papers AI Learner
The Github is limit! Click to go to the new site.

Hierarchical Video Understanding

2018-09-04
Farzaneh Mahdisoltani, Roland Memisevic, David Fleet

Abstract

We introduce a hierarchical architecture for video understanding that exploits the structure of real world actions by capturing targets at different levels of granularity. We design the model such that it first learns simpler coarse-grained tasks, and then moves on to learn more fine-grained targets. The model is trained with a joint loss on different granularity levels. We demonstrate empirical results on the recent release of Something-Something dataset, which provides a hierarchy of targets, namely coarse-grained action groups, fine-grained action categories, and captions. Experiments suggest that models that exploit targets at different levels of granularity achieve better performance on all levels.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1809.03316

PDF

https://arxiv.org/pdf/1809.03316


Similar Posts

Comments