Adobe, Inc.

Matthew Douglas Hoffman

Gautham J Mysore

Hailin Jin

Stephen J DiVerdi

Chen Fang

Dawen Liang

Longqi Yang

Ardavan Saeedi

Lubomira A Dontcheva

Alan Wilson

Zhicheng Liu

Nicolas Maurice Boulanger-Lewandowski

The present disclosure is directed towards methods and systems for determining multimodal image edits for a digital image. The systems and methods receive a digital image and analyze the digital image. The systems and methods further generate a feature vector of the digital image, wherein each value of the feature vector represents a respective feature of the digital image. Additionally, based on the feature vector and determined latent variables, the systems and methods generate a plurality of determined image edits for the digital image, which includes determining a plurality of set of potential image attribute values and selecting a plurality of sets of determined image attribute values from the plurality of sets of potential image attribute values wherein each set of determined image attribute values comprises a determined image edit of the plurality of image edits.

Generating multimodal image edits

A digital medium environment includes an asset processing application that performs editing of assets. A projection function is trained using pairs of actions pertaining to software edits, and assets resulting from the actions to learn a joint embedding between the actions and the assets. The projection function is used in the asset processing application to recommend software actions to create an asset, and also to recommend assets to demonstrate the effects of software actions. Recommendations are based on ranking distance measures that measure distances between actions representations and asset representations in a vector space.

Recommending software actions to create an image and recommending images to demonstrate the effects of software actions

This disclosure involves personalizing user experiences with electronic content based on application usage data. For example, a user representation model that facilitates content recommendations is iteratively trained with action histories from a content manipulation application. Each iteration involves selecting, from an action history for a particular user, an action sequence including a target action. An initial output is computed in each iteration by applying a probability function to the selected action sequence and a user representation vector for the particular user. The user representation vector is adjusted to maximize an output that is generated by applying the probability function to the action sequence and the user representation vector. This iterative training process generates a user representation model, which includes a set of adjusted user representation vectors, that facilitates content recommendations corresponding to users' usage pattern in the content manipulation application.

Personalizing user experiences with electronic content based on user representations learned from application usage data

Generating multimodal image edits for a digital image

Sound processing using a product-of-filters model is described. In one or more implementations, a model is formed by one or more computing devices for a time frame of sound data as a product of filters. The model is utilized by the one or more computing devices to perform one or more sound processing techniques on the time frame of the sound data.

Sound processing using a product-of-filters model

Systems and methods are disclosed for analyzing a plurality of clickstreams associated with a resource to identify popular navigational patterns traversed by users of the resource. The analysis provides a navigational framework for performing continued analysis on segmented portions of the identified navigational patterns. To facilitate the analysis, clickstreams associated with the resource are analyzed to identify sets of clickstreams that have a common group of assets with which users of the resource interacted. Navigational patterns, which include commonly traversed series of assets interacted with by the users, are determined for the identified sets. The navigational pattern is then provided to identify popular navigational patterns traversed by users of the resource.

Clickstream visual analytics based on maximal sequential patterns

Sound processing techniques using recurrent neural networks are described. In one or more implementations, temporal dependencies are captured in sound data that are modeled through use of a recurrent neural network (RNN). The captured temporal dependencies are employed as part of feature extraction performed using nonnegative matrix factorization (NMF). One or more sound processing techniques are performed on the sound data based at least in part on the feature extraction.

Non-negative matrix factorization regularized by recurrent neural networks for audio processing

Sound enhancement techniques through dereverberation are described. In one or more implementations, a method is described of enhancing sound data through removal of reverberation from the sound data by one or more computing devices. The method includes obtaining a model that describes primary sound data that is to be utilized as a prior that assumes no prior knowledge about specifics of the sound data from which the reverberation is to be removed. A reverberation kernel is computed having parameters that, when applied to the model that describes the primary sound data, corresponds to the sound data from which the reverberation is to be removed. The reverberation is removed from the sound data using the reverberation kernel.

Sound enhancement through deverberation

Methods and systems for source separation based on determining a number of bases for a nonnegative matrix factorization (NMF) model are disclosed. A method includes receiving, at a computing device, a mixed signal including a combination of first signal data and second signal data. The method also includes generating, by the computing device, a time-frequency representation of the mixed signal. The method further includes determining, by applying a structured stochastic variational inference (SSVI) algorithm to the NMF model, a number of bases for a dictionary of signal-related components of the mixed signal. The method uses the number of bases and the time-frequency representation to construct the dictionary and an activation matrix of weights, the weights indicating how active each one of the signal-related components is at a given time. The method then uses the dictionary and the activation matrix to separate the first signal data from the second signal data.

Growing community of inventors

San Francisco, CA, United States of America

Matthew Douglas Hoffman