Video Captioning With Attention-Based LSTM and Semantic Consistency.
Lianli GaoZhao GuoHanwang ZhangXing XuHeng Tao ShenPublished in: IEEE Trans. Multim. (2017)
Keyphrases
- video event
- temporal consistency
- sports video
- video content
- semantic concepts
- multimedia
- video sequences
- semantic video
- video data
- natural language
- video streams
- video analysis
- real time video
- video clips
- semantic information
- real time
- online video
- semantic annotation
- semantic knowledge
- visual saliency
- key frames
- visual attention
- action descriptions
- recurrent neural networks
- semantic network
- video surveillance
- event detection
- content based video retrieval
- spatial and temporal
- video frames
- space time
- semantic description
- domain knowledge
- high level
- semantic video retrieval
- consistency checking
- video annotation
- event recognition
- video processing
- semantic search
- video shots
- saliency map
- low level features
- temporal information
- domain ontology
- semantic web
- multi modal
- computer vision