公开(公告)号：US20240203092A1

公开(公告)日：2024-06-20

申请号：US18595115

申请日：2024-03-04

Applicant: VIZIT LABS, INC.

Inventor： Jehan Hamedi ,  Zachary Halloran ,  Elham Saraee

IPC: G06V10/74 ,  G06F18/214 ,  G06F18/22 ,  G06V10/82

CPC classification number: G06V10/761 ,  G06F18/214 ,  G06F18/22 ,  G06V10/82

Abstract: Embodiments may: select a set of training images; extract a first set of features from each training image of the set of training images to generate a first feature tensor for each training image; extract a second set of features from each training image to generate a second feature tensor for each training image; reduce a dimensionality of each first feature tensor to generate a first modified feature tensor for each training image; reduce a dimensionality of each second feature tensor to generate a second modified feature tensor for each training image; construct a first generative model representing the first set of features and a second generative model representing the second set of features of the set of training images; identify a first candidate image; and apply a regression algorithm to the first candidate image and each of the first generative model and the second generative model to determine whether the first candidate image is similar to the set of training images.

公开(公告)号：US11922675B1

公开(公告)日：2024-03-05

申请号：US18494483

申请日：2023-10-25

Applicant: VIZIT LABS, INC.

Inventor： Elham Saraee ,  Zachary Halloran ,  Jehan Hamedi

IPC: G06V10/40 ,  G06F16/438 ,  G06N3/045 ,  G06V10/74 ,  G06V10/82

CPC classification number: G06V10/761 ,  G06F16/438 ,  G06N3/045 ,  G06V10/40 ,  G06V10/82

Abstract: A method includes accessing a web-based property over a network; storing a plurality of images or videos from the web-based property and associations between the plurality of images or videos and a target audience identifier responsive to the web-based property having a stored association with the target audience identifier; retrieving the plurality of images or videos from the database responsive to each of the plurality of images or videos having stored associations with the target audience identifier; executing a neural network to generate a performance score for each of the plurality of images or videos; calculating a target audience benchmark; executing the neural network to generate a first performance score for a first image or video and a second performance score for a second image or video; comparing the first performance score and the second performance score to the benchmark; and generating a record identifying the first image or video.

公开(公告)号：US20240037905A1

公开(公告)日：2024-02-01

申请号：US18483242

申请日：2023-10-09

Applicant: VIZIT LABS, INC.

Inventor： Jehan Hamedi ,  Zachary Halloran ,  Elham Saraee

IPC: G06V10/74 ,  G06F18/214 ,  G06F18/22 ,  G06V10/82

CPC classification number: G06V10/761 ,  G06F18/214 ,  G06F18/22 ,  G06V10/82

Abstract: Embodiments may: select a set of training images; extract a first set of features from each training image of the set of training images to generate a first feature tensor for each training image; extract a second set of features from each training image to generate a second feature tensor for each training image; reduce a dimensionality of each first feature tensor to generate a first modified feature tensor for each training image; reduce a dimensionality of each second feature tensor to generate a second modified feature tensor for each training image; construct a first generative model representing the first set of features and a second generative model representing the second set of features of the set of training images; identify a first candidate image; and apply a regression algorithm to the first candidate image and each of the first generative model and the second generative model to determine whether the first candidate image is similar to the set of training images.

公开(公告)号：US11783567B2

公开(公告)日：2023-10-10

申请号：US18138916

申请日：2023-04-25

Applicant: VIZIT LABS, INC.

Inventor： Jehan Hamedi ,  Zachary Halloran ,  Elham Saraee

IPC: G06V10/74 ,  G06V10/82 ,  G06F18/22 ,  G06F18/214

CPC classification number: G06V10/761 ,  G06F18/214 ,  G06F18/22 ,  G06V10/82

Abstract: Embodiments may: select a set of training images; extract a first set of features from each training image of the set of training images to generate a first feature tensor for each training image; extract a second set of features from each training image to generate a second feature tensor for each training image; reduce a dimensionality of each first feature tensor to generate a first modified feature tensor for each training image; reduce a dimensionality of each second feature tensor to generate a second modified feature tensor for each training image; construct a first generative model representing the first set of features and a second generative model representing the second set of features of the set of training images; identify a first candidate image; and apply a regression algorithm to the first candidate image and each of the first generative model and the second generative model to determine whether the first candidate image is similar to the set of training images.

公开(公告)号：US11768913B2

公开(公告)日：2023-09-26

申请号：US17979978

申请日：2022-11-03

Applicant: Vizit Labs, Inc.

Inventor： Elham Saraee ,  Jehan Hamedi ,  Zachary Halloran

IPC: G06V10/40 ,  G06V10/82 ,  G06F18/214 ,  G06F18/22

CPC classification number: G06F18/214 ,  G06F18/22 ,  G06V10/40 ,  G06V10/82

Abstract: A method may include executing a neural network to extract a first plurality of features from a plurality of first training images and a second plurality of features from a second training image; generating a model comprising a first image performance score for each of the plurality of first training images and a feature weight for each feature, the feature weight for each feature of the first plurality of features calculated based on an impact of a variation in the feature on first image performance scores of the plurality of first training images; training the model by adjusting the impact of a variation of each of a first set of features that correspond to the second plurality of features; executing the model using a third set of features from a candidate image to generate a candidate image performance score; and generating a record identifying the candidate image performance score.

