Adobe, Inc.

Other

William L Marino

Nicolas Huynh Thien

Nico Becherer

Zhe Lin

Oliver Wang

Akhilesh Kumar

Brunno Fidel Maciel Attorre

Xiaozhen Xue

Allison Breanne Walke

Aseem Agarwala

Shabnam Ghadar

Kshitiz Garg

Ali Aminian

Alvin Ghouas

Shabbir Marzban

Brunno Fidel Maciel Attore

Tim Converse

Sudharshan Reddy Kakumanu

Johan Adami

Ben Bowles

Alexander Riss

Dhaval Shah

Meng He

Embodiments of the present invention provide systems, methods, and computer storage media for extracting moments of interest (e.g., video frames, video segments) from a video. In an example embodiment, independent and/or orthogonal machine learning models are used to extract different types of features considering different modalities, and each frame in the video is assigned an importance score for each model. The importance scores for each model are combined into an aggregated importance score for each frame in the video. Depending on the embodiment, the aggregated importance scores are used to visualize the score per frame, identify moments of interest, automatically crop down the video into a highlight reel, browse or visualize the moments of interest within the video, and/or search across multiple videos.

Customizable framework to extract moments of interest

The present disclosure describes systems and methods for a privacy sensitive computing system. One or more embodiments provide a protected computing environment, a code authorization unit, and a data aggregation unit. For example, some embodiments of the privacy sensitive computing system may train unsupervised or self-supervised ML models on user-generated assets subject to privacy considerations that mandate those assets are not viewed directly by human eyes.

Platform for unsupervised machine learning training on unseeable user generated assets

Embodiments of the present invention provide systems, methods, and computer storage media for detecting and classifying an exposure defect in an image using neural networks trained via a limited amount of labeled training images. An image may be applied to a first neural network to determine whether the images includes an exposure defect. Detected defective image may be applied to a second neural network to determine an exposure defect classification for the image. The exposure defect classification can includes severe underexposure, medium underexposure, mild underexposure, mild overexposure, medium overexposure, severe overexposure, and/or the like. The image may be presented to a user along with the exposure defect classification.

Exposure defects classification of images using a neural network

Hierarchical multiclass exposure defects classification in images

Embodiments of the present invention are directed towards reframing videos from one aspect ratio to another aspect ratio while maintaining visibility of regions of interest. A set of regions of interest are determined in frames in a video with a first aspect ratio. The set of regions of interest can be used to estimate an initial camera path. An optimal camera path is determined by leveraging the identified regions of interest using the initial camera path. Sub crops with a second aspect ratio different from the first aspect ratio of the video are identified. The sub crops are placed as designated using the optimal camera path to generate a cropped video with the second aspect ratio.

Intelligent video reframing

Some embodiments of the present disclosure provide a content integration system. The content integration system is configured to retrieve a source digital content, retrieve a target digital content, identify a region within the target digital content for placing or integrating the source digital content, and place or integrate the target digital content onto the identified region of the source digital content. The content integration system can be configured to place the source digital content into the target digital content in an aesthetically-pleasing, unobtrusive, engaging, and/or otherwise favorable manner. The content integration system can be particularly useful for advertisements, enhanced expression, entertainment, information, or communication.

Apparatus, systems, and methods for integrating digital media content into other digital media content

Disclosed herein are techniques for determining brand safety of a video including image frames and audio content. In some embodiments, frame-level features, scene-level features, and video-level features are extracted by a set of frame-level models, a set of scene-level models, and a set of video-level models, respectively. Outputs from lower level models are used as inputs for higher level models. A brand safety score indicating whether it is safe to associate a brand with the video is determined based on the outputs from the set of video-level models. In some embodiments, commercial content associated with the brand is insert into the video that is determined to be safe for the brand.

Brand safety in video content

Disclosed herein are techniques for digital content integration. A computer-implemented method includes receiving a target digital content item that includes a plurality of frames, identifying a set of candidate host frames for inserting source digital content items from the plurality of frames based on one or more attributes of the target digital content item, determining a candidate score for each respective candidate host frame of the candidate host frames, and generating host time defining data including identifications and the candidate scores of the candidate host frames, where the candidate score indicates a degree of transition of the target digital content item at the candidate host frame. One or more candidate host frames are then selected based on the candidate scores for inserting one or more source digital content items into the target digital content item.

Apparatus, systems, and methods for integrating digital media content

An electronic device such as a smart phone, in combination with an application program residing at least partially therein and run at least partially thereby effectively enables selective retroactive recording to capture already-passed audible events when an audible trigger is recognized. When used in conjunction with an internet-based social media network or an interested contact list, audible events that meet certain pre-determined criteria may be automatically shared.

Recording system and method

Growing community of inventors

New York, NY, United States of America

William L Marino