Patents by Inventor Fengbin Chen
Fengbin Chen has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11971885Abstract: Systems and methods for information retrieval are described. Embodiments generate a dense embedding for each of a plurality of media objects to be searched, generate a sparse embedding for each of the media objects using an encoder that takes the dense embedding as an input, wherein the sparse embedding satisfies a sparsity constraint that is applied to at least one layer of the encoder during training, and perform a search on the plurality of media objects based at least in part on the sparse embedding.Type: GrantFiled: February 10, 2021Date of Patent: April 30, 2024Assignee: ADOBE INC.Inventors: Fengbin Chen, Venkat Barakam, Benjamin Leviant, Amine Ben Khalifa, Kerem Turgutlu, Jayant Kumar, Sumeet Zaverilal Gala, Gaurav Kukal, Vipul Dalal
-
Patent number: 11747249Abstract: The disclosure relates to a vertical Hopkinson pressure bar test device and a test method. The device comprises a guide cylinder, an incident bar, a transmission bar, a buffer bar and a striker, and further comprises a base; side support plates arranged vertically and upwards are provided symmetrically on two sides of the base, a horizontal first lateral support plate is provided at the top between the side support plates on the two sides, three groups of horizontal second lateral support plates are provided below the first lateral support plate sequentially between the side support plates on the two sides, and each group is provided with a clamping mechanism clamping a corresponding incident bar, transmission bar or buffer bar; the surfaces of the incident bar is pasted with a first strain gauge pad and the transmission bar is pasted with a second strain gauge pad.Type: GrantFiled: January 3, 2020Date of Patent: September 5, 2023Assignee: HENAN POLYTECHNIC UNIVERSITYInventors: Weimin Liang, Jian Gong, Yu Zhao, Fengbin Chen, Liping Wang, Minmin Li, Gaowei Yue, Haixiao Lin
-
Patent number: 11741157Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for determining multi-term contextual tags for digital content and propagating the multi-term contextual tags to additional digital content. For instance, the disclosed systems can utilize search query supervision to determine and associate multi-term contextual tags (e.g., tags that represent a specific concept based on the order of the terms in the tag) with digital content. Furthermore, the disclosed systems can propagate the multi-term contextual tags determined for the digital content to additional digital content based on similarities between the digital content and additional digital content (e.g., utilizing clustering techniques). Additionally, the disclosed systems can provide digital content as search results based on the associated multi-term contextual tags.Type: GrantFiled: December 7, 2021Date of Patent: August 29, 2023Assignee: Adobe Inc.Inventors: Ajinkya Kale, Baldo Faieta, Benjamin Leviant, Fengbin Chen, Francois Guerin, Kate Sousa, Trung Bui, Venkat Barakam, Zhe Lin
-
Publication number: 20220253435Abstract: Systems and methods for information retrieval are described. Embodiments generate a dense embedding for each of a plurality of media objects to be searched, generate a sparse embedding for each of the media objects using an encoder that takes the dense embedding as an input, wherein the sparse embedding satisfies a sparsity constraint that is applied to at least one layer of the encoder during training, and perform a search on the plurality of media objects based at least in part on the sparse embedding.Type: ApplicationFiled: February 10, 2021Publication date: August 11, 2022Inventors: Fengbin Chen, Venkat Barakam, Benjamin Leviant, Amine Ben Khalifa, Kerem Turgutlu, Jayant Kumar, Sumeet Zaverilal Gala, Gaurav Kukal, Vipul Dalal
-
Publication number: 20220237682Abstract: Systems and methods for item recommendation are described. Embodiments identify a sequence of items selected by a user, embed each item of the sequence of items to produce item embeddings having a reduced number of dimensions, predict a next item based on the item embeddings using a recommendation network, wherein the recommendation network includes a sequential encoder trained based at least in part on a sampled softmax classifier, and wherein predicting the next item represents a prediction that the user will interact with the next item, and provide a recommendation to the user, wherein the recommendation includes the next item.Type: ApplicationFiled: January 27, 2021Publication date: July 28, 2022Inventors: Handong Zhao, Zhankui He, Zhaowen Wang, Zhe Lin, Ajinkya Kale, Fengbin Chen