公开(公告)号：US20230260250A1

公开(公告)日：2023-08-17

申请号：US18138916

申请日：2023-04-25

Applicant: VIZIT LABS, INC.

Inventor： Jehan Hamedi ,  Zachary Halloran ,  Elham Saraee

IPC: G06V10/74 ,  G06F18/214 ,  G06F18/22 ,  G06V10/82

CPC classification number: G06V10/761 ,  G06F18/214 ,  G06F18/22 ,  G06V10/82

Abstract: Embodiments may: select a set of training images; extract a first set of features from each training image of the set of training images to generate a first feature tensor for each training image; extract a second set of features from each training image to generate a second feature tensor for each training image; reduce a dimensionality of each first feature tensor to generate a first modified feature tensor for each training image; reduce a dimensionality of each second feature tensor to generate a second modified feature tensor for each training image; construct a first generative model representing the first set of features and a second generative model representing the second set of features of the set of training images; identify a first candidate image; and apply a regression algorithm to the first candidate image and each of the first generative model and the second generative model to determine whether the first candidate image is similar to the set of training images.

公开(公告)号：US20230259575A1

公开(公告)日：2023-08-17

申请号：US17673635

申请日：2022-02-16

Applicant: VIZIT LABS, INC.

Inventor： Jehan Hamedi ,  Elham Saraee ,  Zachary Halloran

IPC: G06F16/957 ,  G06F16/9535 ,  G06F16/958 ,  G06F16/954 ,  G06F16/955

CPC classification number: G06F16/9577 ,  G06F16/9535 ,  G06F16/958 ,  G06F16/954 ,  G06F16/955

Abstract: A method is disclosed. The method may include establishing a connection with a client device via an application executing on the client device; detecting one or more web pages that the application of the client device has visited during the established connection; determining a target audience for the connection based on the detected one or more web pages; responsive to determining the target audience, identifying a set of content items from memory based on each content item of the set having a stored association with an identifier of the target audience in the memory; selecting a first content item from the set of content items; and transmitting the first content item to the client device over the connection for display on a web page.

公开(公告)号：US20220383615A1

公开(公告)日：2022-12-01

申请号：US17833671

申请日：2022-06-06

Applicant: VIZIT LABS, INC.

Inventor： Elham Saraee ,  Zachary Halloran ,  Jehan Hamedi

IPC: G06V10/74 ,  G06N3/04 ,  G06V10/40 ,  G06V10/82 ,  G06F16/438

Abstract: A method includes accessing a web-based property over a network; storing a plurality of images or videos from the web-based property and associations between the plurality of images or videos and a target audience identifier responsive to the web-based property having a stored association with the target audience identifier; retrieving the plurality of images or videos from the database responsive to each of the plurality of images or videos having stored associations with the target audience identifier; executing a neural network to generate a performance score for each of the plurality of images or videos; calculating a target audience benchmark; executing the neural network to generate a first performance score for a first image or video and a second performance score for a second image or video; comparing the first performance score and the second performance score to the benchmark; and generating a record identifying the first image or video.

公开(公告)号：US20220335256A1

公开(公告)日：2022-10-20

申请号：US17857980

申请日：2022-07-05

Applicant: Vizit Labs, Inc.

Inventor： Elham Saraee ,  Jehan Hamedi ,  Zachary Halloran

IPC: G06K9/62 ,  G06V10/40

Abstract: A method may include executing a neural network to extract a first plurality of features from a plurality of first training images and a second plurality of features from a second training image; generating a model comprising a first image performance score for each of the plurality of first training images and a feature weight for each feature, the feature weight for each feature of the first plurality of features calculated based on an impact of a variation in the feature on first image performance scores of the plurality of first training images; training the model by adjusting the impact of a variation of each of a first set of features that correspond to the second plurality of features; executing the model using a third set of features from a candidate image to generate a candidate image performance score; and generating a record identifying the candidate image performance score.

公开(公告)号：US20250104392A1

公开(公告)日：2025-03-27

申请号：US18948428

申请日：2024-11-14

Applicant: VIZIT LABS, INC.

Inventor： Elham Saraee ,  Jehan Hamedi ,  Zachary Halloran

IPC: G06V10/74 ,  G06F16/438 ,  G06N3/045 ,  G06V10/40 ,  G06V10/82

Abstract: The present disclosure describes a method comprising receiving a video; segmenting the video into a plurality of segments, each of the plurality of segments comprising a plurality of images; executing one or more machine learning models using the plurality of segments to generate a segment score for each of the plurality of segments, the segment score for a segment indicating a likelihood that a user will interact with the segment; generating a video performance score for the video as a function of the segment scores for the plurality of segments; and generating a record comprising the video performance score for the video and an identification of the video.