File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICCV.2017.45
- Scopus: eid_2-s2.0-85041892183
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: A Revisit of Sparse Coding Based Anomaly Detection in Stacked RNN Framework
Title | A Revisit of Sparse Coding Based Anomaly Detection in Stacked RNN Framework |
---|---|
Authors | |
Issue Date | 2017 |
Citation | Proceedings of the IEEE International Conference on Computer Vision, 2017, v. 2017-October, p. 341-349 How to Cite? |
Abstract | Motivated by the capability of sparse coding based anomaly detection, we propose a Temporally-coherent Sparse Coding (TSC) where we enforce similar neighbouring frames be encoded with similar reconstruction coefficients. Then we map the TSC with a special type of stacked Recurrent Neural Network (sRNN). By taking advantage of sRNN in learning all parameters simultaneously, the nontrivial hyper-parameter selection to TSC can be avoided, meanwhile with a shallow sRNN, the reconstruction coefficients can be inferred within a forward pass, which reduces the computational cost for learning sparse coefficients. The contributions of this paper are two-fold: i) We propose a TSC, which can be mapped to a sRNN which facilitates the parameter optimization and accelerates the anomaly prediction. ii) We build a very large dataset which is even larger than the summation of all existing dataset for anomaly detection in terms of both the volume of data and the diversity of scenes. Extensive experiments on both a toy dataset and real datasets demonstrate that our TSC based and sRNN based method consistently outperform existing methods, which validates the effectiveness of our method. |
Persistent Identifier | http://hdl.handle.net/10722/345096 |
ISSN | 2023 SCImago Journal Rankings: 12.263 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Luo, Weixin | - |
dc.contributor.author | Liu, Wen | - |
dc.contributor.author | Gao, Shenghua | - |
dc.date.accessioned | 2024-08-15T09:25:12Z | - |
dc.date.available | 2024-08-15T09:25:12Z | - |
dc.date.issued | 2017 | - |
dc.identifier.citation | Proceedings of the IEEE International Conference on Computer Vision, 2017, v. 2017-October, p. 341-349 | - |
dc.identifier.issn | 1550-5499 | - |
dc.identifier.uri | http://hdl.handle.net/10722/345096 | - |
dc.description.abstract | Motivated by the capability of sparse coding based anomaly detection, we propose a Temporally-coherent Sparse Coding (TSC) where we enforce similar neighbouring frames be encoded with similar reconstruction coefficients. Then we map the TSC with a special type of stacked Recurrent Neural Network (sRNN). By taking advantage of sRNN in learning all parameters simultaneously, the nontrivial hyper-parameter selection to TSC can be avoided, meanwhile with a shallow sRNN, the reconstruction coefficients can be inferred within a forward pass, which reduces the computational cost for learning sparse coefficients. The contributions of this paper are two-fold: i) We propose a TSC, which can be mapped to a sRNN which facilitates the parameter optimization and accelerates the anomaly prediction. ii) We build a very large dataset which is even larger than the summation of all existing dataset for anomaly detection in terms of both the volume of data and the diversity of scenes. Extensive experiments on both a toy dataset and real datasets demonstrate that our TSC based and sRNN based method consistently outperform existing methods, which validates the effectiveness of our method. | - |
dc.language | eng | - |
dc.relation.ispartof | Proceedings of the IEEE International Conference on Computer Vision | - |
dc.title | A Revisit of Sparse Coding Based Anomaly Detection in Stacked RNN Framework | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/ICCV.2017.45 | - |
dc.identifier.scopus | eid_2-s2.0-85041892183 | - |
dc.identifier.volume | 2017-October | - |
dc.identifier.spage | 341 | - |
dc.identifier.epage | 349 | - |