Video2vec: Learning semantic spatio-temporal embeddings for video representation.

Sheng-hung Hu Yikang Li Baoxin Li

Published in: ICPR (2016)

Keyphrases

video representation
spatio temporal
space time
video analysis
video streams
key frames
dynamic textures
multimedia
similarity measure
prior knowledge
video database
video data
video content
semantic information
face recognition
video retrieval
video sequences
generative model
optical flow
moving objects