-
公开(公告)号:US11200611B2
公开(公告)日:2021-12-14
申请号:US16235290
申请日:2018-12-28
Applicant: eBay Inc.
Inventor: Robinson Piramuthu , Timothy Samuel Keefer , Ashmeet Singh Rekhi , Padmapriya Gudipati , Mohammadhadi Kiapour , Shuai Zheng , Alberto Ordonez Pereira , Ravindra Surya Lanka , Md Atiq ul Islam , Nicholas Anthony Whyte , Giridharan Iyengar , Bryan Allen Plummer
IPC: G06F17/00 , G06F7/00 , G06Q30/06 , G06F16/538 , G06F16/9535 , G06F16/532 , G06K9/66 , G06F16/583 , G06N20/00 , G06F3/01 , G06K9/00 , G06K9/62 , G06F3/0482 , G06F3/0484 , G06F3/0488
Abstract: Computer vision for unsuccessful queries and iterative search is described. The described system leverages visual search techniques by determining visual characteristics of objects depicted in images and describing them, e.g., using feature vectors. In some aspects, these visual characteristics are determined for search queries that are identified as not being successful. Aggregated information describing visual characteristics of images of unsuccessful search queries is used to determine common visual characteristics and objects depicted in those images. This information can be used to inform other users about unmet needs of searching users. In some aspects, these visual characteristics are used in connection with iterative image searches where users select an initial query image and then the search results are iteratively refined. Unlike conventional techniques, the described system iteratively refines the returned search results using an embedding space learned from binary attribute labels describing images.
-
公开(公告)号:US10706317B2
公开(公告)日:2020-07-07
申请号:US15836260
申请日:2017-12-08
Applicant: eBay Inc.
Inventor: John Weigel , Niaz Ahamed Khaja Nazimudeen , Padmapriya Gudipati , Timothy Keefer , Fujun Zhong , Ashmeet Singh Rekhi , Kenneth Crookston , Shane Lin , Suchitra Ramesh , Rodolfo Gonzales , Atiq Islam
IPC: G06K9/46 , G06T7/90 , G06F16/951 , G06F16/583
Abstract: Embodiments of the present disclosure provide systems, methods, and computer storage media for implementing a nuanced-color search and recommendation system. Employing various techniques described herein, an improved search engine for categorizable items is provided to generate accurate color-based search results and recommendations that are relevant to a nuanced color provided as a search parameter. In various implementations, digital assets that depict categorizable items can be analyzed to characterize the depicted items with, among other things, a particular shade of a determined dominant color. In this way, categorizable items can be searched based at least in part on a selected shade of a particular dominant color to generate a primary search result. In further embodiments, other categorizable items can be generated as recommendations based on characteristics of the primary search result. That is, other items not necessarily subject of the search, can be provided as recommended items if predefined rules dictate that such items may complement the categorizable items included in the primary search result.
-
公开(公告)号:US11367274B2
公开(公告)日:2022-06-21
申请号:US16899696
申请日:2020-06-12
Applicant: eBay Inc.
Inventor: John Weigel , Niaz Ahamed Khaja Nazimudeen , Padmapriya Gudipati , Timothy Keefer , Fujun Zhong , Ashmeet Singh Rekhi , Kenneth Crookston , Shane Lin , Suchitra Ramesh , Rodolfo Gonzales , Atiq Islam
IPC: G06V10/56 , G06T7/90 , G06F16/951 , G06F16/583
Abstract: Embodiments of the present disclosure provide systems, methods, and computer storage media for implementing a nuanced-color search and recommendation system. Employing various techniques described herein, an improved search engine for categorizable items is provided to generate accurate color-based search results and recommendations that are relevant to a nuanced color provided as a search parameter. In various implementations, digital assets that depict categorizeable items can be analyzed to characterize the depicted items with, among other things, a particular shade of a determined dominant color. In this way, categorizeable items can be searched based at least in part on a selected shade of a particular dominant color to generate a primary search result. In further embodiments, other categorizeable items can be generated as recommendations based on characteristics of the primary search result. That is, other items not necessarily subject of the search, can be provided as recommended items if predefined rules dictate that such items may complement the categorizable items included in the primary search result.
-
公开(公告)号:US11250487B2
公开(公告)日:2022-02-15
申请号:US16388473
申请日:2019-04-18
Applicant: eBay Inc.
