Abstract: A system includes a computing platform including processing hardware and a memory storing software code, a trained machine learning (ML) model, and a content thumbnail generator. The processing hardware executes the software code to receive interaction data describing interactions by a user with content thumbnails, identify, using the interaction data, an affinity by the user for at least one content thumbnail feature, and determine, using the interaction data, a predetermined business rule, or both, content for promotion to the user. The software code further provides a prediction, using the trained ML model and based on the affinity by the user, of the desirability of each of multiple candidate thumbnails for the content to the user, generates, using the content thumbnail generator and based on the prediction, a thumbnail having features of one or more of the candidate thumbnails, and displays the thumbnail to promote the content to the user.

Abstract: According to one implementation, a system includes a computing platform having processing hardware, a system memory storing a software code; and a machine learning model based classifier. The processing hardware is configured to execute the software code to receive tagging quality assurance (QA) data including multiple terms applied as tags and corrections to those tags, to identify, using the tagging QA data, a first problematic term, and to classify, using the machine learning model based classifier, the first problematic term as one of confusing or flawed. The processing hardware is further configured to execute the software code to obtain, when the first problematic term is classified as confusing, a comparative sample for clarifying use of the first problematic term, and to obtain, when the first problematic term is classified as flawed, modification data for editing a predetermined annotation taxonomy including the first problematic term.

Abstract: A system includes a computing platform having processing hardware, and a memory storing software code. The processing hardware is configured to execute the software code to receive an image having a plurality of image regions, determine a boundary of each of the image regions to identify a plurality of bounded image regions, and identify, within each of the bounded image regions, one or more image sub-regions to identify a plurality of image sub-regions. The processing hardware is further configured to execute the software code to identify, within each of the bounded image regions, one or more first features, respectively, identify, within each of the image sub-regions, one or more second features, respectively, and provided an annotated image by annotating each of the bounded image regions using the respective first features and annotating each of the image sub-regions using the respective second features.

Abstract: A system includes a computing platform having processing hardware, and a systems memory storing a software code. The processing hardware is configured to execute the software code to receive content including an image having multiple image regions, determine boundaries of each of the image regions to identify multiple bounded image regions, identify, within each of the bounded image regions, one or more local features and one or more global features, and identify, within each of the hounded image regions, another one or more local features based on a comparison with corresponding local features identified in each of one or more other bounded image regions. The processing hardware is further configured to execute the software code to annotate each of the bounded image regions using its respective one or more local features, its other one or more local features, and its one or more global features, to provide annotated content.

Abstract: According to one implementation, a system includes a computing platform having processing hardware, and a system memory storing a software code. The processing hardware is configured to execute the software code to receive a vocabulary, identify words from the vocabulary for use in extending the vocabulary, pair each of those words with every other of those words to provide word pairs, and output the word pairs to a vocabulary administrator. The software code also receives word pair characterizations identifying each of the word pairs as one of similar, dissimilar, or neither similar nor dissimilar, configures, based on the word pair characterizations, a multi-dimensional vector space including multiple embedding vectors each corresponding respectively to one of the identified words, and cross-references each of those words with its corresponding embedding vector to produce an extended vocabulary corresponding to the received vocabulary.

Abstract: A system for authenticating digital contents includes a computing platform having a hardware processor and a memory storing a software code. According to one implementation, the hardware processor executes the software code to receive digital content, identify an image of a person depicted in the digital content, determine an ear shape parameter of the person depicted in the image, determine another biometric parameter of the person depicted in the image, and calculate a ratio of the ear shape parameter of the person depicted in the image to the biometric parameter of the person depicted in the image. The hardware processor is also configured to execute the software code to perform a comparison of the calculated ratio with a predetermined value, and determine whether the person depicted in the image is an authentic depiction of the person based on the comparison of the calculated ratio with the predetermined value.

