Abstract: Fingerprinting a video including video frames is disclosed. A method includes receiving the video, generating sub-images, generating sub-fingerprints for the video using the sub-images, and matching the video to a reference video using the sub-fingerprints. Generating sub-images includes, for a video frame of some of the video frames, generating a binary image for the video frame, identifying a first region of the binary image, and identifying a sub-image of the video frame that is co-extensive and co-located with the first region of the binary image. A pixel of the video frame is identified in the binary image by a first value or a second value where the first value indicates a motion pixel and the second value indicates a still pixel. The first region includes more of the first value than the second value, and the first region is indicative of a motion in the video frame.

Abstract: Fingerprinting a video including video frames is disclosed. A method includes receiving the video, generating sub-images, generating sub-fingerprints for the video using the sub-images, and matching the video to a reference video using the sub-fingerprints. Generating sub-images includes, for a video frame of some of the video frames, generating a binary image for the video frame, identifying a first region of the binary image, and identifying a sub-image of the video frame that is co-extensive and co-located with the first region of the binary image. A pixel of the video frame is identified in the binary image by a first value or a second value where the first value indicates a motion pixel and the second value indicates a still pixel. The first region includes more of the first value than the second value, and the first region is indicative of a motion in the video frame.

Abstract: Provided content is determined to contain an asset represented by reference content by comparing digital fingerprints of the provided content and the reference content. The fingerprints of the reference content and the provided content are generated using a convolutional neural network (CNN). The CNN is trained using a plurality of frame triplets including an anchor frame representing the reference content, a positive frame which is a transformation of the anchor frame, and a negative frame representing content that is not the reference content. The provided content is determined to contain the asset represented by the reference content based on a similarity measure between the generated fingerprints. If the provided content is determined to contain the asset represented by the reference content, a policy associated with the asset is enforced on the provided content.

Abstract: A method and system generates and compares sub-fingerprints for videos. Sub-fingerprints of a video provide representations of characteristics of portions of video content of the video. Sub-fingerprints can be used to determine whether a video includes video content of another video effectively. The video can include other video content to visually appear different from the other video. When a sub-fingerprint of the video matches a fingerprint of the other video, the video includes video content of the other video. Motions of video content of the video can be tracked to identify regions of video frames that include image content that includes motion. Sub-images can created and used to create sub-fingerprints of the video.

Abstract: A method and system generates and compares sub-fingerprints for videos. Sub-fingerprints of a video provide representations of characteristics of portions of video content of the video. Sub-fingerprints can be used to determine whether a video includes video content of another video effectively. The video can include other video content to visually appear different from the other video. When a sub-fingerprint of the video matches a fingerprint of the other video, the video includes video content of the other video. Motions of video content of the video can be tracked to identify regions of video frames that include image content that includes motion. Sub-images can created and used to create sub-fingerprints of the video.

Abstract: A computer at a content management system receives a first digital content item from a content provider. The computer matches the first digital content item to each of a plurality of reference digital content items in a database. The system determines a plurality of match metrics from the matches. Each match metric is indicative of a similarity between the first digital content item and one of the plurality of reference digital content items. Responsive to one of the match metrics being greater than a threshold level, the system sets a content age of the first digital content item to equal a content age of a reference digital content item associated with the match metric. Responsive to none of the match metrics being greater than the threshold, the system sets the content age of the first digital content item to a time of receiving the first digital content item.

Abstract: Aspects relate to determining whether a probe media content matches one or more reference media content. The reference media content is classified into a content class. The probe media content could also be classified into a content class. Similarities between the probe media content and the reference media content are identified. A matching score given to the probe media content is weighted based on statistics regarding matches and false-positive rates for the content class of the reference media content. Further, classifiers can be trained on computed audio features and video features and/or video metadata and audio metadata of various media content.