Bi-modal First Impressions Recognition Using Temporally Ordered Deep Audio and Stochastic Visual Features.
Arulkumar SubramaniamVismay PatelAshish MishraPrashanth BalasubramanianAnurag MittalPublished in: ECCV Workshops (3) (2016)
Keyphrases
- visual features
- visual information
- audio features
- visual data
- visual content
- temporal information
- image classification
- image search
- acoustic features
- low level
- image retrieval
- image annotation
- keywords
- multimedia
- image collections
- bag of features
- content based video retrieval
- visual similarity
- spatio temporal
- bridge the semantic gap
- semantic gap
- audio visual
- web images
- semantic concepts
- key frames
- image processing
- computer vision
- low level visual features
- object recognition
- global features
- low level features