Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/142119
Title: Temporally enhanced image object proposals for online video object and action detections
Authors: Yang, Jiong
Yuan, Junsong
Keywords: Engineering::Computer science and engineering
Issue Date: 2018
Source: Yang, J., & Yuan, J. (2018). Temporally enhanced image object proposals for online video object and action detections. Journal of Visual Communication and Image Representation, 53, 245-256. doi:10.1016/j.jvcir.2018.03.018
Journal: Journal of Visual Communication and Image Representation
Abstract: Despite the recent advances of image object proposals (IOPs) and video object proposals (VOPs), it still remains a challenge to apply them to online video object/action detection. To address this problem, we propose a novel form of image object proposals, Temporally Enhanced Image Object Proposals (TE-IOPs), for online video object/action detection. The proposed TE-IOPs augment the existing IOPs at every frame by their temporal dynamics in the past few frames. We develop a dynamic programming scheme to efficiently search for such TE-IOPs in an online manner. Compared with existing VOPs that cannot run online, our TE-IOPs can be used for online detection. Compared with IOPs, our TE-IOPs bring rich temporal dynamics with minor computational cost. Experiments on benchmark datasets validate the superior performance of the proposed TE-IOPs over existing IOPs and VOPs, in terms of both the proposal re-ranking and the application of online action detection.
URI: https://hdl.handle.net/10356/142119
ISSN: 1047-3203
DOI: 10.1016/j.jvcir.2018.03.018
Rights: © 2018 Elsevier Inc. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:IGS Journal Articles

Page view(s)

37
Updated on Apr 13, 2021

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.