Login / Signup
Description generation of open-domain videos incorporating multimodal features and bidirectional encoder.
Xiaotong Du
Jiabin Yuan
Hu Liu
Yuke Dai
Published in:
Vis. Comput. (2019)
Keyphrases
</>
open domain
low level
feature extraction
feature vectors
feature space
information extraction
co occurrence
feature set
text classification
image retrieval
video sequences
motion estimation
multi modal
video data
video frames
key frames
video clips
video analysis
feature selection