Abstract: A method includes receiving data characterizing a request to execute an analytic model. The analytic model can include an executable representation associated with a physical system. The method can also include determining, based on the request, a deployment type associated with the analytic model. The deployment type can characterize temporal and computing resource requirements for executing the analytic model using a plurality of computing resources. The method can also include providing the deployment type, deploying the analytic model based on the deployment type, and executing the analytic model. Related systems, techniques, and non-transitory computer readable mediums are also described.

Abstract: The disclosure includes a system and method for distinguishing between stock keeping units of similar appearance that vary in size. An image recognition application receives an image depicting a plurality of items, the image including a reference marker with a known physical dimension. The image recognition application performs image recognition to identify an item in the image and a region of interest for the identified image. The image recognition application further determines a pixel-to-physical dimension ratio using the dimension of a region of interest of the reference marker and the known physical dimension of the reference marker. Finally, the image recognition application determines a stock keeping unit identifier of the identified item in the image based on the pixel-to-physical dimension ratio and a dimension of the region of interest of the identified item.

Abstract: The disclosure includes a system and method for identifying advertising content and providing a user of a mobile device with a channel related to the advertising content. A recognition application receives advertising content comprising a series of frames, identifies images corresponding to the frames within the advertising content, identifies a first set of feature points from a first image of the advertising content, determines whether the first set of feature points matches a second set of feature points stored in a database, and in response to determining that the first set of feature points fails to match the second set of feature points, identifies the first image as being unique, indexes the first image and the first set of feature points and associates the first image with a channel.

Abstract: A crowdsourced question and answer platform enhanced with image recognition technology is disclosed. The platform generates and organizes conversations surrounding an object recognized from an image uploaded by a user. Generating and organizing conversations includes receiving an image a from a user, analyzing the image to recognize an object in the image, receiving a comment related to the recognized object in the image from the user, generating content related to the recognized object in the image based on the received comment and adding the content related to the recognized object in the image to a conversation corresponding to the recognized object in the image.

Abstract: The disclosure includes a system and method for distinguishing between stock keeping units of similar appearance that vary in size. An image recognition application receives an image including a shelving unit stocking a plurality of items, identifies each item in the image, generates a region of interest for each identified item in the image, identifies a physical dimension of a portion of region depicted in the image, determines a dimension of the region of interest for each identified item and the portion of region in pixels, determines a pixel-to-physical dimension ratio using the dimension in pixels of the portion of region and the physical dimension of the portion of region depicted in the image, and determines a stock keeping unit identifier of each identified item in the image based on the pixel-to-physical dimension ratio and the dimension of the region of interest for each identified item.

Abstract: The disclosure includes a system and method for recommending an advertising campaign based on which channels are popular. A recognition application receives captured images from user devices, the captured images including information about products, identify indexed images that match the captured images, identify metadata about the captured images including information associated with products in the captured images, determine popularity of each channel based on a number of interactions that users have had with channels during a time period based on the metadata, receive an advertisement and provide on the one or more channels the advertisement based on the popularity of each channel.

Abstract: A system and method that generates a candidate list of indexed images that potentially match an object in a query image is disclosed. The method includes receiving a query image including an object, receiving a plurality of indexed images that match the object, computing a region of interest for the object, computing an overlap between a first region of interest corresponding to a first indexed image and a second region of interest corresponding to a second indexed image, determining that the overlap between the first region of interest and the second region of interest satisfies a threshold and including the first indexed image and the second indexed image in a candidate list of indexed images.

Abstract: The disclosure includes a system and method for grouping users into one or more categories for delivering targeted advertisements. A media application receives a captured image from a user, identifies an indexed image matching the captured image, retrieves metadata describing the captured image responsive to identifying the indexed image, generates a user profile for the user based on the metadata describing the captured image and a history of at least one previously captured image associated with the user, identifies a product in the captured image based on the metadata describing the captured image, provides the user with information about the product, updates the user profile based on how the user interacts with the product, and categorizes the user into one or more groups based on the user profile.

Abstract: The disclosure includes a system and method selecting advertisements for users based on image capturing patterns across different media. A media application receives a captured image including information about a product from a user, identifying an indexed image matching the captured image including information about the product, retrieving metadata describing the captured image including information about the product responsive to identifying the indexed image, retrieving a user profile stored for the user, identifying an advertisement from a set of advertisements based on the user profile and the metadata describing the captured image including information about the product and providing the user with the advertisement based on the user profile.

Abstract: A system and method that generates a candidate list of indexed images that potentially match an object in a query image is disclosed. The method includes receiving a query image including an object, receiving a plurality of indexed images that match the object, computing a region of interest for the object, computing an overlap between a first region of interest corresponding to a first indexed image and a second region of interest corresponding to a second indexed image, determining that the overlap between the first region of interest and the second region of interest satisfies a threshold and including the first indexed image and the second indexed image in a candidate list of indexed images.

Abstract: The disclosure includes a system and method for distinguishing between items of similar appearance that vary in size. An image recognition application receives an image including a plurality of items, identifies each item in the image, generates a region of interest for each identified item in the image, determines a dimension of the region of interest for each identified item in pixels, determines a plurality of pixel-to-physical dimension ratios for each identified item, identifies a selected pixel-to-physical dimension ratio among the plurality of pixel-to-physical dimension ratios, and determines a stock keeping unit identifier of each identified item in the image based on the selected pixel-to-physical dimension ratio and the dimension of the region of interest for each identified item.

