Audio Visual Scene-Aware Dialog (AVSD) Challenge at DSTC7.
Huda AlAmriVincent CartillierRaphael Gontijo LopesAbhishek DasJue WangIrfan EssaDhruv BatraDevi ParikhAnoop CherianTim K. MarksChiori HoriPublished in: CoRR (2018)
Keyphrases
- audio visual
- visual data
- video scene
- multi modal
- visual information
- emotion recognition
- multi stream
- video sequences
- three dimensional
- video summarization
- multimedia
- person authentication
- temporal context
- image sequences
- user interface
- natural language
- audio visual speech recognition
- video data
- input image
- multimodal fusion
- image set
- data sets
- domain knowledge
- moving objects
- feature selection