Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/107955
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wang, P. | - |
dc.contributor.author | Liu, L. | - |
dc.contributor.author | Shen, C. | - |
dc.contributor.author | Huang, Z. | - |
dc.contributor.author | Van Den Hengel, A. | - |
dc.contributor.author | Shen, H. | - |
dc.date.issued | 2016 | - |
dc.identifier.citation | Proceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016, vol.2016-December, pp.1573-1581 | - |
dc.identifier.isbn | 9781467388511 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/2440/107955 | - |
dc.description.abstract | This paper studies the challenging problem of identifying unusual instances of known objects in images within an "open world" setting. That is, we aim to find objects that are members of a known class, but which are not typical of that class. Thus the "unusual object" should be distinguished from both the "regular object" and the "other objects". Such unusual objects may be of interest in many applications such as surveillance or quality control. We propose to identify unusual objects by inspecting the distribution of object detection scores at multiple image regions. The key observation motivating our approach is that "regular object" images, "unusual object" images and "other objects" images exhibit different region-level scores in terms of both the score values and the spatial distributions. To model these distributions we propose to use Gaussian Processes (GP) to construct two separate generative models, one for the "regular object" and the other for the "other objects". More specifically, we design a new covariance function to simultaneously model the detection score at a single location and the score dependencies between multiple regions. We demonstrate that the proposed approach outperforms comparable methods on a new large dataset constructed for the purpose. | - |
dc.description.statementofresponsibility | Peng Wang, Lingqiao Liu, Chunhua Shen, Zi Huang, Anton van den Hengel, Heng Tao Shen | - |
dc.language.iso | en | - |
dc.publisher | IEEE | - |
dc.relation.ispartofseries | IEEE Conference on Computer Vision and Pattern Recognition | - |
dc.rights | © 2016 IEEE | - |
dc.source.uri | http://dx.doi.org/10.1109/cvpr.2016.174 | - |
dc.subject | Detectors, object recognition, proposals, computer vision, object detection, automobiles, computational modeling | - |
dc.title | What's wrong with that object? Identifying images of unusual objects by modelling the detection score distribution | - |
dc.type | Conference paper | - |
dc.contributor.conference | 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2016) (26 Jun 2016 - 1 Jul 2016 : Las Vegas, NV) | - |
dc.identifier.doi | 10.1109/CVPR.2016.174 | - |
pubs.publication-status | Published | - |
dc.identifier.orcid | Van Den Hengel, A. [0000-0003-3027-8364] | - |
Appears in Collections: | Aurora harvest 3 Computer Science publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
RA_hdl_107955.pdf Restricted Access | Restricted Access | 1.14 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.