Invention Grant
- Patent Title: Accurate tag relevance prediction for image search
-
Application No.: US15094633Application Date: 2016-04-08
-
Publication No.: US10235623B2Publication Date: 2019-03-19
- Inventor: Zhe Lin , Xiaohui Shen , Jonathan Brandt , Jianming Zhang , Chen Fang
- Applicant: ADOBE SYSTEMS INCORPORATED
- Applicant Address: US CA San Jose
- Assignee: Adobe Inc.
- Current Assignee: Adobe Inc.
- Current Assignee Address: US CA San Jose
- Agency: Shook, Hardy & Bacon L.L.P.
- Main IPC: G06N99/00
- IPC: G06N99/00 ; G06F17/30 ; G06N3/08 ; G06N3/04

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.
Public/Granted literature
- US20170236055A1 ACCURATE TAG RELEVANCE PREDICTION FOR IMAGE SEARCH Public/Granted day:2017-08-17
Information query