Multi-modal Video Topic Segmentation with Dual-Contrastive Domain Adaptation.
Linzi XingQuan Hung TranFabian CabaFranck DernoncourtSeunghyun YoonZhaowen WangTrung BuiGiuseppe CareniniPublished in: MMM (3) (2024)
Keyphrases
- multi modal
- domain adaptation
- topic segmentation
- semantic concepts
- cross domain
- multiple sources
- video content
- video data
- semi supervised learning
- semi supervised
- video sequences
- multimedia
- labeled data
- image annotation
- unlabeled data
- high dimensional
- target domain
- sentiment classification
- transfer learning
- knowledge transfer
- unsupervised learning
- document classification
- knn
- face recognition