Disclosed herein are embodiments of systems, methods, and products for a webly supervised training of a convolutional neural network (CNN) to predict emotion in images. A computer may query one or more image repositories using search keywords generated based on the tertiary emotion classes of Parrott's emotion wheel. The computer may filter images received in response to the query to generate a weakly labeled training dataset labels associated with the images that are noisy or wrong may be cleaned prior to training of the CNN. The computer may iteratively train the CNN leveraging the hierarchy of emotion classes by increasing the complexity of the labels (tags) for each iteration. Such curriculum guided training may generate a trained CNN that is more accurate than the conventionally trained neural networks.

The present disclosure provides an eye animated expression display method. The method includes: receiving an instruction for displaying an eye animated expression; parsing a JSON file storing the eye animated emoticon to obtain a parsing result; and displaying the eye animated emoticon on the eye display screen based on the parsing result. The present disclosure further provides a robot. In the above-mentioned manner, the present disclosure is capable of improving the interactive performance of the eyes of the robot while reducing the space for storing eye animated expressions.

Embodiments provide systems, methods, and non-transitory computer storage media for providing search result images based on associations of keywords and depth-levels of an image. In embodiments, depth-levels of an image are identified using depth-map information of the image to identify depth-segments of the image. The depth-segments are analyzed to determine keywords associated with each depth-segment based on objects, features, or content in each depth-segment. An image depth-level data structure is generated by matching keywords generated for the entire image with the keywords at each depth-level and assigning the depth-level to the keyword in the image depth-level data structure for the entire image. The image depth-level data structure may be queried for images that contain keywords and depth-level information that match the keywords and depth-level information specified in a search query.

Embodiments provide systems, methods, and non-transitory computer storage media for providing search result images based on associations of keywords and depth-levels of an image. In embodiments, depth-levels of an image are identified using depth-map information of the image to identify depth-segments of the image. The depth-segments are analyzed to determine keywords associated with each depth-segment based on objects, features, or content in each depth-segment. An image depth-level data structure is generated by matching keywords generated for the entire image with the keywords at each depth-level and assigning the depth-level to the keyword in the image depth-level data structure for the entire image. The image depth-level data structure may be queried for images that contain keywords and depth-level information that match the keywords and depth-level information specified in a search query.

A method for receiving a request for a design template from a client device, the design template including a dynamic media file indicator is provided. The request includes collecting user information indicative of a location of the client device, a demographic datum of a user associated with the client device, or a language of the user associated with the client device, and selecting a media file from a database of media files based on the user information. The method also includes modifying the design template based on the user information to include the media file and providing the design template comprising the media file for display by the client device. A computer-readable medium including commands and a system including a processor to execute the commands and perform the above method are also provided.

Disclosed herein are embodiments of systems, methods, and products comprises an analytic server, which uses scalable vector graphic (SVG) format to encapsulate building floorplan and metadata. The analytic server creates a floorplan map in SVG format that includes both a graphic map and a specification file. When a user issues an information request by clicking on one graphical element, the analytic server determines the object identifier of the clicked graphical element, queries the specification file to receive metadata about the clicked graphical element based on the object identifier, and renders a user interface to display the metadata about the graphical element. When the user modifies the graphical element, the analytic server determines new data of the graphical element and updates the corresponding object metadata with the new data in the specification file.

Disclosed herein are embodiments of systems, methods, and products comprises an analytic server, which uses scalable vector graphic (SVG) format to encapsulate building floorplan and metadata. The analytic server creates a floorplan map in SVG format that includes both a graphic map and a specification file. When a user issues an information request by clicking on one graphical element, the analytic server determines the object identifier of the clicked graphical element, queries the specification file to receive metadata about the clicked graphical element based on the object identifier, and renders a user interface to display the metadata about the graphical element. When the user modifies the graphical element, the analytic server determines new data of the graphical element and updates the corresponding object metadata with the new data in the specification file.

Disclosed herein are embodiments of systems, methods, and products comprises an analytic server, which uses scalable vector graphic (SVG) format to encapsulate building floorplan and metadata. The analytic server creates a floorplan map in SVG format that includes both a graphic map and a specification file. When a user issues an information request by clicking on one graphical element, the analytic server determines the object identifier of the clicked graphical element, queries the specification file to receive metadata about the clicked graphical element based on the object identifier, and renders a user interface to display the metadata about the graphical element. When the user modifies the graphical element, the analytic server determines new data of the graphical element and updates the corresponding object metadata with the new data in the specification file.

Systems and methods for creating a physical memento with digital tracking are provided herein. In one example, a system may comprise receiving, at one or more processors, a personal message; transmitting, at the one or more processors via a network interface device coupled to the one or more processors, a secure message based on the personal message to a distributed ledger network, wherein the secure message is recorded in the distributed ledger network and the secure message comprises a timestamp associated with the message; and engraving, via one or more engraving tools, a physical item with information relevant to the message.

A system for presenting a collection of objects including a database of images for each of the collection of objects and a computer in data communications with the database. The system also includes a plurality of tags respectively associated with each of the collection of objects and data associated with each of the collection of objects both of which are stored in the database together with the corresponding image. Further, the system has a mosaic created as an array of at least some of the images from each of the collection of objects. The computer includes software that is configured to receive an image selection from an array position of the mosaic or one of the plurality of tags and to retrieve and transmit the corresponding image and data from the database for display.