.png){kind=icon}
.png){kind=icon}
Return
A heterogeneous deep consistent matrix factorization method for micro-video multi-label classification
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.131759.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We propose a novel heterogeneous deep consistent matrix factorization method to explore the instance-label consensual characteristics for micro-video multi-label classification. • We construct three inverse covariance estimation modules to capture the correlation structures of label semantics, instance-domain attributes and label-domain attributes, respectively. • Extensive experiments conducted on two available datasets demonstrate the superior performance against the state-of-the-art methods.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W