Video Memorability Prediction From Jointly-learnt Semantic and Visual Features.
Iván Martín-FernándezRicardo KleinleinCristina Luna JiménezManuel Gil-MartínFernando Fernández MartínezPublished in: CBMI (2023)
Keyphrases
- visual features
- semantic concepts
- content based video retrieval
- key frames
- low level features
- semantic features
- video shots
- visual information
- image classification
- visual content
- semantic gap
- motion features
- semantic content
- visual data
- low level visual features
- image search
- low level
- human actions
- video database
- bridge the semantic gap
- image retrieval
- video content
- image annotation
- image collections
- keywords
- visual appearance
- visual concepts
- audio features
- video data
- textual descriptions
- video analysis
- bag of features
- video clips
- multi modal
- multimedia
- content based retrieval
- global features
- video retrieval
- visual and textual features
- web images
- low level features and high level
- co occurrence
- wordnet
- semantic information
- video streams
- visual similarity
- visual patterns
- audio visual