Towards Bridging Video and Language by Caption Generation and Sentence Localization.
Shaoxiang ChenPublished in: ACM Multimedia (2021)
Keyphrases
- natural language
- text generation
- video retrieval
- activity detection
- video sequences
- news video
- video data
- programming language
- video database
- video shots
- video content
- target language
- video frames
- language learning
- video streams
- syntactic parsing
- multimedia
- natural language generation
- caption text
- video analysis
- video clips
- video images
- linguistic knowledge
- word order
- real time
- parallel corpus
- language processing
- key frames
- event detection
- localization method
- semantic information
- visual features
- mobile robot
- probabilistic context free grammars
- syntactic categories