English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos

MPS-Authors
There are no MPG-Authors available
External Resource
No external resources are shared
Fulltext (public)

arXiv:1507.05738.pdf
(Preprint), 5MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Yeung, S., Russakovsky, O., Jin, N., Andriluka, M., Mori, G., & Fei-Fei, L. (2015). Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos. Retrieved from http://arxiv.org/abs/1507.05738.


Cite as: http://hdl.handle.net/11858/00-001M-0000-002A-0AA0-3
Abstract
Every moment counts in action recognition. A comprehensive understanding of human activity in video requires labeling every frame according to the actions occurring, placing multiple labels densely over a video sequence. To study this problem we extend the existing THUMOS dataset and introduce MultiTHUMOS, a new dataset of dense labels over unconstrained internet videos. Modeling multiple, dense labels benefits from temporal relations within and across classes. We define a novel variant of long short-term memory (LSTM) deep networks for modeling these temporal relations via multiple input and output connections. We show that this model improves action labeling accuracy and further enables deeper understanding tasks ranging from structured retrieval to action prediction.