Quantifying the visual concreteness of words and topics in multimodal datasets.
Jack HesselDavid M. MimnoLillian LeePublished in: CoRR (2018)
Keyphrases
- keywords
- multi modal
- visual features
- latent topics
- text documents
- information retrieval
- data sets
- multimodal information
- latent dirichlet allocation
- word sense disambiguation
- text corpora
- visual cues
- related words
- text mining
- cross modal
- short texts
- statistical topic models
- lda model
- topic hierarchy
- short text
- topic detection
- word segmentation
- video search
- topic modeling
- text data
- visual information
- benchmark datasets
- probabilistic model