An interaction module includes: a first text-image interaction module configured to generate a vector representation of a first text-image pair based on an encoded representation of a reference image and an encoded representation of a text modifier, the reference image and the text modifier received from a computing device. A second text-image interaction module is configured to generate a vector representation of a second text-image pair based on the encoded representation of the text modifier and an encoded representation of a candidate target image. A compatibility module is configured to compute, based on the vector representation of the first text-image pair and the vector representation of the second text-image pair, a compatibility score for a triplet including the reference image, the text modifier, and the candidate target image. A ranking module is configured to rank a set of candidate target images including the candidate target image by compatibility scores.

An interaction module includes: a first text-image interaction module configured to generate a vector representation of a first text-image pair based on an encoded representation of a reference image and an encoded representation of a text modifier, the reference image and the text modifier received from a computing device. A second text-image interaction module is configured to generate a vector representation of a second text-image pair based on the encoded representation of the text modifier and an encoded representation of a candidate target image. A compatibility module is configured to compute, based on the vector representation of the first text-image pair and the vector representation of the second text-image pair, a compatibility score for a triplet including the reference image, the text modifier, and the candidate target image. A ranking module is configured to rank a set of candidate target images including the candidate target image by compatibility scores.

Technologies are described for reconstructing physical objects which are preserved or represented in pictorial records. The reconstructed models can be three-dimensional (3D) point clouds and can be compared to existing physical models and/or other reconstructed models based on physical geometry. The 3D point cloud models can be encoded into one or more latent space feature vector representations which can allow both local and global geometric properties of the object to be described. The one or more feature vector representations of the object can be used individually or in combination with other descriptors for retrieval and classification tasks. Neural networks can be used in the encoding of the one or more feature vector representations.

Technologies are described for reconstructing physical objects which are preserved or represented in pictorial records. The reconstructed models can be three-dimensional (3D) point clouds and can be compared to existing physical models and/or other reconstructed models based on physical geometry. The 3D point cloud models can be encoded into one or more latent space feature vector representations which can allow both local and global geometric properties of the object to be described. The one or more feature vector representations of the object can be used individually or in combination with other descriptors for retrieval and classification tasks. Neural networks can be used in the encoding of the one or more feature vector representations.

A query image is received, along with a query to initiate a search process to find other images based on the query image. The query includes a preference value associated with an attribute, the preference value indicative of a level of emphasis to be placed on the attribute during the search. A full query vector, which is within a first dimensional space and representative of the query image, is generated. The full query vector is projected to a reduced dimensional space having a dimensionality lower than the first dimensional space, to generate a query vector. An attribute direction corresponding to the attribute is identified. A plurality of candidate vectors of the reduced dimensional space is searched, based on the attribute direction, the query vector, and the preference value, to identify a target vector of the plurality of candidate vectors. A target image, representative of the target vector, is displayed.

A query image is received, along with a query to initiate a search process to find other images based on the query image. The query includes a preference value associated with an attribute, the preference value indicative of a level of emphasis to be placed on the attribute during the search. A full query vector, which is within a first dimensional space and representative of the query image, is generated. The full query vector is projected to a reduced dimensional space having a dimensionality lower than the first dimensional space, to generate a query vector. An attribute direction corresponding to the attribute is identified. A plurality of candidate vectors of the reduced dimensional space is searched, based on the attribute direction, the query vector, and the preference value, to identify a target vector of the plurality of candidate vectors. A target image, representative of the target vector, is displayed.

A system and method for image-based personalized food item search, design, and culinary fulfillment. The system is a cloud-based network comprising a food image engine, a prediction engine, a food item design engine, and portals for restaurants and patrons to enter their information. The system may receive as an input a food item image, perform image recognition on the food item image to identify a target food item, use the identified target food item to predict an ingredient list for the target food item, and generate personalized target food item recommendations for patrons based on a multitude of variables associated with the business enterprises, patrons historic culinary transactions, dietary needs and preferences both explicit and inferred. The system may be accessed through web browsers or purpose-built computer and mobile phone applications.

A system and method for image-based personalized food item search, design, and culinary fulfillment. The system is a cloud-based network comprising a food image engine, a prediction engine, a food item design engine, and portals for restaurants and patrons to enter their information. The system may receive as an input a food item image, perform image recognition on the food item image to identify a target food item, use the identified target food item to predict an ingredient list for the target food item, and generate personalized target food item recommendations for patrons based on a multitude of variables associated with the business enterprises, patrons historic culinary transactions, dietary needs and preferences both explicit and inferred. The system may be accessed through web browsers or purpose-built computer and mobile phone applications.

An image search system including an interface and a compute engine set is provided. The interface is configured to obtain a to-be-searched image. The compute engine set includes a first compute engine and a second compute engine. The first compute engine is configured to compute similarities between the to-be-searched image and a plurality of images included in a gallery; and the second compute engine is configured to determine a search result based on the similarities between the searched image and the plurality of images included in the gallery, where the search result includes a target image similar to the to-be-searched image.

An image search system including an interface and a compute engine set is provided. The interface is configured to obtain a to-be-searched image. The compute engine set includes a first compute engine and a second compute engine. The first compute engine is configured to compute similarities between the to-be-searched image and a plurality of images included in a gallery; and the second compute engine is configured to determine a search result based on the similarities between the searched image and the plurality of images included in the gallery, where the search result includes a target image similar to the to-be-searched image.