectors
- spatial data
- data fusion
- tv broadcast
- multiresolution
- spatial and temporal information
- temporal order
- video retrieval
- temporal patterns
- video shots
- video signals
- video scene