Bi-modal First Impressions Recognition using Temporally Ordered Deep Audio and Stochastic Visual Features.
Arulkumar SubramaniamVismay PatelAshish MishraPrashanth BalasubramanianAnurag MittalPublished in: CoRR (2016)
Keyphrases
- visual features
- visual information
- visual data
- audio features
- image classification
- temporal information
- visual content
- image retrieval
- audio visual
- low level
- image search
- spatio temporal
- low level features
- acoustic features
- content based video retrieval
- image collections
- keywords
- multimedia
- image annotation
- video shots
- bag of features
- visual appearance
- web images
- global features
- key frames
- textual features
- visual descriptors
- low level visual features
- machine learning
- high level
- semantic gap
- semantic similarity