Systems and methods for generating a high-level visual vocabulary
First Claim
Patent Images
1. A method comprising:
- generating inter-visual-word relationships between a plurality of visual words based on visual word-label relationships, wherein the visual word-label relationships are based on co-occurrences of respective visual words and labels in one or more images, and wherein the inter-visual word relationships are based on scores between the visual word-label relationships of respective visual words;
mapping the visual words to a vector space based on the inter-visual-word relationships; and
generating high-level visual words in the vector space.
1 Assignment
0 Petitions
Accused Products
Abstract
Systems and methods for learning a high-level visual vocabulary generate inter-visual-word relationships between a plurality of visual words based on visual word-label relationships, map the visual words to a vector space based on the inter-visual word relationships, and generate high-level visual words in the vector space.
-
Citations
13 Claims
-
1. A method comprising:
- generating inter-visual-word relationships between a plurality of visual words based on visual word-label relationships, wherein the visual word-label relationships are based on co-occurrences of respective visual words and labels in one or more images, and wherein the inter-visual word relationships are based on scores between the visual word-label relationships of respective visual words;
mapping the visual words to a vector space based on the inter-visual-word relationships; and
generating high-level visual words in the vector space. - View Dependent Claims (2, 3, 4, 5, 6, 7)
- generating inter-visual-word relationships between a plurality of visual words based on visual word-label relationships, wherein the visual word-label relationships are based on co-occurrences of respective visual words and labels in one or more images, and wherein the inter-visual word relationships are based on scores between the visual word-label relationships of respective visual words;
-
8. One or more non-transitory computer-readable media storing instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform operations comprising:
- generating inter-visual-word relationships between a plurality of visual words based on visual word-label relationships, wherein the visual word-label relationships are based on co-occurrences of respective visual words and labels in one or more images, and wherein the inter-visual word relationships are based on scores between the visual word-label relationships of respective visual words;
mapping the visual words to a vector space based on the inter-visual-word relationships; and
generating high-level visual words in the vector space based on respective positions of the visual words in the vector space. - View Dependent Claims (9, 10, 11)
- generating inter-visual-word relationships between a plurality of visual words based on visual word-label relationships, wherein the visual word-label relationships are based on co-occurrences of respective visual words and labels in one or more images, and wherein the inter-visual word relationships are based on scores between the visual word-label relationships of respective visual words;
-
12. A method comprising:
- generating inter-visual-word relationships between a plurality of visual words;
generating sets of importance weights for the visual words, wherein a set of importance weights includes a respective weight for each of the visual words;
mapping the visual words to one or more vector spaces based on the inter-visual word relationships and on the sets of importance weights, wherein each vector space corresponds to a respective one of the sets of importance weights;
generating high-level visual words in the plurality of vector spaces;
assigning a respective importance score to each of the high-level visual words; and
selecting high-level visual words based on their respective importance scores.
- generating inter-visual-word relationships between a plurality of visual words;
-
13. A system comprising:
- one or more computer-readable media; and
one or more processors that are coupled to the one or more computer-readable media and that are configured to cause the system to generate inter-visual-word relationships between a plurality of visual words based on visual word-label relationships, wherein the visual word-label relationships are based on co-occurrences of respective visual words and labels in one or more images, and wherein the inter-visual word relationships are based on scores between the visual word-label relationships of respective visual words, map the visual words to a vector space based on the inter-visual-word relationships, and generate high-level visual words in the vector space.
- one or more computer-readable media; and
Specification