Abstract: A recommendation system leverages multi-target search to provide item listing recommendations and/or query suggestions. For a given input image with multiple objects, multi-target search uses object detection to detect each object, and stores complementary object data associating each object from the image. Additionally, a search of an item listing datastore is performed using each object from the image as a search query. Based on item listings returned as search results, complementary item listings data associating item listings is stored. In some configurations, the complementary item listings data is also used to train a machine learning model to predict complementary item listings for a given item listing. When an input item listing is received, item listing recommendations and/or query suggestions are determined for the input item listing using the complementary object data, the complementary item listing data, and/or the machine learning model.

Abstract: The present disclosure relates to compositions and methods for marking/tagging objects for identification. In particular, tagging objects with a nucleic acid taggant (genetic tag based merchandise authentication).

Abstract: Systems and methods are provided for automatically generating a thumbnail for a video on an online shopping site. The disclosed technology automatically generates a thumbnail for a video, where the thumbnail represents an item but not necessarily content of the video. A thumbnail generator receives a video that describes the item and an ordered list of item images associated with the item used in an item listing. The thumbnail generator extracts video frames from the video based on sampling rules and determines similarity scores for the sampled video frames. A similarity score indicates a degree of similarity between content of a video frame and an item image. The thumbnail generator determines weighted similarity scores based item images and occurrences of sampled video frames in the video. The disclosed technology generates a thumbnail for the video by selecting a sample video frame based on the weighted similarity scores.

Abstract: An assembly for a mailer is described. The assembly supports the mailing of articles such as trading cards and includes an insert defining a set of pockets shaped to receive the articles. The pockets are formed between attachment members of the insert and are arranged adjacent to each other along a length of the insert. Each pocket includes an open end arranged toward an upper end of the insert formed by a terminating edge of the insert. Further, each pocket includes a closed end arranged toward a lower end of the insert and formed by a folded edge of the insert. In one or more implementations, the assembly further includes a backer and a spacer shaped to fit against opposing surfaces of the insert that increase a rigidity and flatness of the assembly.

Abstract: Various embodiments use a neural network to analyze images for aspects that characterize the images, to present locations of those aspects on the images, and, additionally, to permit a user to interact with those locations on the images. For example, a user may interact with a visual cue over one of those locations to modify, refine, or filter the results of a visual search, performed on a publication corpus, that uses an input image (e.g., one captured using a mobile device) as a search query.

Abstract: A bad change detector for operational features of digital platforms is described. Metric data from a website is acquired by the bad change detector while implementing a first version of an operational feature of the website and while implementing a second version of the operational feature. A bad change to the website is detected by measuring an inequality among values of a frequency distribution defined by a time series of the metric data. The operational feature is reverted to the first version, automatically and without user intervention, in response to detecting the bad change, thereby improving operation of computing devices that implement the website.

Abstract: Dynamic shard allocation in a near real-time search platform is described. A computing system may include a cluster comprising a plurality of nodes, each node of the plurality of nodes comprising a plurality of shards storing searchable data. A query load distribution of the cluster is assessed in real-time. A first shard of a first node and a second shard of a second node are identified based on the query load distribution. The first shard of the first node is commanded to exchange with the second shard of the second node.

Abstract: Systems, methods, and computer program products for identifying a candidate product in an electronic marketplace based on a visual comparison between candidate product image visual text content and input query image visual text content. Unlike conventional optical character recognition (OCR) based systems, embodiments automatically localize and isolate portions of a candidate product image and an input query image that each contain visual text content, and calculate a visual similarity measure between the respective portions. A trained neural network may be re-trained to more effectively find visual text content by using the localized and isolated visual text content portions as additional ground truths. The visual similarity measure serves as a visual search result score for the candidate product. Any number of images of any number of candidate products may be compared to an input query image to enable text-in-image based product searching without resorting to conventional OCR techniques.

Abstract: A system, a method, and a device for authentication of a product includes one or more databases configured to store data of one or more products, and a user device communicatively coupled to the databases via a network. The user device includes at least one memory configured to store computer executable instructions, and at least one processor configured to execute the computer-executable instructions to receive, from an authenticator, product search data of the product, and to search the product in the databases based on the product search data. The product is listed by a user for authentication, and the product is authenticated by scanning an authentication tag attached to the product. The authentication tag is pre-programmed and becomes inactive when detached from the product. There is also a dual-purpose device for authenticating a commercial product and associating a brand with the authentication of the product.

Abstract: Systems, methods, and computer program products for identifying a candidate product in an electronic marketplace based on a visual comparison between candidate product image visual content and input query image visual content. Embodiments generate and store descriptive image signatures from candidate product images or selected portions of such images. A subsequently calculated visual similarity measure serves as a visual search result score for the candidate product in comparison to an input query image. Any number of images of any number of candidate products may be analyzed, such as for items available for sale in an online marketplace. Image analysis results are stored in a database and made available for subsequent automated on-demand visual comparisons to an input query image. The embodiments enable substantially real time visual based product searching of a potentially vast catalog of items.

