VideoBERT: A Joint Model for Video and Language Representation Learning.
Chen SunAustin MyersCarl VondrickKevin MurphyCordelia SchmidPublished in: ICCV (2019)
Keyphrases
- mathematical model
- computational model
- prior knowledge
- learning models
- learning scheme
- inference process
- objective function
- formal representation
- learning algorithm
- real time
- similarity measure
- learning process
- learning systems
- spatial and temporal
- learning tasks
- learned models
- representation language
- long term memory
- structured representations
- programming language
- supervised learning
- object oriented
- artificial neural networks
- high level
- multimedia
- machine learning