Weakly-supervised Audio Separation via Bi-modal Semantic Similarity.
Tanvir MahmudSaeed AmizadehKazuhito KoishidaDiana MarculescuPublished in: CoRR (2024)
Keyphrases
- semantic similarity
- weakly supervised
- co occurrence
- relation extraction
- semantic features
- topic models
- wordnet
- similarity measure
- object class
- superpixels
- semi supervised
- semantic information
- visual information
- named entities
- word sense disambiguation
- domain knowledge
- object segmentation
- visual similarity
- computer vision
- natural language processing
- object detection