Conference item icon

Conference item

Support-set bottlenecks for video-text representation learning

Abstract:

The dominant paradigm for learning video-text representations – noise contrastive learning – increases the similarity of the representations of pairs of samples that are known to be related, such as text and video from the same sample, and pushes away the representations of all other pairs. We posit that this last behaviour is too strict, enforcing dissimilar representations even for samples that are semantically-related – for example, visually similar videos or ones that share the same depic...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publication website:
https://openreview.net/forum?id=EqoXe2zmhrh

Authors


Expand authors...
Publisher:
OpenReview Publisher's website
Publication date:
2021-05-03
Acceptance date:
2021-01-07
Event title:
9th International Conference on Learning Representations (ICLR 2021)
Event location:
Virtual event
Event website:
https://iclr.cc/Conferences/2021
Event start date:
2021-05-03T00:00:00Z
Event end date:
2021-05-07T00:00:00Z
Language:
English
Keywords:
Pubs id:
1242718
Local pid:
pubs:1242718
Deposit date:
2022-03-08

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP