Exploration of Visual Features and their weighted-additive fusion for Video Captioning.
Praveen S. VAkhilesh BharadwajHarsh RajJanhavi DadhaniaGanesh Samarth C. A.Nikhil PareekS. R. M. PrasannaPublished in: CoRR (2021)
Keyphrases
- visual features
- key frames
- late fusion
- semantic concepts
- video shots
- motion features
- image classification
- human actions
- visual data
- visual information
- visual content
- content based video retrieval
- image retrieval
- keywords
- image search
- video sequences
- low level features
- image annotation
- video streams
- video data
- video clips
- low level
- image collections
- audio features
- video database
- visual appearance
- bridge the semantic gap
- video retrieval
- video content
- global features
- bag of features
- multimedia
- semantic gap
- data fusion
- multi modal
- web images
- visual similarity
- multimedia data
- video frames
- visual descriptors
- visual properties