-
公开(公告)号:US20240078258A1
公开(公告)日:2024-03-07
申请号:US18505776
申请日:2023-11-09
Applicant: Google LLC
Inventor: Zhen Li , Yi-ting Chen , Ning Ye , Yaxi Gao , Zijian Guo , Aleksei Timofeev , Futang Peng , Thomas J. Duerig
IPC: G06F16/55 , G06F16/242 , G06F16/953 , G06F18/22 , G06N3/044 , G06N3/084 , G06N20/00
CPC classification number: G06F16/55 , G06F16/2425 , G06F16/953 , G06F18/22 , G06N3/044 , G06N3/084 , G06N20/00
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for jointly training an image embedding model and a text embedding model. In one aspect, a method comprises: processing data from a historical query log of a search system to generate a candidate set of training examples, wherein each training example comprises: (i) a search query comprising a sequence of one or more words, (ii) an image, and (iii) selection data characterizing how often users selected the image in response to the image being identified by a search result for the search query; selecting a plurality of training examples from the candidate set of training examples; and using the training data to jointly train the image embedding model and the text embedding model.
-
公开(公告)号:US11586927B2
公开(公告)日:2023-02-21
申请号:US16265793
申请日:2019-02-01
Applicant: Google LLC
Inventor: Zhen Li , Yi-ting Chen , Yaxi Gao , Da-Cheng Juan , Aleksei Timofeev , Chun-Ta Lu , Futang Peng , Sujith Ravi , Andrew Tomkins , Thomas J. Duerig
IPC: G06K9/00 , G06N3/084 , G06F16/538 , G06F16/9538 , G06K9/62 , G06N3/04
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an image embedding model. In one aspect, a method comprises: obtaining training data comprising a plurality of training examples, wherein each training example comprises: an image pair comprising a first image and a second image; and selection data indicating one or more of: (i) a co-click rate of the image pair, and (ii) a similar-image click rate of the image pair; and using the training data to train an image embedding model having a plurality of image embedding model parameters.
-
公开(公告)号:US20200250537A1
公开(公告)日:2020-08-06
申请号:US16265793
申请日:2019-02-01
Applicant: Google LLC
Inventor: Zhen Li , Yi-ting Chen , Yaxi Gao , Da-Cheng Juan , Aleksei Timofeev , Chun-Ta Lu , Futang Peng , Sujith Ravi , Andrew Tomkins , Thomas J. Duerig
IPC: G06N3/08 , G06K9/62 , G06F16/9538 , G06F16/538 , G06N3/04
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an image embedding model. In one aspect, a method comprises: obtaining training data comprising a plurality of training examples, wherein each training example comprises: an image pair comprising a first image and a second image; and selection data indicating one or more of: (i) a co-click rate of the image pair, and (ii) a similar-image click rate of the image pair; and using the training data to train an image embedding model having a plurality of image embedding model parameters.
-
公开(公告)号:US20240330361A1
公开(公告)日:2024-10-03
申请号:US18741082
申请日:2024-06-12
Applicant: Google LLC
Inventor: Zhen Li , Yi-Ting Chen , Yaxi Gao , Da-Cheng Juan , Aleksei Timofeev , Chun-Ta Lu , Futang Peng , Sujith Ravi , Andrew Tomkins , Thomas J. Duerig
IPC: G06F16/55 , G06F16/538 , G06F16/9538 , G06F18/214 , G06F18/22 , G06F18/40 , G06N3/042 , G06N3/044 , G06N3/084
CPC classification number: G06F16/55 , G06F16/538 , G06F16/9538 , G06F18/2148 , G06F18/22 , G06F18/41 , G06N3/042 , G06N3/044 , G06N3/084
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an image embedding model. In one aspect, a method comprises: obtaining training data comprising a plurality of training examples, wherein each training example comprises: an image pair comprising a first image and a second image; and selection data indicating one or more of: (i) a co-click rate of the image pair, and (ii) a similar-image click rate of the image pair; and using the training data to train an image embedding model having a plurality of image embedding model parameters.
