Adobe, Inc.

Xerox Corporation

Conduent Business Services, LLC

Fuji Xerox Co., Ltd.

Jayant Kumar

Raja Bala

Edgar A Bernal

Qun Li

Kerem Can Turgutlu

Zhe Lin

Rohith Mohan Dodle

Gaurav Kukal

Vipul Dalal

Kannan Iyer

Vera Lychagina

Mina Doroudi

Archit Kalra

Amine Ben Khalifa

Sanat Sharma

Beilei Xu

Peter Paul

Francine R Chen

Matthew Adam Shreve

Phillip J Emmett

Jing Zheng

Xiaodong Yang

Jeyasri Subramanian

Sudhakar Pandey

Peter J Baust

Tarun Vashisth

Vipulkumar C Dalal

Sharad Mangalick

Jianming Zhang

Palghat Srinivas Ramesh

Laurent Denoue

Martin Sidney Maltz

Scott Carter

Orhan Bulan

Sriganesh Madhvanath

Aliakbar Darabi

Shabnam Ghadar

Hengzhou Ding

Saeid Motiian

Oliver Brdiczka

Safwan R Wshah

Midhun Harikumar

Alexandru Vasile Costin

Daniel Miranda

Ashok Gupta

Benjamin Leviant

Fengbin Chen

Venkat Barakam

Megan Clar

Eric Harte

Kushith Amerasinghe

Sungmin Eum

Prethebha Chandrasegaran

Charles R McKinney

Ming Liu

Manasi Deshmukh

Chirag Arora

Karthik Suresh

Ravindra Sadaphule

Yun Zhang

Andrei Stefan

Xitong Yang

Sumeet Zaverilal Gala

Systems and methods for image processing are described. Embodiments of the present disclosure receive an image depicting an object; generate a sequence of tokens including a set of tokens corresponding to the object and a set of mask tokens corresponding to an additional object to be inserted into the image; generate a placement token value for the set of mask tokens based on the sequence of tokens using a sequence encoder, wherein the placement token value represents position information of the additional object; and insert the additional object into the image based on the position information to obtain a composite image.

Neural image compositing with layout transformers

Systems and methods for information retrieval are described. Embodiments generate a dense embedding for each of a plurality of media objects to be searched, generate a sparse embedding for each of the media objects using an encoder that takes the dense embedding as an input, wherein the sparse embedding satisfies a sparsity constraint that is applied to at least one layer of the encoder during training, and perform a search on the plurality of media objects based at least in part on the sparse embedding.

Retrieval aware embedding

An illustrator system accesses a multi-element document, the multi-element document including a plurality of elements. The illustrator system determines, for each of the plurality of elements, an element-specific topic distribution comprising a ranked list of topics. The illustrator system creates a first aggregated topic distribution from the determined element-specific topic distributions. The illustrator system determines a global intent for the multi-element document, the global intent including one or more terms from the first aggregated topic distribution. The illustrator system queries a database using the global intent to retrieve a substitute element. The illustrator system generates a replacement multi-element document that includes a substitute element in place of an element in the multi-element document The at least one substitute element is different from the element in the displayed multi-element document.

Deriving global intent from a composite document to facilitate editing of the composite document

Embodiments are disclosed for receiving a modal input including at least one of a text input or an image input. The method may include extracting an intent label from the modal input. The method may further include generating, by an intent embedding generator, an intent embedding from the intent label. The method may further include comparing the intent embedding to a plurality of candidate font embeddings to obtain one or more candidate fonts based on a similarity of the intent embedding to the plurality of candidate font embeddings in an embedding space. The method may further include identifying a recommended font based on the similarity of the intent embedding to a selected candidate font embedding of the plurality of candidate font embeddings.

Multimodal input contextual font recommendations

Disclosed are systems and methods for dynamically determining categories for images. A computer-implemented method may include training a neural network to receive an input image and determine one or more image categories associated with the input image; obtaining a set of images associated with a user; determining, using the trained neural network, one or more image categories associated with each image included in the obtained set of images; determining one or more dominant image categories associated with the user based on the determined image categories for the obtained set of images; and determining an image editing user interface for the user based on the determined one or more dominant image categories.

