Abstract: An image processing system automatically segments and labels an image using a hierarchical classification model. A global classification model determines initial labels for an image based on features of the image. A label-based descriptor is generated based on the initial labels. A local classification model is then selected from a plurality of learned local classification model based on the label-based descriptor. The local classification model is applied to the features of the input image to determined refined labels. The refined labels are stored in association with the input image.

Abstract: A method, computer program product, and computer system for identifying a first portion of a facial image in a first image, wherein the first portion includes noise. A corresponding portion of the facial image is identified in a second image, wherein the corresponding portion includes less noise than the first portion. One or more filter parameters of the first portion are determined based upon, at least in part, the first portion and the corresponding portion. At least a portion of the noise from the first portion is smoothed based upon, at least in part, the one or more filter parameters. At least a portion of face specific details from the corresponding portion is added to the first portion.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage medium, for training a neural network, wherein the neural network is configured to receive an input data item and to process the input data item to generate a respective score for each label in a predetermined set of multiple labels. The method includes actions of obtaining a set of training data that includes a plurality of training items, wherein each training item is associated with a respective label from the predetermined set of multiple labels; and modifying the training data to generate regularizing training data, comprising: for each training item, determining whether to modify the label associated with the training item, and changing the label associated with the training item to a different label from the predetermined set of labels, and training the neural network on the regularizing data.

Abstract: A video server receives an uploaded video and determines whether the video contains third-party content and which portions of the uploaded video match third-party content. The video server determines whether to degrade the matching portions and/or how (e.g., extent, type) to do so. The video server separates the matching portion from original portions in the uploaded video and generates a degraded version of the matching content by applying an effect such as compression, edge distortion, temporal distortion, noise addition, color distortion, or audio distortion. The video server combines the degraded portions with the original portions to output a degraded version of the uploaded video. The video server stores and/or distributes the degraded version of the uploaded video. The video server may offer the uploading user licensing terms with the content owner that the user may accept to reverse the degradation.

Abstract: Image similarity operations are performed in which a seed image is analyzed, and a set of semantic classifications are determined from analyzing the seed image. The set of semantic classifications can include multiple positive semantic classifications. A distance measure is determined that is specific to the set of semantic classifications. The seed image is compared to a collection of images using the distance measure. A set of similar images is determined from comparing the seed image to the collection of images.

Abstract: Systems and techniques are provided for a ranking approach to train deep neural nets for multilabel image annotation. Label scores may be received for labels determined by a neural network for training examples. Each label may be a positive label or a negative label for the training example. An error of the neural network may be determined based on a comparison, for each of the training examples, of the label scores for positive labels and negative labels for the training example and a semantic distance between each positive label and each negative label for the training example. Updated weights may be determined for the neural network based on a gradient of the determined error of the neural network. The updated weights may be applied to the neural network to train the neural network.

Abstract: This disclosure relates to transformation invariant media matching. A fingerprinting component can generate a transformation invariant identifier for media content by adaptively encoding the relative ordering of interest points in media content. The interest points can be grouped into subsets, and stretch invariant descriptors can be generated for the subsets based on ratios of coordinates of interest points included in the subsets. The stretch invariant descriptors can be aggregated into a transformation invariant identifier. An identification component compares the identifier against a set of identifiers for known media content, and the media content can be matched or identified as a function of the comparison.

Abstract: Systems and methods for facilitating media fingerprinting are provided. In one aspect, a system can include: a memory, a microprocessor, a communication component that receives media; and a media fingerprinting component that fingerprints the media. The media fingerprinting component employs a fingerprint generation component stored in the memory and includes: a first hash generation component that generates sets of hashes corresponding to versions of the media; and a second hash generation component that computes a final hash based, at least, on hashing the sets of hashes. In some aspects, the media fingerprinting component can generate a flip-resistant fingerprint based, at least, on the final hash. In some aspects, the flip-resistant fingerprint is the final hash.

Abstract: An image processing system automatically segments and labels an image using a hierarchical classification model. A global classification model determines initial labels for an image based on features of the image. A label-based descriptor is generated based on the initial labels. A local classification model is then selected from a plurality of learned local classification model based on the label-based descriptor. The local classification model is applied to the features of the input image to determined refined labels. The refined labels are stored in association with the input image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using a neural network system that includes a batch normalization layer. One of the methods includes receiving a respective first layer output for each training example in the batch; computing a plurality of normalization statistics for the batch from the first layer outputs; normalizing each component of each first layer output using the normalization statistics to generate a respective normalized layer output for each training example in the batch; generating a respective batch normalization layer output for each of the training examples from the normalized layer outputs; and providing the batch normalization layer output as an input to the second neural network layer.

Abstract: A computer-implemented method, computer program product, and computing system is provided for interacting with images having similar content. In an embodiment, a method may include identifying a plurality of photographs as including a common characteristic. The method may also include generating a flipbook media item including the plurality of photographs. The method may further include associating one or more interactive control features with the flipbook media item.