Abstract: Techniques for machine learning optimization are provided. A video comprising a plurality of segments is received, and a first segment of the plurality of segments is processed with a machine learning (ML) model to generate a plurality of tags, where each of the plurality of tags indicates presence of an element in the first segment. A respective accuracy value is determined for each respective tag of the plurality of tags, where the respective accuracy value is based at least in part on a maturity score for the ML model. The first segment is classified as accurate, based on determining that an aggregate accuracy of tags corresponding to the first segment exceeds a predefined threshold. Upon classifying the first segment as accurate, the first segment is bypassed during a review process.

Abstract: There is provided a system including a non-transitory memory storing an executable code and a hardware processor executing the executable code to receive a media content including a plurality of frames, divide the media content into a plurality of shots, each of the plurality of shots including a plurality of frames of the media content based on a first similarity between the plurality of frames, determine a plurality of sequential shots of the plurality of shots to be part of a first sub-scene of a plurality of sub-scenes of a scene based on a timeline continuity of the plurality of sequential shots, identify each of the plurality of shots of the media content and each of the plurality of sub-scenes with a corresponding beginning time code and a corresponding ending time code.

Abstract: A system includes a computing platform having processing hardware, and a memory storing software code and a machine learning (ML) model-based feature classifier. When executed, the software code receives media content including a first media component corresponding to a first media mode and a second media component corresponding to a second media mode, encodes the first media component using a first encoder to generate multiple first embedding vectors, and encodes the second media component using a second encoder to generate multiple second embedding vectors. The software code further combines the first embedding vectors and the second embedding vectors to provide an input data structure for a neural network mixer, process, using the neural network mixer, the input data structure to provide feature data corresponding to a feature of the media content, and predict, using the ML model-based feature classifier and the feature data, a classification of the feature.

Abstract: According to one implementation, a system includes a computing platform having processing hardware, a system memory storing a software code; and a machine learning model based classifier. The processing hardware is configured to execute the software code to receive tagging quality assurance (QA) data including multiple terms applied as tags and corrections to those tags, to identify, using the tagging QA data, a first problematic term, and to classify, using the machine learning model based classifier, the first problematic term as one of confusing or flawed. The processing hardware is further configured to execute the software code to obtain, when the first problematic term is classified as confusing, a comparative sample for clarifying use of the first problematic term, and to obtain, when the first problematic term is classified as flawed, modification data for editing a predetermined annotation taxonomy including the first problematic term.

Abstract: A content segmentation system includes a computing platform having processing hardware and a system memory storing a software code and a trained machine learning model. The processing hardware is configured to execute the software code to receive content, the content including multiple sections each having multiple content blocks in sequence, to select one of the sections for segmentation, and to identify, for each of the content blocks of the selected section, at least one respective representative unit of content. The software code is further executed to generate, using the at least one respective representative unit of content, a respective embedding vector for each of the content blocks of the selected section to provide a multiple embedding vectors, and to predict, using the trained machine learning model and the embedding vectors, subsections of the selected section, at least some of the subsections including more than one of the content blocks.

Abstract: A method includes producing a filter mask based on a blur mask and a saliency mask and identifying locations of a plurality of bounding boxes of a plurality of objects of interest in a received image. The method also includes applying the filter mask to the received image and to the locations of the plurality of bounding boxes in the received image to remove at least one object of interest from consideration. The method further includes performing a comparison of a location of a bounding box of the plurality of bounding boxes of an object of interest remaining in consideration to a predetermined safe region of the received image and generating a validation result based on the comparison.

Abstract: A video content matching system includes a computing platform having a hardware processor and a memory storing a software code. When executed, the software code obtains a reference digital profile of a reference video segment, obtains a target digital profile of target video content, and compares the reference and target digital profiles to detect a candidate video segment of the target video content for matching to the reference video segment. The software code also frame aligns reference video frames of the reference video segment with corresponding candidate video frames of the candidate video segment to provide frame aligned video frame pairs, pixel aligns the frame aligned video frame pairs to produce frame and pixel aligned video frame pairs, and identifies, using the frame and pixel aligned video frame pairs, the candidate video segment as a matching video segment or a non-matching video segment for the reference video segment.

