Joint Visual-Semantic Embedding and Grounding via Multi-Task Training for Image Searching
US-2021271707-A1 · Sep 2, 2021 · US
US12423928B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12423928-B2 |
| Application number | US-202418614273-A |
| Country | US |
| Kind code | B2 |
| Filing date | Mar 22, 2024 |
| Priority date | Oct 11, 2021 |
| Publication date | Sep 23, 2025 |
| Grant date | Sep 23, 2025 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Methods, systems, and storage media for auto-generating an artificial reality environment based on access to personal user content are disclosed. Exemplary implementations may: receive consent from a user to access user content on a user device, the user content comprising digital media; generate a user profile based at least in part on the user content; determine user preferences based at least in part on the user profile; generate an artificial reality environment based at least in part on the user preferences; and share the artificial reality environment with contacts of the user.
Opening claim text (preview).
What is claimed is: 1. A computer-implemented method for sharing artificial reality content, comprising: receiving, at a user device, a text or voice input; accessing a set of images on the user device based on the text or voice input; obtaining, using an assistant system, information used to present a user-specific avatar for a first user of the user device and a background theme for the user-specific avatar based at least in part on the set of images and user preferences associated with the first user; and in accordance with a determination that the user-specific avatar and the background theme for the user-specific avatar should be shared with other specific users: providing the information used to present the user-specific avatar and the background theme for the user-specific avatar to a second user associated with the first user, wherein: the set of images correspond to one or more of a shared real-world experience and a shared experience in an artificial reality environment between the first user and the second user. 2. The computer-implemented method of claim 1 , further comprising: obtaining, using the assistant system, information used to present a representation of the set of images based at least in part on the set of images and user preferences associated with the first user; and in accordance with the determination that the user-specific avatar and the background theme for the user-specific avatar should be shared with the other specific users: providing the information used to present the representation of the set of images to the second user. 3. The computer-implemented method of claim 1 , wherein, the information used to present the user-specific avatar and the background theme for the user-specific avatar comprises information that, when rendered on an artificial reality headset, produces a three-dimensional effect perceived by the second user. 4. The computer-implemented method of claim 1 , wherein providing the information used to present the user-specific avatar and the background theme for the user-specific avatar includes providing at least one of the shared real-world experience and the shared experience in the artificial reality environment. 5. The computer-implemented method of claim 1 , further comprising: in accordance with the determination that the user-specific avatar and the background theme for the user-specific avatar should be shared with other specific users: providing the information used to present the user-specific avatar and the background theme for the user-specific avatar to a third user associated with the first user, wherein: the set of images correspond to one or more of another shared real-world experience and another shared experience in another artificial reality environment between the first user and the third user. 6. The computer-implemented method of claim 1 , further comprising determining the user preferences based at least in part on user content on the user device, wherein the user preferences relate to one or more of food preferences, music preferences, travelling preferences, favorite places visited, preferences for specific types of activities, fashion style, and/or preferences of the second user. 7. The computer-implemented method of claim 1 , wherein the information used to present the user-specific avatar and the background theme for the user-specific avatar is provided to the second user via and/or based on a social graph. 8. The computer-implemented method of claim 1 , wherein the second user is a contact of the first user on the user device. 9. The computer-implemented method of claim 1 , wherein obtaining the background theme for the user-specific avatar based at least in part on the set of images and user preferences associated with the first user comprises: identifying a plurality of background themes based at least in part on the set of images; and selecting, via a recommendation engine, the background theme based on personal information of the first user. 10. The computer-implemented method of claim 1 , wherein a machine learning (ML) model is used to obtain the information used to present the user-specific avatar and the background theme for the user-specific avatar. 11. The computer-implemented method of claim 1 , wherein the user device comprises an artificial reality headset, a smartphone, a tablet, a computer, and/or a laptop. 12. The computer-implemented method of claim 1 , wherein the set of images are captured by a camera disposed on the user device. 13. A system configured for sharing artificial reality content, comprising: one or more processors; and a memory storing instructions which, when executed by the one or more processors, cause the system to: receive, at a user device, a text or voice input; access a set of images on the user device based on the text or voice input; obtain, using an assistant system, information used to present a user-specific avatar for a first user of the user device and a background theme for the user-specific avatar based at least in part on the set of images and user preferences associated with the first user; and in accordance with a determination that the user-specific avatar and the background theme for the user-specific avatar should be shared with other specific users: provide the information used to present the user-specific avatar and the background theme for the user-specific avatar to a second user associated with the first user, wherein: the set of images correspond to one or more of a shared real-world experience and a shared experience in an artificial reality environment between the first user and the second user. 14. The system of claim 13 , wherein, the information used to present the user-specific avatar and the background theme for the user-specific avatar comprises information that, when rendered on an artificial reality headset, produces a three-dimensional effect perceived by the second user. 15. The system of claim 13 , wherein providing the information used to present the user-specific avatar and the background theme for the user-specific avatar includes providing at least one of the shared real-world experience and the shared experience in the artificial reality environment. 16. The system of claim 13 , wherein the instructions further cause the system to: in accordance with the determination that the user-specific avatar and the background theme for the user-specific avatar should be shared with other specific users: provide the information used to present the user-specific avatar and the background theme for the user-specific avatar to a third user associated with the first user, wherein: the set of images correspond to one or more of another shared real-world experience and another shared experience in another artificial reality environment between the first user and the third user. 17. A non-transient computer-readable storage medium having instructions embodied thereon for sharing artificial reality content, the instructions, when executed by one or more processors, cause a computer system to: receive, at a user device, a text or voice input; access a set of images on the user device based on the text or voice input; obtain, using an assistant system, information used to present a user-specific avatar for a first user of the user device and a background theme for the user-specific avatar based at least in part on the set of images and user preferences associated with the first user; and in accordance with a determination that the user-specific avatar and the background theme for the user-specific ava
Business processes related to social networking or social networking services · CPC title
Input arrangements with force or tactile feedback as computer generated output to the user · CPC title
Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection · CPC title
Eye tracking input arrangements (G06F3/015 takes precedence) · CPC title
Head tracking input arrangements · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.