Level-wise aligned dual networks for text–video retrieval

Level-wise aligned dual networks for text–video retrieval

Abstract The vast amount of videos on the Internet makes efficient and accurate text–video retrieval tasks increasingly important. The current methods leverage a high-dimensional space to align video and text for these tasks. However, a high-dimensional space cannot fully use different levels of inf...

Celý popis

Podrobná bibliografie
Hlavní autoři: Qiubin Lin, Wenming Cao, Zhiquan He
Médium: Článek
Jazyk:English
Vydáno: SpringerOpen 2022-07-01
Edice:EURASIP Journal on Advances in Signal Processing
Témata:
Text–video retrieval
Level-wise aligned mechanism
Semantic space
Latent space
On-line přístup:https://doi.org/10.1186/s13634-022-00887-y

Internet

https://doi.org/10.1186/s13634-022-00887-y

Podobné jednotky