Abstract: There is provided a system including a non-transitory memory storing an executable code and a hardware processor executing the executable code to receive a media content including a plurality of frames, divide the media content into a plurality of shots, each of the plurality of shots including a plurality of frames of the media content based on a first similarity between the plurality of frames, determine a plurality of sequential shots of the plurality of shots to be part of a first sub-scene of a plurality of sub-scenes of a scene based on a timeline continuity of the plurality of sequential shots, identify each of the plurality of shots of the media content and each of the plurality of sub-scenes with a corresponding beginning time code and a corresponding ending time code.

Abstract: According to one implementation, an automated audio mapping system includes a computing platform having a hardware processor and a system memory storing an audio mapping software code including an artificial neural network (ANN) trained to identify multiple different audio content types. The hardware processor is configured to execute the audio mapping software code to receive content including multiple audio tracks, and to identify, without using the ANN, a first music track and a second music track of the multiple audio tracks. The hardware processor is further configured to execute the audio mapping software code to identify, using the ANN, the audio content type of each of the multiple audio tracks except the first music track and the second music track, and to output a mapped content file including the multiple audio tracks each assigned to a respective one predetermined audio channel based on its identified audio content type.

Abstract: A method includes generating a delicate area map by performing a morphological function on a portion of a received first image and identifying a plurality of edges in the first image, the plurality of edges comprising a plurality of pixels. The method also includes verifying a first contrast metric for a first subset of pixels that are in the plurality of pixels but not in the delicate area map, verifying a second contrast metric for a second subset of pixels that are in the plurality of pixels and in the delicate area map, and generating a validation result based on the verifying of the first contrast metric and the verifying of the second contrast metric.

Abstract: A system for authenticating digital contents includes a computing platform having a hardware processor and a memory storing a software code. According to one implementation, the hardware processor executes the software code to receive digital content, identify an image of a person depicted in the digital content, determine an ear shape parameter of the person depicted in the image, determine another biometric parameter of the person depicted in the image, and calculate a ratio of the ear shape parameter of the person depicted in the image to the biometric parameter of the person depicted in the image. The hardware processor is also configured to execute the software code to perform a comparison of the calculated ratio with a predetermined value, and determine whether the person depicted in the image is an authentic depiction of the person based on the comparison of the calculated ratio with the predetermined value.

Abstract: A system includes a computing platform having processing hardware, and a system memory storing software code and a machine learning (ML) model. The processing hardware is configured to execute the software code to receive from a client, a request for a dataset, the request identifying a content type of the dataset, obtain the dataset having the content type, and select, based on the content type, an anonymization technique for the dataset, the anonymization technique selected so as to render at least one feature included in the dataset recognizable but unidentifiable. The processing hardware is further configured to execute the software code to anonymize, using the ML model and the selected anonymization technique, the at least one feature included in the dataset, and to output to the client, in response to the request, an anonymized dataset including the at least one anonymized feature.

Abstract: A video content matching system includes a computing platform having a hardware processor and a memory storing a software code. When executed, the software code obtains a reference digital profile of a reference video segment, obtains a target digital profile of target video content, and compares the reference and target digital profiles to detect a candidate video segment of the target video content for matching to the reference video segment. The software code also frame aligns reference video frames of the reference video segment with corresponding candidate video frames of the candidate video segment to provide frame aligned video frame pairs, pixel aligns the frame aligned video frame pairs to produce frame and pixel aligned video frame pairs, and identifies, using the frame and pixel aligned video frame pairs, the candidate video segment as a matching video segment or a non-matching video segment for the reference video segment.

Abstract: A system includes a computing platform having processing hardware and a memory storing a software code. The processing hardware executes the software code to receive a dataset including at least some data samples having multiple metadata labels, and identify a partitioning constraint and a partitioning of the dataset into data subsets. The software code also executed obtains, for each metadata label, a desired distribution ratio based on the number of the data subsets and a total number of instances that each metadata label has been applied to the data samples, aggregates, using the partitioning constraint, the data samples into data sample groups, assigns, using the partitioning constraint and the desired distribution ratio for each of the metadata labels, each of the data sample groups to one of the data subsets, wherein each of the data subsets are unique, and trains, using one of the data subsets, a machine learning model.