Device, system, and method of visual inference by collaborative composition
AssigneeYeda Research and Development Co. Ltd.
InventorsMichal Irani, Alon Faktor
Life of this patent
Estimating the term…
Abstract
Device, system, and method of visual inference by collaborative composition. A method of searching for similar target content-items for a plurality of source content-items, the method implementable on a computing device, comprises: for each of said plurality of source content-items, searching for similar target content-items in a dataset, while taking into account collaborative feedback exchanged among at least some of currently-searched said plurality of source content-items.
Claims26
A computer implemented method of searching for similar target content-items for a plurality of source content-items, all stored in at least one memory unit the method comprising:
- for each of said plurality of source content-items, searching for similar target content-items in a dataset, while taking into account collaborative feedback exchanged among at least some of currently-searched said plurality of source content-items;
- wherein said searching further comprising at least one of:
- measuring similarity between each one of said source content-items and a small subset of target content-items in said dataset, said small subset is unique to each one of said source content-items and is determined by said collaborative feedback;
- and
- computing similarity-by-composition by measuring similarity of detected shared regions among said source content-items and said target content-items.
A computing device, having one or more memory units, for searching for similar target content-items for a plurality of source content-items, all stored in at least one of said memory units, the computing device comprising:
- a searcher module, stored in at least one of said memory units, configured to search for each of said plurality of source content-items, for similar target content-items in a dataset, while taking into account collaborative feedback exchanged among at least some of currently-searched said plurality of source content-items;
- an affinity calculator, stored in at least one of said memory units, configured to measure similarity between each one of said source content-items and a small subset of target content-items in said dataset, said small subset is unique to each one of said source content-items and is determined by said collaborative feedback;
- and
- an output unit, configured to output searching results of said searching module.
Dependencies are inferred from the claim text.