Technical solutions for video event recognition relate to the fields of knowledge graphs, deep learning and computer vision. A video event graph is constructed, and each event in the video event graph includes: M argument roles of the event and respective arguments of the argument roles, with M being a positive integer greater than one. For a to-be-recognized video, respective arguments of the M argument roles of a to-be-recognized event corresponding to the video are acquired. According to the arguments acquired, an event is selected from the video event graph as a recognized event corresponding to the video.

Technical solutions for video event recognition relate to the fields of knowledge graphs, deep learning and computer vision. A video event graph is constructed, and each event in the video event graph includes: M argument roles of the event and respective arguments of the argument roles, with M being a positive integer greater than one. For a to-be-recognized video, respective arguments of the M argument roles of a to-be-recognized event corresponding to the video are acquired. According to the arguments acquired, an event is selected from the video event graph as a recognized event corresponding to the video.

A translation support device includes a storage device and a control device. The storage device stores therein an original document file in which original document data is recorded, and a translated document file in which translated document data, representing a translated document translated from an original document represented by the original document data, is recorded. The control device includes a processor, and acts as a detector and a generator, when the processor executes a control program. The detector detects, through comparison between the original document file and the translated document file, a same portion contained in common in both of the files, as an untranslated portion. The generator generates untranslated portion information indicating the untranslated portion.

A translation support device includes a storage device and a control device. The storage device stores therein an original document file in which original document data is recorded, and a translated document file in which translated document data, representing a translated document translated from an original document represented by the original document data, is recorded. The control device includes a processor, and acts as a detector and a generator, when the processor executes a control program. The detector detects, through comparison between the original document file and the translated document file, a same portion contained in common in both of the files, as an untranslated portion. The generator generates untranslated portion information indicating the untranslated portion.

Techniques are described for migrating information from a first account to a second account, based on analyzed image(s) of document(s). Image(s) of a document may be generated using an image capture device of a smartphone or other portable computing device. The image(s) may be analyzed, through pattern recognition analysis or barcode scanning, to extract the information from the image(s). The information may then be employed to schedule a transaction, such as payment of a bill described in the information. In some instances, the extracted information may be used as part of an account migration process, in which transactions are migrated from a first account to a second account.

In some implementations, a transaction card security system may detect a transaction card in an image, and may perform image processing to identify one or more character sequences or one or more designs that appear on the transaction card. The one or more character sequences or the one or more designs may identify an institution associated with the transaction card and/or a cardholder associated with the transaction card. The transaction card security system may identify the institution or the cardholder associated with the transaction card based on the one or more character sequences or the one or more designs, and may perform one or more actions relating to security of the transaction card based on detecting the transaction card in the image and identifying the institution or the cardholder associated with the transaction card.

The proposed model is a Variational Autoencoder having a learnable prior that is parametrized with a Tensor Train (VAE-TTLP). The VAE-TTLP can be used to generate new objects, such as molecules, that have specific properties and that can have specific biological activity (when a molecule). The VAE-TTLP can be trained in a way with the Tensor Train so that the provided data may omit one or more properties of the object, and still result in an object with a desired property.

A client device configured with a neural network includes a processor, a memory, a user interface, a communications interface, a power supply and an input device, wherein the memory includes a trained neural network received from a server system that has trained and configured the neural network for the client device. A server system and a method of training a neural network are disclosed.

Methods and systems are provided for end-to-end text recognition in digitized documents of handwritten characters over multiple lines without explicit line segmentation. An image is received. Based on the image, one or more feature maps are determined. Each of the one or more feature maps include one or more feature vectors. Based at least in part on the one or more feature maps, one or more scalar scores are determined. Based on the one or more scalar scores, one or more attention weights are determined. By applying the one or more attention weights to each of the one or more feature vectors, one or more image summary vectors are determined. Based at least in part on the one or more image summary vectors, one or more handwritten characters are determined.

A computer implemented method of performing single pass optical character recognition (OCR) including at least one fully convolutional neural network (FCN) engine including at least one processor and at least one memory, the at least one memory including instructions that, when executed by the at least processor, cause the FCN engine to perform a plurality of steps. The steps include preprocessing an input image, extracting image features from the input image, determining at least one optical character recognition feature, building word boxes using the at least one optical character recognition feature, determining each character within each word box based on character predictions and transmitting for display each word box including its predicted corresponding characters.