Lama alssum

OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detection featured image
Deep Learning

OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detection

Temporal action detection (TAD) is a fundamental video understanding task that aims to identify human actions and localize their temporal boundaries in videos. Although this field …

Shuming liu
•
Read more
Just a Glimpse: Rethinking Temporal Information for Video Continual Learning featured image
Deep Learning

Just a Glimpse: Rethinking Temporal Information for Video Continual Learning

Class-incremental learning is one of the most important settings for the study of Continual Learning, as it closely resembles real-world application scenarios. With constrained …

Lama alssum
•
Read more