In various example embodiments, a system and method for determining an item that has confirmed characteristics are described herein. An image that depicts an object is received from a client device. Structured data that corresponds to characteristics of one or more items are retrieved. A set of characteristics is determined, the set of characteristics being predicted to match with the object. An interface that includes a request for confirmation of the set of characteristics is generated. The interface is displayed on the client device. Confirmation that at least one characteristic from the set of characteristics matches with the object depicted in the image is received from the client device.

A method and apparatus are provided that analyzing sequence-to-sequence data, such as sequence-to-sequence speech data or sequence-to-sequence machine translation data for example, by minimum Bayes risk (MBR) training a sequence-to-sequence model and within introduction of applications of softmax smoothing to an N-best generation of the MBR training of the sequence-to-sequence model.

The present disclosure is directed to generating animated images for presentation by a dynamic keyboard interface. In particular, the methods and systems of the present disclosure can: receive data describing advertisement content, and data describing a first context in which to present the advertisement content; generate data describing a first animated image including at least a portion of the advertisement content; determine a second context in which to present the advertisement content; generate data describing a second animated image including at least a portion of the advertisement content; and communicate, to one or more user devices on which one or more applications are executed, data indicating a plurality of different animated images for presentation by a dynamic keyboard interface in association with the one or more applications, the plurality of different animated images comprising the first animated image and the second animated image.

In implementations of answering questions during video playback, a video system can receive a question related to a video at a timepoint of the video during playback of the video, and determine audio sentences of the video that occur within a segment of the video that includes the timepoint. The video system can generate a classification vector from words of the question and the audio sentences, and determine an answer to the question utilizing the classification vector. The video system can obtain answer candidates, and the answer to the question can be selected as one of the answer candidates based on matching the classification vector to one of the answer vectors.

A method and a system are described for context based clustering of one or more objects. The method comprises receiving, by the object clustering system, receiving, by an object clustering system, an object clustering request for one or more objects associated with a plurality of contextual parameters, where the plurality of contextual parameters comprises one or more physical attributes and one or more non-physical attributes. It further includes tagging the one or more non-physical attributes respectively to the one or more physical attributes. It further includes identifying a common context from the one or more physical attributes associated with the one or more objects based on the tagging. It further includes mapping the one or more physical attributes to the one or more objects based on the common context. It then includes clustering the one or more objects based on the mapping.

Systems, methods, and other techniques for extracting data from obituaries are provided. In some embodiments, an obituary containing a plurality of words is received. Using a machine learning model, an entity tag from a set of entity tags may be assigned to each of one or more words of the plurality of words. Each particular tag from the set of entity tags may include a relationship component and a category component. The relationship component may indicate a relationship between a particular word and the deceased individual. The category component may indicate a categorization of the particular word to a particular category from a set of categories. The extracted data may be stored in a genealogical database.

A method and a system for improved object marking in sensor data, as the result of which an at least partially automated annotation of objects or object classes in a recorded data set is possible. The method provides that a scene is detected in a first state by at least one sensor. An association of a first object marking with at least one object contained in the scene in a first data set containing the scene in the first state then takes place. The similar or matching scene is subsequently detected in a second state that is different from the first state by the at least one sensor, and an at least partial acceptance of the first object marking, contained in the first data set, for the object recognized in the second state of the scene as a second object marking in a second data set takes place.

A computer system trains a machine learning model. A vector representation is generated for each document in a collection of documents. The documents are clustered based on the vector representations of the documents to produce a plurality of clusters. A training set is produced by selecting one or more documents from each cluster, wherein the selected documents represent a sample of the collection of documents to train the machine learning model. The machine learning model is trained by applying the training set to the machine learning model. Embodiments of the present invention further include a method and program product for training a machine learning model in substantially the same manner described above.

An authentication server (2) includes: an image obtaining unit (210) that obtains a captured image obtained by capturing authentication target person with position information indicating a captured position at which the authentication target person is captured; a face authentication unit (212) that authenticates the authentication target person by using a face image of the authentication target person in the captured image; a background comparison unit (214) that determines, based on the position information, expected background information related to background behind the authentication target person expected to be included in the captured image, and compares the expected background information and actual background information related to a background behind the authentication target person actually included in the captured image; and a communication apparatus (23) that outputs information indicating an authenticated result of the authentication target person and information indicating a compared result of the expected background information and the actual background information.

Augmented reality features are selected for presentation to a display of an electronic eyewear device by using a camera of the electronic eyewear device to capture a scan image and processing the scan image to extract contextual signals. Simultaneously, voice data from the user is captured by a microphone of the electronic eyewear device and voice-to-text conversion of the captured voice data is performed to identify keywords in the voice data. The extracted contextual signals and the identified keywords are then used to select at least one augmented reality feature that matches the extracted contextual signals and the identified keywords, and the selected augmented reality feature is presented to the display for user selection. The contextual information thus refines the search results to provide the augmented reality feature best suited for the context of the scan image captured by the electronic eyewear device.