VideoCLIP: A Cross-Attention Model for Fast Video-Text Retrieval Task with Image CLIP.

Yikang Li Jenhao Hsiao Chiuman Ho

Published in: ICMR (2022)

Keyphrases

image data
multiscale
image analysis
image classification
single image
probabilistic model
video data
image segmentation
similarity measure
image retrieval
image features
input image
video streams
video clips
statistical model
energy function
feature points
high level