Please use this identifier to cite or link to this item:
Title: Action detection in complex scenes with spatial and temporal ambiguities
Authors: Hu, Y.
Cao, L.
Lv, F.
Yan, S. 
Gong, Y.
Huang, T.S.
Issue Date: 2009
Citation: Hu, Y., Cao, L., Lv, F., Yan, S., Gong, Y., Huang, T.S. (2009). Action detection in complex scenes with spatial and temporal ambiguities. Proceedings of the IEEE International Conference on Computer Vision : 128-135. ScholarBank@NUS Repository.
Abstract: In this paper, we investigate the detection of semantic human actions in complex scenes. Unlike conventional action recognition in well-controlled environments, action detection in complex scenes suffers from cluttered backgrounds, heavy crowds, occluded bodies, and spatial-temporal boundary ambiguities caused by imperfect human detection and tracking. Conventional algorithms are likely to fail with such spatial-temporal ambiguities. In this work, the candidate regions of an action are treated as a bag of instances. Then a novel multiple-instance learning framework, named SMILE-SVM (Simulated annealingMultiple Instance LEarning Support Vector Machines), is presented for learning human action detector based on imprecise action locations. SMILE-SVM is extensively evaluated with satisfactory performances on two tasks: 1) human action detection on a public video action database with cluttered backgrounds, and 2) a real world problem of detecting whether the customers in a shopping mall show an intention to purchase the merchandise on shelf (even if they didn't buy it eventually). In addition, the complementary nature of motion and appearance features in action detection are also validated, demonstrating a boosted performance in our experiments. ©2009 IEEE.
Source Title: Proceedings of the IEEE International Conference on Computer Vision
ISBN: 9781424444205
DOI: 10.1109/ICCV.2009.5459153
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.


checked on Oct 15, 2021


checked on Oct 15, 2021

Page view(s)

checked on Oct 14, 2021

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.