Interaction augmented transformer with decoupled decoding for video captioning
Tao Jin, Zhou Zhao, Peng Wang, Jun Yu, Fei Wu
Topics & Concepts
Closed captioningDecoding methodsComputer scienceTransformerArtificial intelligenceSpeech recognitionComputer visionTelecommunicationsElectrical engineeringVoltageImage (mathematics)EngineeringMultimodal Machine Learning ApplicationsVideo Analysis and SummarizationSubtitles and Audiovisual Media