Efficiently identifying images, videos, songs or documents most relevant to the user using binary search trees on attributes for guiding relevance feedback

摘要

A method, system and computer program product for efficiently identifying images, videos, audio files or documents relevant to a user using binary search trees in attribute space for guiding relevance feedback. A binary tree is constructed for each relative attribute of interest. A “pivot exemplar” (at a node of the binary tree) is set for each relative attribute's binary tree as corresponding to the database image, video, audio file or document with a median relative attribute value among that subtree's child examples. A pivot exemplar out of the available current pivot exemplars that has the highest expected information gain is selected to be provided to the user. Comparative attribute feedback is then received from the user regarding whether a degree of the attribute in the user's target image, video, audio file or document is more, less or equal with the attribute displayed in the selected pivot exemplar.

主权项

1. A method for efficiently identifying images, videos, audio files or documents relevant to a user using attribute binary trees for guiding relevance feedback, the method comprising:
constructing a binary search tree for each relative attribute of interest in a pool of database images, videos, audio files or documents; setting a current pivot exemplar for each binary tree as corresponding to a database image, video, audio file or document with a median relative attribute value among all remaining database items in a subtree; predicting an information gain that would result from asking a user how a user's target image, video, audio file or document compares to each pivot exemplar of a plurality of pivot exemplars, wherein said comparison is made in terms of an attribute associated with that pivot's binary tree; providing a pivot exemplar deemed most informative from among said plurality of pivot exemplars to a user to provide a comparison between said attribute in said user's target image, video, audio file or document and in said current pivot exemplar; and receiving, by a processor, comparative attribute feedback from said user regarding whether a degree of said attribute in said user's target image, video, audio file or document is more, less or equal with said attribute displayed in said provided pivot exemplar.