-
Publication number: 20220100791Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for determining multi-term contextual tags for digital content and propagating the multi-term contextual tags to additional digital content. For instance, the disclosed systems can utilize search query supervision to determine and associate multi-term contextual tags (e.g., tags that represent a specific concept based on the order of the terms in the tag) with digital content. Furthermore, the disclosed systems can propagate the multi-term contextual tags determined for the digital content to additional digital content based on similarities between the digital content and additional digital content (e.g., utilizing clustering techniques). Additionally, the disclosed systems can provide digital content as search results based on the associated multi-term contextual tags.Type: ApplicationFiled: December 7, 2021Publication date: March 31, 2022Inventors: Ajinkya Kale, Baldo Faieta, Benjamin Leviant, Fengbin Chen, Francois Guerin, Kate Sousa, Trung Bui, Venkat Barakam, Zhe Lin
-
Patent number: 11232147Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for determining multi-term contextual tags for digital content and propagating the multi-term contextual tags to additional digital content. For instance, the disclosed systems can utilize search query supervision to determine and associate multi-term contextual tags (e.g., tags that represent a specific concept based on the order of the terms in the tag) with digital content. Furthermore, the disclosed systems can propagate the multi-term contextual tags determined for the digital content to additional digital content based on similarities between the digital content and additional digital content (e.g., utilizing clustering techniques). Additionally, the disclosed systems can provide digital content as search results based on the associated multi-term contextual tags.Type: GrantFiled: July 29, 2019Date of Patent: January 25, 2022Assignee: Adobe Inc.Inventors: Ajinkya Kale, Baldo Faieta, Benjamin Leviant, Fengbin Chen, Francois Guerin, Kate Sousa, Trung Bui, Venkat Barakam, Zhe Lin
-
Publication number: 20210293679Abstract: The disclosure relates to a vertical Hopkinson pressure bar test device and a test method. The device comprises a guide cylinder, an incident bar, a transmission bar, a buffer bar and a striker, and further comprises a base; side support plates arranged vertically and upwards are provided symmetrically on two sides of the base, a horizontal first lateral support plate is provided at the top between the side support plates on the two sides, three groups of horizontal second lateral support plates are provided below the first lateral support plate sequentially between the side support plates on the two sides, and each group is provided with a clamping mechanism clamping a corresponding incident bar, transmission bar or buffer bar; the surfaces of the incident bar is pasted with a first strain gauge pad and the transmission bar is pasted with a second strain gauge pad.Type: ApplicationFiled: January 3, 2020Publication date: September 23, 2021Inventors: Weimin LIANG, Jian GONG, Yu ZHAO, Fengbin CHEN,, Liping WANG, Minmin LI, Gaowei YUE, Haixiao LIN
-
Publication number: 20210034657Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for determining multi-term contextual tags for digital content and propagating the multi-term contextual tags to additional digital content. For instance, the disclosed systems can utilize search query supervision to determine and associate multi-term contextual tags (e.g., tags that represent a specific concept based on the order of the terms in the tag) with digital content. Furthermore, the disclosed systems can propagate the multi-term contextual tags determined for the digital content to additional digital content based on similarities between the digital content and additional digital content (e.g., utilizing clustering techniques). Additionally, the disclosed systems can provide digital content as search results based on the associated multi-term contextual tags.Type: ApplicationFiled: July 29, 2019Publication date: February 4, 2021Inventors: Ajinkya Kale, Baldo Faieta, Benjamin Leviant, Fengbin Chen, Francois Guerin, Kate Sousa, Trung Bui, Venkat Barakam, Zhe Lin