Show simple item record

dc.contributor.advisorGhanem, Bernard*
dc.contributor.authorAlwassel, Humam*
dc.date.accessioned2018-04-29T06:44:10Z
dc.date.available2018-04-29T06:44:10Z
dc.date.issued2018-04-17
dc.identifier.urihttp://hdl.handle.net/10754/627678
dc.description.abstractState-of-the-art temporal action detectors inefficiently search the entire video for specific actions. Despite the encouraging progress these methods achieve, it is crucial to design automated approaches that only explore parts of the video which are the most relevant to the actions being searched. To address this need, we propose the new problem of action spotting in videos, which we define as finding a specific action in a video while observing a small portion of that video. Inspired by the observation that humans are extremely efficient and accurate in spotting and finding action instances in a video, we propose Action Search, a novel Recurrent Neural Network approach that mimics the way humans spot actions. Moreover, to address the absence of data recording the behavior of human annotators, we put forward the Human Searches dataset, which compiles the search sequences employed by human annotators spotting actions in the AVA and THUMOS14 datasets. We consider temporal action localization as an application of the action spotting problem. Experiments on the THUMOS14 dataset reveal that our model is not only able to explore the video efficiently (observing on average 17.3% of the video) but it also accurately finds human activities with 30.8% mAP (0.5 tIoU), outperforming state-of-the-art methodsen
dc.language.isoenen
dc.subjectvideo understandingen
dc.subjectaction localizationen
dc.subjectaction spottingen
dc.titleEfficient Temporal Action Localization in Videosen
dc.typeThesisen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division*
thesis.degree.grantorKing Abdullah University of Science and Technologyen
dc.contributor.committeememberHeidrich, Wolfgang*
dc.contributor.committeememberWonka, Peter*
thesis.degree.disciplineComputer Scienceen
thesis.degree.nameMaster of Scienceen


Files in this item

Thumbnail
Name:
HumamAlwasselThesis.pdf
Size:
2.438Mb
Format:
PDF
Description:
Thesis
Embargo End Date:
2019-04-17
Thumbnail
Name:
MS_thesis_approval_HumamAlwass ...
Size:
721.9Kb
Format:
PDF
Thumbnail
Name:
copyright_HumamAlwassel.pdf
Size:
873.9Kb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record