Video screening using a machine learning video screening model trained using self-supervised training

A method of video content screening using a video screening model trained using self-supervised training, the method comprising:

• obtaining an input video;
• obtaining, from a trained video screening model trained using self-supervised training, screening data indicating an automatically identified association between the input video and a reference video, wherein the self-supervised training includes:
• obtaining an automatically generated training dataset, wherein obtaining the automatically generated training dataset includes:
• obtaining a training video;
• obtaining the reference video;
• obtaining predicate screening data generated using a first previously trained video screening model with respect to the training video and the reference video, wherein the predicate screening data indicates a predicate temporal segment within the training video and a corresponding reference temporal segment within the reference video;
• obtaining, from a second previously trained video screening model, candidate screening data for an extended temporal segment from the training video, wherein the extended temporal segment includes the predicate temporal segment and at least one of a frame from the training video preceding the predicate temporal segment or a frame from the training video subsequent to the predicate temporal segment, wherein the candidate screening data indicates an association between a screening frame from the reference video and a candidate subframe, wherein the candidate subframe is a spatial portion of a candidate frame from the extended temporal segment;
• and
• in response to a determination that:
• a determined similarity value with respect to the candidate subframe and the screening frame is greater than or equal to a first defined similarity threshold,
• data indicating the association between the candidate subframe and the screening frame is absent from filtering screening data obtained from the first previously trained video screening model with respect to the training video and the reference video, and
• a determination that a similarity value with respect to the screening frame and a spatial portion of the screening frame is less than a second defined similarity threshold,
• including, in the automatically generated training dataset, training example data indicating the association between the candidate subframe and the screening frame;
• debiasing the automatically generated training dataset;
• obtaining an untrained video screening model;
• and
• obtaining the trained video screening model by training the untrained video screening model using the automatically generated training dataset;
• and
• in response to obtaining the screening data, identifying the input video as a screened video.

A system for training a video screening model using self-supervised training, the system comprising:

• a non-transitory memory storing instructions;
• and
• a processor that executes the instructions to:
• obtain a trained video screening model, wherein, to obtain the trained video screen model, the processor executes the instructions to train an untrained video screening model using a training dataset, wherein, to automatically generate the training dataset the processor executes the instructions to:
• obtain automatically generated predicate screening data indicating a predicate temporal segment within a training video and a corresponding reference temporal segment within the reference video;
• obtain candidate screening data for an extended temporal segment from the training video, wherein the extended temporal segment includes the predicate temporal segment and at least one frame from the training video adjacent to the predicate temporal segment, wherein the candidate screening data indicates a similarity between a screening frame from the reference video and a candidate subframe, wherein the candidate subframe is a spatial portion of a candidate frame from the extended temporal segment;
• and
• in response to a determination that a determined similarity between the candidate subframe and the screening frame is greater than or equal to a defined similarity threshold, include, in the automatically generated training dataset, training example data indicating the similarity between the candidate subframe and the screening frame.