Inventor: Robinson Piramuthu , Timothy Samuel Keefer , Kenneth Clark Crookston , Ashmeet Singh Rekhi , Niaz Ahamed Khaja Nazimudeen , Padmapriya Gudipati , Shane Lin , John F. Weigel , Fujun Zhong , Suchitra Ramesh , Mohammadhadi Kiapour , Shuai Zheng , Alberto Ordonez Pereira , Ravindra Surya Lanka , Md Atiq Ul Islam , Nicholas Anthony Whyte , Giridharan Iyengar , Bryan Allen Plummer
IPC: G06Q30/00 , G06Q30/06 , G06F16/538 , G06F16/9535 , G06F16/532 , G06K9/66 , G06F16/583 , G06N20/00 , G06F3/01 , G06K9/00 , G06K9/62 , G06F3/0482 , G06F3/0484 , G06F3/0488
Abstract: Computer vision and image characteristic search is described. The described system leverages visual search techniques by determining visual characteristics of objects depicted in images and comparing the determined characteristics to visual characteristics of other images, e.g., to identify similar visual characteristics in the other images. In some aspects, the described system performs searches that leverage a digital image as part of a search query to locate digital content of interest. In some aspects, the described system surfaces multiple user interface instrumentalities that include images of patterns, textures, or materials and that are selectable to initiate a visual search of digital content having a similar pattern, texture, or material. The described aspects also include pattern-based authentication in which the system determines authenticity of an item in an image based on a similarity of its visual characteristics to visual characteristics of known authentic items.
-
公开(公告)号:US11086925B2
公开(公告)日:2021-08-10
申请号:US16140305
申请日:2018-09-24
Applicant: eBay Inc.
Inventor: Ashmeet Singh Rekhi , Shane Lin , Suchitra Ramesh , An Feng-I Chen , Padmapriya Gudipati , Justin Nicholas House , Kenneth Crookston , John Weigel , Timothy Keefer , Satya Krishna Suman Voleti , Zhe Sun
IPC: G06F16/00 , G06F16/583 , G06Q30/06 , G06F16/29 , G06F16/9537
Abstract: Systems and methods for improving a search process are provided. A networked system accesses, from online sources, fashion trend information including pictures illustrating fashion trends. The networked system determines a plurality of top fashion trends, and extracts, using an image detection algorithm, images of fashion items from a picture associated with each of the top fashion trends. Using the extracted images, the networked system performs an image search for matching inventory items. The networked system then generates and stored a plurality of fashion trend user interfaces, whereby the plurality of fashion trend user interfaces each comprise selectable elements that represent the plurality of top fashion trends. At runtime, the networked system receives an indication to initiate a search for fashion by trends, and in response, accesses the plurality of stored fashion trend user interfaces. One of the plurality of stored fashion trend user interfaces is presented on a user device.
-
公开(公告)号:US20210201378A1
公开(公告)日:2021-07-01
申请号:US17141618
申请日:2021-01-05
Applicant: eBay Inc.
Inventor: Robinson Piramuthu , Timothy Samuel Keefer , Ashmeet Singh Rekhi , Padmapriya Gudipati , Mohammadhadi Kiapour , Shuai Zheng , Md Atiq ul Islam , Nicholas Anthony Whyte , Giridharan Iyengar
IPC: G06Q30/06 , G06F16/538 , G06F16/9535 , G06F16/532 , G06K9/66 , G06F16/583 , G06N20/00 , G06F3/01 , G06K9/00 , G06K9/62
Abstract: Techniques and systems are described that leverage computer vision as part of search to expand functionality of a computing device available to a user and increase operational computational efficiency as well as efficiency in user interaction. In a first example, user interaction with items of digital content is monitored. Computer vision techniques are used to identify digital images in the digital content, objects within the digital images, and characteristics of those objects. This information is used to assign a user to a user segment of a user population which is then used to control output of subsequent digital content to the user, e.g., recommendations, digital marketing content, and so forth.
-
公开(公告)号:US20200320333A1
公开(公告)日:2020-10-08
申请号:US16899696
申请日:2020-06-12
Applicant: eBay Inc.
Inventor: John Weigel , Niaz Ahamed Khaja Nazimudeen , Padmapriya Gudipati , Timothy Keefer , Fujun Zhong , Ashmeet Singh Rekhi , Kenneth Crookston , Shane Lin , Suchitra Ramesh , Rodolfo Gonzales , Atiq Islam
IPC: G06K9/46 , G06T7/90 , G06F16/951 , G06F16/583
Abstract: Embodiments of the present disclosure provide systems, methods, and computer storage media for implementing a nuanced-color search and recommendation system. Employing various techniques described herein, an improved search engine for categorizable items is provided to generate accurate color-based search results and recommendations that are relevant to a nuanced color provided as a search parameter. In various implementations, digital assets that depict categorizeable items can be analyzed to characterize the depicted items with, among other things, a particular shade of a determined dominant color. In this way, categorizeable items can be searched based at least in part on a selected shade of a particular dominant color to generate a primary search result. In further embodiments, other categorizeable items can be generated as recommendations based on characteristics of the primary search result. That is, other items not necessarily subject of the search, can be provided as recommended items if predefined rules dictate that such items may complement the categorizable items included in the primary search result.
