Can I read Self-Regulated Learning for Egocentric Video Activity Anticipation on EtoBox?

Self-Regulated Learning for Egocentric Video Activity Anticipation by Zhaobo Qi; Shuhui Wang; Chi Su; Li Su; Qingming Huang; Qi Tian is a Computer Science article available to read on EtoBox.

What is Self-Regulated Learning for Egocentric Video Activity Anticipation about?

Future activity anticipation is a challenging problem in egocentric vision. As a standard future activity anticipation paradigm, recursive sequence prediction suffers from the accumulation of errors. To address this problem, we propose a simple and effective Self-Regulated Learning framework, which aims to regulate the intermediate representation consecutively to produce representation that (a) emphasizes the novel information in the frame of the current time-stamp in contrast to previously observed content, and (b) reflects its correlation with previously observed frames. The former is achieved by minimizing a contrastive loss, and the latter can be achieved by a dynamic reweighing mechanism to attend to informative frames in the observed content with a similarity comparison between feature of the current frame and observed frames. The learned final video representation can be further enhanced by multi-task learning which performs joint feature learning on the target activity labels and the automatically detected action and object class tokens. SRL sharply outperforms existing state-of-the-art in most cases on two egocentric video datasets and two third-person video datasets. Its

Who reads Self-Regulated Learning for Egocentric Video Activity Anticipation?

Author

Zhaobo Qi; Shuhui Wang; Chi Su; Li Su; Qingming Huang; Qi Tian

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Published

2023

Language

EN

Field

Computer Science (Physical Sciences)