US 2019/0156125 A1 · Characterizing Content with a Predictive Error Representation

Abstract

A media item comprising a set of frames is received by a feature extraction system. A frame predictor is executed on each frame of the set of frames. An error representation is extracted for each frame of the set of frames during the execution of the frame predictor. An error-based feature vector is generated from the error representations associated with each frame of the set of frames. A seed media item is identified having a first error-based feature vector. A similarity score is determined among the first error-based feature vector and each error-based feature vector of a set of error-based feature vectors. A subset of error-based feature vectors, hence a subset of corresponding media items, is selected based on similarity score.

Claims20

Dependent claims

A method comprising:

receiving a media item comprising an ordered set of frames;
applying a frame predictor to one or more frames of the set of frames to generate a set of predicted frames, the frame predictor generating a subsequent frame of the media item based on at least one previous frame of the media item;
comparing the set of predicted frames to the corresponding ordered set of frames and based on the comparison determining one or more error representations describing differences between the predicted frames and the corresponding frames of the media item;
and
generating an error-based feature vector characterizing the media item based on one or more determined error representations.

2 more elements

A non-transitory computer-readable storage medium storing computer program instructions executable by a processor to perform operations comprising:

receiving a media item comprising an ordered set of frames;
applying a frame predictor to one or more frames of the set of frames to generate a set of predicted frames, the frame predictor generating a subsequent frame of the media item based on at least one previous frame of the media item;
comparing the set of predicted frames to the corresponding ordered set of frames and based on the comparison determining one or more error representations describing differences between the predicted frames and the corresponding frames of the media item;
and
generating an error-based feature vector characterizing the media item based on one or more determined error representations.

2 more elements

Dependencies are inferred from the claim text.

Characterizing Content with a Predictive Error Representation

Life of this patent

Characterizing Content with a Predictive Error Representation

Life of this patent

Abstract

Claims20