Bridging High-Quality Audio and Video via Language for Sound Effects Retrieval from Visual Queries.
Julia WilkinsJustin SalamonMagdalena FuentesJuan Pablo BelloOriol NietoPublished in: CoRR (2023)
Keyphrases
- content based video retrieval
- audio content
- video indexing and retrieval
- high quality
- visual query language
- multimedia information
- visual data
- multimedia
- audio visual content
- content based retrieval
- video indexing
- query formulation
- multimedia data
- video content
- retrieval systems
- cross modal
- lifelog
- video database
- video data
- video retrieval
- visual information
- visual features
- multimedia databases
- news video
- query language
- audio video
- retrieval process
- boolean queries
- video search
- audio signal
- audio features
- video analysis
- monolingual retrieval
- audio visual
- retrieval quality
- multimedia content
- digital video
- video shots
- video streams
- audio recordings
- image database
- image retrieval
- video files
- range queries
- query processing
- video sequences
- music information retrieval
- information retrieval
- visual concepts
- media streams
- natural language
- soccer video
- visual similarity
- low level
- web search engines
- textual descriptions
- concept detectors
- broadcast news
- cross language retrieval
- query terms
- retrieval model
- document retrieval
- information retrieval systems
- query expansion
- user queries
- indexing structure
- audio files
- semantic content