Enabling Weakly-Supervised Temporal Action Localization from On-Device Learning of the Video Stream. (arXiv:2208.12673v1 [cs.CV])

Detecting actions in videos have been widely applied in on-device
applications. Practical on-device videos are always untrimmed with both action
and background. It is desirable for a model to both recognize the class of
action and localize the temporal position where the action happens. Such a task
is called temporal action location (TAL), which is always trained on the cloud
where multiple untrimmed videos are collected and labeled. It is desirable for
a TAL model to continuously and locally learn …

arxiv cv enabling learning localization on-device learning temporal video weakly-supervised