公开(公告)号：US20170236032A1

公开(公告)日：2017-08-17

申请号：US15043174

申请日：2016-02-12

Applicant: ADOBE SYSTEMS INCORPORATED

Inventor： ZHE LIN ,  XIAOHUI SHEN ,  JONATHAN BRANDT ,  JIANMING ZHANG ,  CHEN FANG

IPC: G06K9/62 ,  G06N3/08 ,  G06F17/30

CPC classification number: G06K9/623 ,  G06F16/24578 ,  G06F16/285 ,  G06F16/51 ,  G06F16/583 ,  G06K9/4628 ,  G06K9/6223 ,  G06K9/6262 ,  G06K9/6276 ,  G06N3/0454 ,  G06N3/08 ,  G06N20/10

Abstract: Embodiments of the present invention provide an automated image tagging system that can predict a set of tags, along with relevance scores, that can be used for keyword-based image retrieval, image tag proposal, and image tag auto-completion based on user input. Initially, during training, a clustering technique is utilized to reduce cluster imbalance in the data that is input into a convolutional neural network (CNN) for training feature data. In embodiments, the clustering technique can also be utilized to compute data point similarity that can be utilized for tag propagation (to tag untagged images). During testing, a diversity based voting framework is utilized to overcome user tagging biases. In some embodiments, bigram re-weighting can down-weight a keyword that is likely to be part of a bigram based on a predicted tag set.

公开(公告)号：US20170140248A1

公开(公告)日：2017-05-18

申请号：US14940916

申请日：2015-11-13

Applicant: ADOBE SYSTEMS INCORPORATED

Inventor： ZHAOWEN WANG ,  XIANMING LIU ,  HAILIN JIN ,  CHEN FANG

IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08

CPC classification number: G06N3/0454 ,  G06K9/4628 ,  G06K9/6257 ,  G06K9/627 ,  G06K9/628 ,  G06K9/6284 ,  G06K9/629 ,  G06N3/04 ,  G06N3/08 ,  G06Q50/01

Abstract: Embodiments of the present invention relate to learning image representation by distilling from multi-task networks. In implementation, more than one single-task network is trained with heterogeneous labels. In some embodiments, each of the single-task networks is transformed into a Siamese structure with three branches of sub-networks so that a common triplet ranking loss can be applied to each branch. A distilling network is trained that approximates the single-task networks on a common ranking task. In some embodiments, the distilling network is a Siamese network whose ranking function is optimized to approximate an ensemble ranking of each of the single-task networks. The distilling network can be utilized to predict tags to associate with a test image or identify similar images to the test image.

公开(公告)号：US20180174070A1

公开(公告)日：2018-06-21

申请号：US15381637

申请日：2016-12-16

Applicant: Adobe Systems Incorporated

Inventor： MATTHEW HOFFMAN ,  LONGQI YANG ,  HAILIN JIN ,  CHEN FANG

IPC: G06N99/00 ,  G06N7/00

CPC classification number: G06N20/00 ,  G06N7/005 ,  G06Q30/0255 ,  G06Q30/0277 ,  G06T11/00 ,  H04L67/22 ,  H04W12/06

Abstract: This disclosure involves personalizing user experiences with electronic content based on application usage data. For example, a user representation model that facilitates content recommendations is iteratively trained with action histories from a content manipulation application. Each iteration involves selecting, from an action history for a particular user, an action sequence including a target action. An initial output is computed in each iteration by applying a probability function to the selected action sequence and a user representation vector for the particular user. The user representation vector is adjusted to maximize an output that is generated by applying the probability function to the action sequence and the user representation vector. This iterative training process generates a user representation model, which includes a set of adjusted user representation vectors, that facilitates content recommendations corresponding to users' usage pattern in the content manipulation application.

公开(公告)号：US20170236055A1

公开(公告)日：2017-08-17

申请号：US15094633

申请日：2016-04-08

Applicant: ADOBE SYSTEMS INCORPORATED

Inventor： ZHE LIN ,  XIAOHUI SHEN ,  JONATHAN BRANDT ,  JIANMING ZHANG ,  CHEN FANG

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06F17/30247 ,  G06N3/0454 ,  G06N3/0472 ,  G06N99/005

Abstract: Embodiments of the present invention provide an automated image tagging system that can predict a set of tags, along with relevance scores, that can be used for keyword-based image retrieval, image tag proposal, and image tag auto-completion based on user input. Initially, during training, a clustering technique is utilized to reduce cluster imbalance in the data that is input into a convolutional neural network (CNN) for training feature data. In embodiments, the clustering technique can also be utilized to compute data point similarity that can be utilized for tag propagation (to tag untagged images). During testing, a diversity based voting framework is utilized to overcome user tagging biases. In some embodiments, bigram re-weighting can down-weight a keyword that is likely to be part of a bigram based on a predicted tag set.