Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos

Multimodal self-supervised learning is getting more and more attention as it allows not only to train large networks without human supervision but also to search and retrieve data across various modalities. In this context, this paper proposes a framework that, starting from a pre-trained backbone,...

Full description

Saved in:
Bibliographic Details
Main Authors: Chen, Brian, Rouditchenko, Andrew, Duarte, Kevin, Kuehne, Hilde, Thomas, Samuel, Boggust, Angie, Panda, Rameswar, Kingsbury, Brian, Feris, Rogerio, Harwath, David, Glass, James, Picheny, Michael, Chang, Shih-Fu
Format: Conference Proceeding
Language:English
Subjects:
Annotations
Computer vision
Image and video retrieval
Location awareness
Optical losses
Pipelines
Semantics
Training
Transfer/Low-shot/Semi/Unsupervised Learning
Video analysis and understanding
Vision + language
Vision + other modalities
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!