Media tag recommendation technologies
First Claim
Patent Images
1. A tag recommendation system comprising:
- a computing device;
a tag selection element implemented at least in part by the computing device and configured for selecting a plurality of candidate media/tag pairs wherein a candidate tag of each of the candidate media/tag pairs exhibits raw co-occurrence with a target tag of a target media/tag pair;
a tag co-occurrence normalization element configured for processing each of the plurality of candidate media/tag pairs against the target media/tag pair resulting in corresponding tag co-occurrence (“
TC”
) relevance measures wherein the TC relevance measures are in a semantic domain;
a visual language modeling element configured for generating a candidate visual language model (“
VLM”
) for each candidate tag of the plurality of candidate media/tag pairs and a target VLM for a target tag of the target media/tag pair, and further configured for processing each of the candidate VLMs against the target VLM resulting in corresponding tag content correlation (“
TCC”
) relevance measures wherein such relevance measures are in a visual domain;
a visual correlation element configured for processing each of the candidate VLMs against the target VLM resulting in corresponding image-conditioned tag correlation (“
ITC”
) relevance measures wherein the ITC relevance measures are in a visual domain, wherein the ITC relevance measures are based at least in part on a distance between the target tag and at least one candidate tag, and wherein the distance is an asymmetric distance or a symmetric distance, and wherein the asymmetric distance defined as
2 Assignments
0 Petitions
Accused Products
Abstract
Technologies for recommending relevant tags for the tagging of media based on one or more initial tags provided for the media and based on a large quantity of other tagged media. Sample media as candidates for recommendation are provided by a set of weak rankers based on corresponding relevance measures in semantic and visual domains. The various samples provided by the weak rankers are then ranked based on relative order to provide a list of recommended tags for the media. The weak rankers provide sample tags based on relevance measures including tag co-occurrence, tag content correlation, and image-conditioned tag correlation.
14 Citations
16 Claims
-
1. A tag recommendation system comprising:
-
a computing device; a tag selection element implemented at least in part by the computing device and configured for selecting a plurality of candidate media/tag pairs wherein a candidate tag of each of the candidate media/tag pairs exhibits raw co-occurrence with a target tag of a target media/tag pair; a tag co-occurrence normalization element configured for processing each of the plurality of candidate media/tag pairs against the target media/tag pair resulting in corresponding tag co-occurrence (“
TC”
) relevance measures wherein the TC relevance measures are in a semantic domain;a visual language modeling element configured for generating a candidate visual language model (“
VLM”
) for each candidate tag of the plurality of candidate media/tag pairs and a target VLM for a target tag of the target media/tag pair, and further configured for processing each of the candidate VLMs against the target VLM resulting in corresponding tag content correlation (“
TCC”
) relevance measures wherein such relevance measures are in a visual domain;a visual correlation element configured for processing each of the candidate VLMs against the target VLM resulting in corresponding image-conditioned tag correlation (“
ITC”
) relevance measures wherein the ITC relevance measures are in a visual domain, wherein the ITC relevance measures are based at least in part on a distance between the target tag and at least one candidate tag, and wherein the distance is an asymmetric distance or a symmetric distance, and wherein the asymmetric distance defined as - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A method for generating an image-conditioned tag correlation (“
- ITC”
) relevance measure, the method comprising;generating, by a computing device, a target visual language model (“
VLM”
) for a target tag ti of a target media/tag pair;generating a candidate VLM for a candidate tag tj of a plurality of candidate media/tag pairs wherein the candidate tag tj co-occurs with the target tag ti of the target media/tag pair; defining a similarity between a target media it stance of the target media/tag pair and a candidate media instance of the candidate media/tag pair as likelihood ; defining a distance between ti and tj that is the inter-product of two likelihood vectors of likelihood between a target media of the target media/tag pair and tags ti and tj, wherein the distance is an asymmetric distance or a symmetric distance, and wherein the asymmetric distance defined as - View Dependent Claims (10)
- ITC”
-
11. A method for combining multi-domain relevance measures provided by a plurality of weak rankers, the method comprising:
defining an instance space that is comprised of a plurality of sets, each set being a set of instances provided by a distinct weak ranker of the plurality of the weak rankers, each instance of a set of instances being a sample tag from a media/tag pair, wherein a first weak ranker of the plurality of the weak rankers provides a first set of instances based on tag co-occurrence (“
TC”
) relevance measures, and a second weak ranker of the plurality of the weak rankers provides a second set of instances based on tag content correlation (“
TCC”
) relevance measures, and a third weak ranker of the plurality of the weak rankers provides a third set of instances based on image-conditioned tad correlation (“
ITC”
) relevance measures, wherein the ITC relevance measures are based at least in part on a distance between a target tag and at least one candidate tag, and wherein the distance is an asymmetric distance or a symmetric distance, and wherein the asymmetric distance defined as- View Dependent Claims (12, 13, 14, 15, 16)
Specification