-
公开(公告)号:US20230205813A1
公开(公告)日:2023-06-29
申请号:US18171511
申请日:2023-02-20
Applicant: Google LLC
Inventor: Zhen Li , Yi-Ting Chen , Yaxi Gao , Da-Cheng Juan , Aleksei Timofeev , Chun-Ta Lu , Futang Peng , Sujith Ravi , Andrew Tomkins , Thomas J. Duerig
IPC: G06F16/55 , G06F16/538 , G06F16/9538 , G06N3/084 , G06F18/22 , G06F18/40 , G06F18/214 , G06N3/042 , G06N3/044
CPC classification number: G06F16/55 , G06F16/538 , G06F16/9538 , G06N3/084 , G06F18/22 , G06F18/41 , G06F18/2148 , G06N3/042 , G06N3/044
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an image embedding model. In one aspect, a method comprises: obtaining training data comprising a plurality of training examples, wherein each training example comprises: an image pair comprising a first image and a second image; and selection data indicating one or more of: (i) a co-click rate of the image pair, and (ii) a similar-image click rate of the image pair; and using the training data to train an image embedding model having a plurality of image embedding model parameters.
-
公开(公告)号:US12038970B2
公开(公告)日:2024-07-16
申请号:US18171511
申请日:2023-02-20
Applicant: Google LLC
Inventor: Zhen Li , Yi-Ting Chen , Yaxi Gao , Da-Cheng Juan , Aleksei Timofeev , Chun-Ta Lu , Futang Peng , Sujith Ravi , Andrew Tomkins , Thomas J. Duerig
IPC: G06F16/00 , G06F16/538 , G06F16/55 , G06F16/9538 , G06F18/214 , G06F18/22 , G06F18/40 , G06N3/042 , G06N3/044 , G06N3/084
CPC classification number: G06F16/55 , G06F16/538 , G06F16/9538 , G06F18/2148 , G06F18/22 , G06F18/41 , G06N3/042 , G06N3/044 , G06N3/084
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an image embedding model. In one aspect, a method comprises: obtaining training data comprising a plurality of training examples, wherein each training example comprises: an image pair comprising a first image and a second image; and selection data indicating one or more of: (i) a co-click rate of the image pair, and (ii) a similar-image click rate of the image pair; and using the training data to train an image embedding model having a plurality of image embedding model parameters.
-
公开(公告)号:US12008057B2
公开(公告)日:2024-06-11
申请号:US17509767
申请日:2021-10-25
Applicant: Google LLC
Inventor: Kristina Bohl , Ivan Oropeza , Lily Berg , Tracy Gu , Ethan Schreiber , Shanfeng Zhang , Howard Zhou , David Hendon , Zhen Li , Futang Peng , Teresa Ko , Jason Chang
IPC: G06F16/9535 , G06F16/906 , G06F16/9538 , G06F40/30 , G06N20/00
CPC classification number: G06F16/9535 , G06F16/906 , G06F16/9538 , G06F40/30 , G06N20/00
Abstract: A media application determines, based on pixels of images or videos from a collection of media items, clusters of media items such that the media items in each cluster have a visual similarity, wherein the collection of media items is associated with a user account. The media application selects a subset of the clusters of media from corresponding clusters of media items based on the media items in each cluster having a visual similarity within a range of threshold similarity values. The media application causes a user interface to be displayed that includes the subset of the clusters of media.
-
公开(公告)号:US20200250538A1
公开(公告)日:2020-08-06
申请号:US16265811
申请日:2019-02-01
Applicant: Google LLC
Inventor: Zhen Li , Yi-ting Chen , Ning Ye , Yaxi Gao , Zijian Guo , Aleksei Timofeev , Futang Peng , Thomas J. Duerig
IPC: G06N3/08 , G06K9/62 , G06F16/953 , G06F16/242 , G06N20/00 , G06N3/04
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for jointly training an image embedding model and a text embedding model. In one aspect, a method comprises: processing data from a historical query log of a search system to generate a candidate set of training examples, wherein each training example comprises: (i) a search query comprising a sequence of one or more words, (ii) an image, and (iii) selection data characterizing how often users selected the image in response to the image being identified by a search result for the search query; selecting a plurality of training examples from the candidate set of training examples; and using the training data to jointly train the image embedding model and the text embedding model.
-
-
-
-
-
-
-