Abstract: A method and apparatus are provided for performing an image search based on a search query having a portion P1 and a portion P2. Based on the first search query, a second search query is generated that includes a portion P3 and the portion P2 such that the second search query is broader in scope than the first search query, while still retaining the portion P2 of the first query. A first image search is then performed for the first search query to obtain a first set of search results and a second image search is performed for the second search query to obtain a second set of search results. Consequently, an image from the first set of search results is selected for presentation to a user, wherein the selection is based on content of the second set of search results.

Abstract: A computer-implemented method, computer program product, and computing system is provided for interacting with images having similar content. In an embodiment, a method may include identifying a plurality of photographs as including a common characteristic. The method may also include generating a flipbook media item including the plurality of photographs. The method may further include associating one or more interactive control features with the flipbook media item.

Abstract: Methods, systems and computer program product embodiments for hashing techniques for determining similarity between data sets are described herein. A method embodiment includes, initializing a random number generator with a weighted min-hash value as a seed, wherein the weighted min-hash value approximates a similarity distance between data sets. A number of bits in the weighted min-hash value is determined by uniformly sampling an integer bit value using the random number generator. A system embodiment includes a repository configured to store a plurality of data sets and a hash generator configured to generate weighted min-hash values from the data sets. The system further includes a similarity determiner configured to determine a similarity between the data sets.

Abstract: A method and apparatus for performing sparse coding dictionary priming are disclosed. Sparse coding dictionary priming may include iteratively training a coding dictionary, which may include a plurality of codewords or bases. Iteratively training the coding dictionary may include identifying a sampling index cardinality, identifying a portion of a video stream, decomposing the portion of the video stream, and updating the codeword based on the portion of the video stream. Decomposing the portion of the video stream may include randomly identifying a set of codewords from the plurality of codewords wherein a cardinality of the set of codewords is the sampling index cardinality and wherein the sampling index cardinality is less a cardinality of the plurality of codewords, and determining a codeword having a maximum correlation with the portion of the video stream from the set of codewords.

Abstract: A linear function describing a framework for identifying an object of class k in an image sample x may be described by: wk*x+bk, where bk is the bias term. The higher the value obtained for a particular classifier, the better the match or strength of identity. A method is disclosed for classifier and/or content padding to convert dot-products to distances, applying a hashing and/or nearest neighbor technique on the resulting padded vectors, and preprocessing that may improve the hash entropy. A vector for an image, an audio, and/or a video may be received. One or more classifier vectors may be obtained. A padded image, video, and/or audio vector and classifier vector may be generated. A dot product may be approximated and a hashing and/or nearest neighbor technique may be performed on the approximated dot product to identify at least one class (or object) present in the image, video, and/or audio.

Abstract: Systems, methods and computer readable media for image enhancement using learned non-photorealistic effects. In some implementations, a method can include obtaining an original image. The method can also include analyzing the original image to determine one or more characteristics of the original image. The method can further include selecting one or more filters based on the one or more characteristics and applying the one or more filters to the original image to generate a modified image. The method can include causing the modified image to be displayed.

Abstract: Systems and methods for facilitating video fingerprinting are provided. In one embodiment, a system can include: a memory, a microprocessor, a communication component that receives a video, and a video fingerprinting component that fingerprints the video with a subfingerprint (SFP). The video fingerprinting component can employ an SFP component stored in the memory and that comprises: a feature extraction component that determines local descriptors for at least one frame of a video; and a quantization component that quantizes the local descriptors to generate first frame information including a set of values for the at least one frame. The SFP component can also include: an accumulation component that accumulates first frame information over a snippet of the video; and an SFP generation component that computes the SFP associated with the snippet. The SFP can be computed based on a hash based on the accumulated first frame information over the snippet.

Abstract: This disclosure relates to transformation invariant media matching. A fingerprinting component can generate a transformation invariant identifier for media content by adaptively encoding the relative ordering of signal markers in media content. The signal markers can be adaptively encoded via reference point geometry, or ratio histograms. An identification component compares the identifier against a set of identifiers for known media content, and the media content can be matched or identified as a function of the comparison.

Abstract: A method and system generates and compares fingerprints for videos in a video library. The video fingerprints provide a compact representation of the temporal locations of discontinuities in the video that can be used to quickly and efficiently identify video content. Discontinuities can be, for example, shot boundaries in the video frame sequence or silent points in the audio stream. Because the fingerprints are based on structural discontinuity characteristics rather than exact bit sequences, visual content of videos can be effectively compared even when there are small differences between the videos in compression factors, source resolutions, start and stop times, frame rates, and so on. Comparison of video fingerprints can be used, for example, to search for and remove copyright protected videos from a video library. Furthermore, duplicate videos can be detected and discarded in order to preserve storage space.