公开(公告)号：US20240257496A1

公开(公告)日：2024-08-01

申请号：US18162544

申请日：2023-01-31

Applicant: Adobe Inc.

Inventor： Simon JENNI ,  John COLLOMOSSE

IPC: G06V10/764

CPC classification number: G06V10/764

Abstract: Embodiments are disclosed for training a system to generate audio and video representations using self-supervised learning. The method may include receiving a video signal including an audio component and a video component. A first machine learning model is trained to determine a representation of the audio component using a contrastive learning task and a temporal learning task. A second machine learning model to determine a representation of the video component using the contrastive learning task and the temporal learning task. By training the machine learning models using both contrastive learning tasks and temporal learning tasks, the machine learning models learn short term features, long term features, and semantic features of input data.

公开(公告)号：US20250103649A1

公开(公告)日：2025-03-27

申请号：US18473045

申请日：2023-09-22

Applicant: Adobe Inc.

Inventor： Ritwik SINHA ,  Viswanathan SWAMINATHAN ,  Simon JENNI ,  Md Mehrab TANJIM ,  John COLLOMOSSE

IPC: G06F16/732 ,  G06F16/738 ,  G06F16/75

Abstract: Embodiments are disclosed for performing content authentication. A method of content authentication may include dividing a query video into a plurality of chunks. A feature vector may be generated, using a fingerprinting model, for each chunk from the plurality of chunks. Similar video chunks are identified from a trusted chunk database based on the feature vectors using a multi-chunk search policy. One or more original videos corresponding to the query video are then returned.

公开(公告)号：US20240273355A1

公开(公告)日：2024-08-15

申请号：US18168236

申请日：2023-02-13

Applicant: Adobe Inc.

Inventor： Nicholas J. BRYAN ,  Simon JENNI ,  John COLLOMOSSE ,  Christian James STEINMETZ

IPC: G06N3/08 ,  G06F16/632

CPC classification number: G06N3/08 ,  G06F16/632

Abstract: Embodiments are disclosed for identifying matching content using neural content fingerprints. The method may include receiving a request to identify content matching a query content item, wherein the query content item is a time varying content item, generating, by an embedding network, a neural fingerprint for the query content item, identifying one or more candidate content items based on the neural fingerprint of the query content item, determining, by a ranking network, one or more similarity scores corresponding to the one or more candidate content items, and identifying one or more matching content items based on the one or more similarity scores.