Dense Video Captioning Using Unsupervised Semantic Information.
Valter Luís Estevam JuniorRayson LarocaHélio PedriniDavid MenottiPublished in: CoRR (2021)
Keyphrases
- semantic information
- semantic concepts
- wordnet
- semantic analysis
- keywords
- semantic features
- video streams
- video sequences
- domain knowledge
- video content
- semantic knowledge
- contextual information
- structural information
- metadata
- semantic similarity
- textual descriptions
- syntactic information
- video data
- background knowledge
- domain ontology
- video frames
- semantic meaning
- low level features
- semantic relatedness
- high level
- semantic tags
- video analysis
- visual information
- video retrieval
- multimedia data
- data sets
- low level
- xml documents
- multimedia
- data mining
- video clips
- image classification
- semi supervised
- semantic content
- decision trees
- machine learning