-
公开(公告)号:US20200097568A1
公开(公告)日:2020-03-26
申请号:US16140305
申请日:2018-09-24
Applicant: eBay Inc.
Inventor: Ashmeet Singh Rekhi , Shane Lin , Suchitra Ramesh , An Feng-I Chen , Padmapriya Gudipati , Justin Nicholas House , Kenneth Crookston , John Weigel , Timothy Keefer , Satya Krishna Suman Voleti , Zhe Sun
Abstract: Systems and methods for improving a search process are provided. A networked system accesses, from online sources, fashion trend information including pictures illustrating fashion trends. The networked system determines a plurality of top fashion trends, and extracts, using an image detection algorithm, images of fashion items from a picture associated with each of the top fashion trends. Using the extracted images, the networked system performs an image search for matching inventory items. The networked system then generates and stored a plurality of fashion trend user interfaces, whereby the plurality of fashion trend user interfaces each comprise selectable elements that represent the plurality of top fashion trends. At runtime, the networked system receives an indication to initiate a search for fashion by trends, and in response, accesses the plurality of stored fashion trend user interfaces. One of the plurality of stored fashion trend user interfaces is presented on a user device.
-
公开(公告)号:US20190205962A1
公开(公告)日:2019-07-04
申请号:US16235140
申请日:2018-12-28
Applicant: eBay Inc.
Inventor: Robinson Piramuthu , Timothy Samuel Keefer , Kenneth Clark Crookston , Ashmeet Singh Rekhi , Niaz Ahamed Khaja Nazimudeen , Padmapriya Gudipati , Shane Lin , John F. Weigel , Fujun Zhong , Suchitra Ramesh , Mohammadhadi Kiapour , Shuai Zheng , Alberto Ordonez Pereira , Ravindra Surya Lanka , Md Atiq ul Islam , Nicholas Anthony Whyte , Giridharan Iyengar , Bryan Allen Plummer
CPC classification number: G06F16/532 , G06F3/017 , G06F3/0482 , G06F16/3326 , G06F16/538 , G06F16/583 , G06F16/9032 , G06F16/9035 , G06F16/907 , G06F16/908 , G06F16/9535 , G06K9/00671 , G06K9/66 , G06N20/00
Abstract: Computer vision and image characteristic search is described. The described system leverages visual search techniques by determining visual characteristics of objects depicted in images and comparing the determined characteristics to visual characteristics of other images, e.g., to identify similar visual characteristics in the other images. In some aspects, the described system performs searches that leverage a digital image as part of a search query to locate digital content of interest. In some aspects, the described system surfaces multiple user interface instrumentalities that include images of patterns, textures, or materials and that are selectable to initiate a visual search of digital content having a similar pattern, texture, or material. The described aspects also include pattern-based authentication in which the system determines authenticity of an item in an image based on a similarity of its visual characteristics to visual characteristics of known authentic items.
-
公开(公告)号:US20190080198A1
公开(公告)日:2019-03-14
申请号:US15836260
申请日:2017-12-08
Applicant: eBay Inc.
Inventor: John Weigel , Niaz Ahamed Khaja Nazimudeen , Padmapriya Gudipati , Timothy Keefer , Fujun Zhong , Ashmeet Singh Rekhi , Kenneth Crookston , Shane Lin , Suchitra Ramesh , Rodolfo Gonzales , Atiq Islam
CPC classification number: G06K9/4652 , G06F16/5838 , G06F16/951 , G06T7/90 , G06T2207/10024
Abstract: Embodiments of the present disclosure provide systems, methods, and computer storage media for implementing a nuanced-color search and recommendation system. Employing various techniques described herein, an improved search engine for categorizable items is provided to generate accurate color-based search results and recommendations that are relevant to a nuanced color provided as a search parameter. In various implementations, digital assets that depict categorizeable items can be analyzed to characterize the depicted items with, among other things, a particular shade of a determined dominant color. In this way, categorizeable items can be searched based at least in part on a selected shade of a particular dominant color to generate a primary search result. In further embodiments, other categorizeable items can be generated as recommendations based on characteristics of the primary search result. That is, other items not necessarily subject of the search, can be provided as recommended items if predefined rules dictate that such items may complement the categorizable items included in the primary search result.
-
-
-
-
-
-
-
-
-