Show simple item record

dc.contributor.authorBuch, Shyamal
dc.contributor.authorEscorcia, Victor
dc.contributor.authorShen, Chuanqi
dc.contributor.authorGhanem, Bernard
dc.contributor.authorNiebles, Juan Carlos
dc.date.accessioned2018-01-15T06:35:10Z
dc.date.available2018-01-15T06:35:10Z
dc.date.issued2017-11-09
dc.identifier.citationBuch S, Escorcia V, Shen C, Ghanem B, Niebles JC (2017) SST: Single-Stream Temporal Action Proposals. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Available: http://dx.doi.org/10.1109/cvpr.2017.675.
dc.identifier.doi10.1109/cvpr.2017.675
dc.identifier.urihttp://hdl.handle.net/10754/626797
dc.description.abstractOur paper presents a new approach for temporal detection of human actions in long, untrimmed video sequences. We introduce Single-Stream Temporal Action Proposals (SST), a new effective and efficient deep architecture for the generation of temporal action proposals. Our network can run continuously in a single stream over very long input video sequences, without the need to divide input into short overlapping clips or temporal windows for batch processing. We demonstrate empirically that our model outperforms the state-of-the-art on the task of temporal action proposal generation, while achieving some of the fastest processing speeds in the literature. Finally, we demonstrate that using SST proposals in conjunction with existing action classifiers results in improved state-of-the-art temporal action detection performance.
dc.description.sponsorshipThis research was sponsored, in part, by the Stanford AI Lab-Toyota Center for Artificial Intelligence Research, Toyota Research Institute (TRI), and by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research. This article reflects the opinions and conclusions of its authors and not TRI or any other Toyota entity. We thank our anonymous reviewers, De-An Huang, Oliver Groth, Fabian Caba, Joseph Lim, Jingwei Ji, and Fei-Fei Li for helpful comments and discussion.
dc.publisherIEEE
dc.relation.urlhttp://ieeexplore.ieee.org/document/8100158/
dc.titleSST: Single-Stream Temporal Action Proposals
dc.typeConference Paper
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentElectrical Engineering Program
dc.contributor.departmentVisual Computing Center (VCC)
dc.identifier.journal2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
dc.contributor.institutionStanford University
kaust.personEscorcia, Victor
kaust.personGhanem, Bernard


This item appears in the following Collection(s)

Show simple item record