Abstract: A method for sequencing products on a retail shelf, or other objects, recognized in an image of the retail shelf includes detecting products in the received image and calculating a final sequence position for each detected product. The final sequence position is calculated by generating a region of interest for each detected product in the received image, generating a plurality of unique raster numbers for each region of interest using a raster number equation by varying parameters of the raster number equation based on pixel coordinates of each region of interest, determining a plurality of sequence positions for each region of interest using the plurality of unique raster numbers, and determining the final sequence position for each region of interest using the plurality of sequence positions for each region of interest. The disclosure also includes systems for implementing the method.

Abstract: Techniques are described for providing automated recommendations of real-world locations, such as businesses, for users to visit based at least in part on historical location-preference information. The historical location-preference information used by the recommendation system may include the historical location-preference information of the person that requests the recommendation, other people explicitly identified as participants by the requestor, and/or other people implicitly determined to be participants. The historical location-preference information may be explicit, such as “check-ins” or reviews, or implicit. Implicit participants may be identified in a variety of ways, including social network relationships and the context in which the recommendation request is submitted.

Abstract: The disclosure includes a system and method for distinguishing between stock keeping units of similar appearance that vary in size. An image recognition application receives an image including a shelving unit stocking a plurality of items, identifies each item in the image, generates a region of interest for each identified item in the image, identifies a physical dimension of a portion of region depicted in the image, determines a dimension of the region of interest for each identified item and the portion of region in pixels, determines a pixel-to-physical dimension ratio using the dimension in pixels of the portion of region and the physical dimension of the portion of region depicted in the image, and determines a stock keeping unit identifier of each identified item in the image based on the pixel-to-physical dimension ratio and the dimension of the region of interest for each identified item.

Abstract: A crowdsourced question and answer platform enhanced with image recognition technology is disclosed. The platform generates and organizes conversations surrounding an object recognized from an image uploaded by a user. Generating and organizing conversations includes receiving an image a from a user, analyzing the image to recognize an object in the image, receiving a comment related to the recognized object in the image from the user, generating content related to the recognized object in the image based on the received comment and adding the content related to the recognized object in the image to a conversation corresponding to the recognized object in the image.

Abstract: The disclosure includes a system and method for distinguishing between stock keeping units of similar appearance that vary in size. An image recognition application receives an image depicting a plurality of items, the image including a reference marker with a known physical dimension. The image recognition application performs image recognition to identify an item in the image and a region of interest for the identified image. The image recognition application further determines a pixel-to-physical dimension ratio using the dimension of a region of interest of the reference marker and the known physical dimension of the reference marker. Finally, the image recognition application determines a stock keeping unit identifier of the identified item in the image based on the pixel-to-physical dimension ratio and a dimension of the region of interest of the identified item.

Abstract: The disclosure includes a system and method for distinguishing between items of similar appearance that vary in size. An image recognition application receives an image including a plurality of items, identifies each item in the image, generates a region of interest for each identified item in the image, determines a dimension of the region of interest for each identified item in pixels, determines a plurality of pixel-to-physical dimension ratios for each identified item, identifies a selected pixel-to-physical dimension ratio among the plurality of pixel-to-physical dimension ratios, and determines a stock keeping unit identifier of each identified item in the image based on the selected pixel-to-physical dimension ratio and the dimension of the region of interest for each identified item.

Abstract: A method for sequencing products on a retail shelf, or other objects, recognized in an image of the retail shelf includes detecting products in the received image and calculating a final sequence position for each detected product. The final sequence position is calculated by generating a region of interest for each detected product in the received image, generating a plurality of unique raster numbers for each region of interest using a raster number equation by varying parameters of the raster number equation based on pixel coordinates of each region of interest, determining a plurality of sequence positions for each region of interest using the plurality of unique raster numbers, and determining the final sequence position for each region of interest using the plurality of sequence positions for each region of interest. The disclosure also includes systems for implementing the method.

Abstract: The disclosure includes a system and method for distinguishing between stock keeping units of similar appearance that vary in size. An image recognition application receives an image depicting a plurality of items, identifies each item in the image, generates a region of interest for each identified item in the image, determines a pixel dimension of the region of interest for each identified item, determines whether one of the identified items in the image is a reference marker with a stored physical dimension, determines a pixel-to-physical dimension ratio for the reference marker using the dimension in pixels and stored physical dimension of the reference marker, and determines a stock keeping unit identifier of each identified item in the image based on the pixel-to-physical dimension ratio and the pixel dimension of the region of interest for each identified item.

Abstract: The disclosure includes a system and method for distinguishing between stock keeping units of similar appearance that vary in size. An image recognition application receives an image including a shelving unit stocking a plurality of items, identifies each item in the image, generates a region of interest for each identified item in the image, identifies a physical dimension of a portion of region depicted in the image, determines a dimension of the region of interest for each identified item and the portion of region in pixels, determines a pixel-to-physical dimension ratio using the dimension in pixels of the portion of region and the physical dimension of the portion of region depicted in the image, and determines a stock keeping unit identifier of each identified item in the image based on the pixel-to-physical dimension ratio and the dimension of the region of interest for each identified item.