{"type":"ScholarlyArticle","title":"A Parallel Computation that Assigns Canonical Object-Based Frames of Reference","authors":[{"name":"Geoffrey E. Hinton","slug":"geoffrey-e-hinton","given":"Geoffrey E.","family":"Hinton","affiliation":""}],"abstract":"A. vievpoint-independent description of the shape of en object can be generated by imposing a canonical frame of reference on the object and describing the spatial dispositions of the parte relative to this object-based frame. When a familiar object is in an unusual orientation, the deciding factor in the choice of the canonical object-based frame 11ay be the fact that relative to this frame the object has a familiar shape description. This may suggest that we first hypothesise an object-based frame and then test the resultant shape description for familiarity. However, it is possible to organise the interactions between units in a parallel network so that the pattern of activity in the network simultaneously converges on a representation of the shape and a representation of the objectbased frame of reference. The connections in the network are determined by the constraints inherent in the image formation process.","doi":null,"url":"https://ijcai.org/proceedings/1981/129","pdf":"https://ijcai.org/proceedings/1981/0129.pdf","markdown":"https://ijcai.org/proceedings/1981/129.md","bibtex":"https://ijcai.org/proceedings/1981/bibtex/129","volume":{"slug":"1981","title":"Proceedings of the Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 1981","url":"https://ijcai.org/proceedings/1981/","year":1981,"location":"Vancouver, British Columbia, Canada","dates":"24-28 August 1981","editors":"Roger C. Schank","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Vision: 3-d","track":"Vision: 3-d","number":129,"pages":{"first":683,"last":684},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}