BiTransformer: augmenting semantic context in video captioning via bidirectional decoder.

Maosheng Zhong Hao Zhang Yong Wang Hao Xiong

Published in: Mach. Vis. Appl. (2022)

Keyphrases

semantic context
video annotation
video data
key frames
video analysis
visual information
video content
video search
video streams
multimedia
visual data
video surveillance
video retrieval
video frames
image search
visual concepts
video processing
bag of words
higher level
video sequences