Abstract: Techniques for mapping size information associated with a client to target brands, garments, sizes, shapes, and styles for which there is no standardized correlation. The size information associated with a client may be generated by modeling client garments, accessing computer aided drawing (CAD) files associated with client garments, or by analyzing a history of garment purchases associated with the client. Information for target garments may be generated in a similar fashion. A system may then create a standardized scale with a set of sizes for a target, and map a client base size to that standardized size scale. Similar matching and mapping may also be done with shape and style considerations. A recommendation based on the mapping may then be communicated to the client.

Abstract: Techniques for managing electronic user profiles are presented herein. An example method includes accessing, from a data structure, a user profile. The user profile can include a profile identifier and a plurality of data fields. The method also includes displaying, on a display device, an interactive user interface. The user interface can include a plurality of user interface action elements. Each of the user interface action elements can be associated with a data field in the data structure. Each of the user interface action elements can also be individually selectable by a respective user action to transmit the associated data field to a remote device. In response to receiving a selection of a user interface action element, the method can further include transmitting the associated data field and the profile identifier to a router configured to send, based on the profile identifier, the associated data field to the remote device.

Abstract: A query modality recommendation system provides recommendations to use a particular query modality based on one or more categories of search results for a search query. Upon receiving a search query in a first query modality at a search engine, the query modality recommendation system determines to recommend use of a second query modality based on one or more categories of the search results. For example, the first query modality may be a textual query and the second query modality may be an image query. In aspects, recommending use of the second query modality comprises comparing a first search performance of the one or more categories for the first query modality in historical search queries to a second search performance of the one or more categories for the second query modality in the historical search queries.

Abstract: A system receives image data associated with an item, where the image data comprising a view of the item from two or more angles; determines physical attributes of the item; generates a base model of the item; samples the base model to generate one or more sampled models, each of the one or more sampled models comprising a subset of the geometric data, the subset of the geometric data determined based on one or more device characteristics of one or more user devices that interface with the system; receives device characteristics of a user device associated with a request from the user device for the item; selects, based on the received device characteristics, a sampled model of the item; and transmits a data object comprising the selected sampled model to the user device to cause the user device to generate a three-dimensional rendering of the item.

Abstract: In various example embodiments, a system and method for dynamically generating virtual marketplace platforms are presented. The system receives a set of facility data, a set of selections for a set of user interaction objects, and a set of object placement selections. The set of user interaction objects includes a first subset and a second subset. The system generates a virtual facility comprising the facility data and the set of user interaction objects distributed based on the object placement selections. The system receives user data for a user interacting with the virtual facility and one or more objects of the first and second subset of user interaction objects, dynamically arranges the second subset of user interaction objects into a second arrangement and causes presentation of the virtual facility and the set of user interaction objects to the user.

Abstract: The disclosed technologies include receiving a request from a second computing device to verify ownership of a blockchain address. A challenge content is generated and sent to the requestor. A signature is received comprising a hash of the challenge content generated using a private key. A public key corresponding to the private key is obtained, and the signature is validated using the public key. In response to validating the signature, a characteristic is associated with a user associated with the blockchain address.

Abstract: An apparatus and method for real-time audio processing employs a gaze detection sensor to detect a direction of a user's gaze and output a gaze signal corresponding to the detected direction of the user's gaze. A digital signal processing unit responds to a plurality of signals corresponding to a plurality of sounds received at the apparatus, and the determined direction of gaze to identify a signal of interest from the plurality of signals using the gaze signal. The signal of interest is processed for output to the user. In embodiments, a microphone array provides the plurality of signals. An imaging sensor may work with either the microphone array or the gaze detection sensor to identify the signal of interest.

Abstract: Automated determination of web page rendering performance techniques and systems are described. In one example, a web page including multiple user-interactive elements that can be selected or navigated via user input is received. A frame rendering system is employed to automatically identify the user-interactive elements and generate scripts to simulate user input at the user-interactive elements. The generated scripts are then used to simulate user input at the user-interactive elements. The scripts may be generated to simulate user interaction via a variety of different device types, and under a variety of different network conditions. During the simulation, a rendering performance score for the web page is generated by monitoring rendering performance relative to a threshold rendering rate.

Abstract: The disclosed technologies include receiving a request from a second computing device to verify ownership of a blockchain address. A challenge content is generated and sent to the requestor. A signature is received comprising a hash of the challenge content generated using a private key. A public key corresponding to the private key is obtained, and the signature is validated using the public key. In response to validating the signature, a characteristic is associated with a user associated with the blockchain address.

Abstract: A method, system, and computer-readable medium are disclosed for generating a unified user profile. For example, a system may store, on a client device, a token under a first domain name. The token may specify state data for a communication session between the client device and a first content publisher addressed by the first domain name. The communication session utilizes a stateless communication protocol. The system may then generate a redirection resource locator. The redirection resource locator may include an identifier for a web object belonging to a second content publisher addressed by a second domain name and the token. The system then stores, on the client device, the token under the second domain name by directing the client device to send a web object request generated based at least in part on the redirection resource locator to the second content publisher. The web object request may request the web object from the second content publisher and including the token.