Systems and methods for dynamic image category determination

This disclosure describes methods, non-transitory computer readable storage media, and systems that generate a digital knowledge graph based on a plurality of tutorial content items to generate recommendations of digital resource items. Specifically, the disclosed system extracts a plurality of tasks, subject categories related to the tasks, and context signals related to an environment for the tasks from a plurality of tutorial content items for one or more digital content editing applications. The disclosed system generates a digital knowledge graph including nodes corresponding to the tasks and subject categories connected via edges based on relationships extracted from the tutorial content items. In some embodiments, the disclosed system also includes nodes corresponding to digital resource items in the digital knowledge graph or in a subgraph. The disclosed system utilizes the digital knowledge graph with context data to provide a recommendation of digital resource items for display at a client device.

Generating and utilizing a digital knowledge graph to provide contextual recommendations in digital content editing applications

The present disclosure relates to an image merging system that automatically and seamlessly detects and merges missing people for a set of digital images into a composite group photo. For instance, the image merging system utilizes a number of models and operations to automatically analyze multiple digital images to identify a missing person from a base image, segment the missing person from the second image, and generate a composite group photo by merging the segmented image of the missing person into the base image. In this manner, the image merging system automatically creates merged group photos that appear natural and realistic.

Automatically merging people and objects from multiple digital images to generate a composite digital image

Disclosed are systems and methods for dynamically determining categories for images. A computer-implemented method includes training a neural network to receive an input image and determine one or more image categories associated with the input image; obtaining a set of images associated with a user; and determining, using the trained neural network, one or more image categories associated with each image included in the obtained set of images.

Techniques are disclosed for parsing a source image, to identify segments of one or more objects within the source image. The parsing is carried out by an image parsing pipeline that includes three distinct stages comprising three respectively neural network models. The source image can include one or more objects. A first neural network model of the pipeline identifies a section of the source image that includes the object comprising a plurality of segments. A second neural network model of the pipeline generates, from the section of the source image, a mask image, where the mask image identifies one or more segments of the object. A third neural network model of the pipeline further refines the identification of the segments in the mask image, to generate a parsed image. The parsed image identifies the segments of the object, by assigning corresponding unique labels to pixels of different segments of the object.

Multi-object image parsing using neural network pipeline

There is described a computing device and method in a digital medium environment for custom auto tagging of multiple objects. The computing device includes an object detection network and multiple image classification networks. An image is received at the object detection network and includes multiple visual objects. First feature maps are applied to the image at the object detection network and generate object regions associated with the visual objects. The object regions are assigned to the multiple image classification networks, and each image classification network is assigned to a particular object region. The second feature maps are applied to each object region at each image classification network, and each image classification network outputs one or more classes associated with a visual object corresponding to each object region.

Custom auto tagging of multiple objects

Custom Auto Tagging of Multiple Objects

A mobile electronic device processes a sequence of images to identify and re-identify an object of interest in the sequence. An image sensor of the device, receives a sequence of images. The device detects an object in a first image as well as positional parameters of the device that correspond to the object in the first image. The device determines a range of positional parameters within which the object may appear in a field of view of the device. When the device detects that the object of interest exited the field of view it subsequently uses motion sensor data to determine that the object of interest has likely re-entered the field of view, it will analyze the current frame to confirm that the object of interest has re-entered the field of view.

Method and system for detecting that an object of interest has re-entered a field of view of an imaging device

A method and system for domain adaptation based on multi-layer fusion in a convolutional neural network architecture for feature extraction and a two-step training and fine-tuning scheme. The architecture concatenates features extracted at different depths of the network to form a fully connected layer before the classification step. First, the network is trained with a large set of images from a source domain as a feature extractor. Second, for each new domain (including the source domain), the classification step is fine-tuned with images collected from the corresponding site. The features from different depths are concatenated with and fine-tuned with weights adjusted for a specific task. The architecture is used for classifying high occupancy vehicle images.

Multi-layer fusion in a convolutional neural network for image classification

A method and system for identifying content relevance comprises acquiring video data, mapping the acquired video data to a feature space to obtain a feature representation of the video data, assigning the acquired video data to at least one action class based on the feature representation of the video data, and determining a relevance of the acquired video data.

System and method for relevance estimation in summarization of videos of multi-step activities

Growing community of inventors

San Jose, CA, United States of America

Jayant Kumar