--- abstract: "In order to perform object recognition, it is necessary to form perceptual representations that are sufficiently specific to distinguish between objects, but that are also sufficiently flexible to generalise across changes in location, rotation and scale. A standard method for learning perceptual representations that are invariant to viewpoint is to form temporal associations across image sequences showing object transformations. However, this method requires that individual stimuli are presented in isolation and is therefore unlikely to succeed in real-world applications where multiple objects can co-occur in the visual input. This article proposes a simple modification to the learning method, that can overcome this limitation, and results in more robust learning of invariant representations.\n" altloc: - file:///home/mike/WebPages/Doc/tpami05.pdf chapter: ~ commentary: ~ commref: ~ confdates: ~ conference: ~ confloc: ~ contact_email: ~ creators_id: [] creators_name: - family: Spratling given: Michael honourific: Dr lineage: '' date: 2005 date_type: published datestamp: 2006-05-25 department: ~ dir: disk0/00/00/48/84 edit_lock_since: ~ edit_lock_until: ~ edit_lock_user: ~ editors_id: [] editors_name: [] eprint_status: archive eprintid: 4884 fileinfo: /style/images/fileicons/application_pdf.png;/4884/1/tpami05.pdf full_text_status: public importid: ~ institution: ~ isbn: ~ ispublished: pub issn: ~ item_issues_comment: [] item_issues_count: 0 item_issues_description: [] item_issues_id: [] item_issues_reported_by: [] item_issues_resolved_by: [] item_issues_status: [] item_issues_timestamp: [] item_issues_type: [] keywords: Computational models of vision; Neural Nets; invariance; object recognition lastmod: 2011-03-11 08:56:26 latitude: ~ longitude: ~ metadata_visibility: show note: ~ number: 5 pagerange: 753-761 pubdom: FALSE publication: IEEE Transactions on Pattern Analysis and Machine Intelligence publisher: ~ refereed: TRUE referencetext: ~ relation_type: [] relation_uri: [] reportno: ~ rev_number: 12 series: ~ source: ~ status_changed: 2007-09-12 17:03:18 subjects: - neuro-mod - comp-sci-mach-vis - comp-sci-neural-nets succeeds: ~ suggestions: ~ sword_depositor: ~ sword_slug: ~ thesistype: ~ title: Learning viewpoint invariant perceptual representations from cluttered images type: journalp userid: 1040 volume: 27