Amazon Technologies, Inc.

Xiang Hao

Vernon Germano

Muhammad Raffay Hamid

Kripa Kanchana Sivakumar

Jingxiang Chen

Mayank Sharma

Xiaohan Nie

Ahmed Aly Saad Ahmed

Shixing Chen

Yi Sun

Mohamed Kamal Omar

Steven James Cox

Tarun Gupta

Emily Evon McAninly

Lakshay Sharma

Saida Lehiany

Diana Nassar

Benjamin Cheung

Zhitao Qiu

A plurality of similar video pairs may be determined based on one or more similarity information types. Each video pair of the plurality of similar video pairs may include a first respective video and a second respective video. For each video pair, one or more similar scene pairs may be determined. Each of the one or more similar scene pairs may include a respective first scene from the first respective video and a second respective scene from the second respective video. An encoder may be trained using a contrastive learning model that contrasts a plurality of similar scene pairs with a plurality of random scenes. The plurality of similar scene pairs may include the one or more scene pairs for each video pair. One or more scene features of one or more other scenes of one or more other videos may be determined using the encoder.

Contrastive learning of scene representation guided by video similarities

A system can be utilized to retrieve media content and rating schemas, to determine maturity ratings for media content. The media content can be utilized to determine segments of data as building blocks associated with mature content. The building blocks can be mapped to content descriptors and rating levels associated with the rating schemas. The building blocks can be compared the media content to identify portions of the media content that have characteristics represented by the building blocks. The building blocks representing the characteristics in the portions of the media content can be utilized to select content descriptors and rating levels associated with the media content. The selected content descriptor and selected rating levels can be utilized to control how, and/or whether, the media content is made available for output to the consumers.

Age-appropriate media content ratings determination

Devices, systems, and methods are provided for context-based abusive language detection and responses. A method may include identifying text associated with first video content, and determining that a first word in the text matches a first keyword indicative of abusive language. The method may include determining a first label associated with the first word, the first label indicating that the first word is ambiguous. The method may include identifying a first sentence of the text, the first sentence including the first word. The method may include determining first and second context of the first word and the first sentence. The method may include determining, based on the first and second context, using a machine learning model, a second label associated with the first sentence, the second label indicating a probability that the first sentence includes abusive language. The method may include generating second video content for presentation.

Context-based abusive language detection and response for media

Techniques for temporal localization of mature content in long-form videos using only video-level labels are described. According to some embodiments, computer-implemented method includes receiving a request to train a machine learning model on a training video file comprising at least one mature content label, training the machine learning model to generate a feature vector for each of a plurality of video frames of the training video file, generate a plurality of frame-level mature content classification scores of the training video file from the feature vectors of the training video file, and generate a video-level mature content classification score of the training video file from the plurality of frame-level mature content classification scores for the training video file based at least in part on the at least one mature content label of the training video file, receiving a request for an input video file, generating, by the machine learning model in response to the request, a feature vector for each of a plurality of video frames of the input video file, a plurality of frame-level mature content classification scores of the input video file from the feature vectors of the input video file, and a video-level mature content classification score of the input video file from the plurality of frame-level mature content classification scores for the input video file, and transmitting the plurality of frame-level mature content classification scores of the input video file or the video-level mature content classification score of the input video file to a client application or to a storage location.

Temporal localization of mature content in long-form videos using only video-level labels

Methods, systems, and computer-readable media for media classification using local and global audio features are disclosed. A media classification system determines local features of an audio input using an audio event detector model that is trained to detect a plurality of audio event classes descriptive of objectionable content. The local features are extracted using maximum values of audio event scores for individual audio event classes. The media classification system determines one or more global features of the audio input using the audio event detector model. The global feature(s) are extracted using averaging of clip-level descriptors of a plurality of clips of the audio input. The media classification system determines a content-based rating for media comprising the audio input based (at least in part) on the local features of the audio input and based (at least in part) on the global feature(s) of the audio input.

Media classification using local and global audio features

Methods and apparatus are relating to the use of machine learning techniques to identify unrated content that will be appealing to particular demographics. Using explicit feedback (e.g., star ratings) and implicit feedback (e.g., viewing behavior) for a given demographic, feature sets are extracted from the rated titles and then used to recognize similar titles in unrated content.

Content appeal prediction using machine learning

Methods and apparatus are described that relate to the use of machine learning techniques to accurately predict ratings for various types of content across multiple mature themes.

Mature themes prediction for online content

Techniques for providing video content are described, where portions of the video content may be determined based an artificial intelligence model. In an example, a computer system may input, to a neural network, a vector representation of a frame. The neural network may be configured based on an error of associating the frame with an incorrect category. The error may be based on timing of the frame and on an error time margin relative to a start time or an end time of the incorrect category. The computer system may receive back an association between the vector representation and a category and may generate, based on the association, an identifier of a portion of the video content. The identifier may associate the portion of the video content with the category and identify a start time or an end time of the portion of the video content.

Determining portions of video content based on artificial intelligence model

An image quality assessment solution analyzes an image quality and a correlation of an image to an item description associated with the item. The content quality assessment may assign a quality score to the image based on a composition of the image and/or correlation with the image description. The score may be based on a model that is trained to analyze images using a learning model. Based on the image score, a correlation score, or other scores, the user may be given feedback on how to improve an image. A service provider providing this service may use the score to influence recommendation results that use the images.

Growing community of inventors

Kenmore, WA, United States of America

Xiang Hao