Is an object-centric video representation beneficial for transfer?

The objective of this work is to learn an object-centric video representation, with the aim of improving transferability to novel tasks, i.e., tasks different from the pre-training task of action classification. To this end, we introduce a new object-centric video recognition model based on a transf...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής
Κύριοι συγγραφείς: Zhang, C, Gupta, A, Zisserman, A
Μορφή: Conference item
Γλώσσα:English
Έκδοση: Springer 2023