Cross-modal Token Selection for Video Understanding.

Liyong Pan Zechao Li Henghao Zhao Rui Yan

Published in: HCMA@MM (2022)

Keyphrases

cross modal
multi modal
visual data
multimedia retrieval
video data
video content
video sequences
visual recognition
semantic concepts
video streams
multimedia databases
multimedia
multimedia data
video frames
image data
image retrieval
space time
video analysis
image database
multimedia documents
image sequences