Amazon Technologies, Inc.

Loris Bazzani

Michael Donoser

Eleonora Vig

Nikhil Garg

Vernon Germano

Kripa Kanchana Sivakumar

Felix Hieber

Maksim Lapin

Bojan Pepik

Matthew Norman

Emily Evon McAninly

Prateek Ramesh Chandra Shah

Eric Orme

Benjamin Chung Yen Cheung

Yanbei Chen

Erhan Gundogdu

Tobias Domhan

Yuxin Hou

Antonio D'Innocente

Amaia Salvador Aguilera

Filip Saina

Angel Noe Martinez Gonzalez

Systems and techniques are generally described for attribute-based content selection and search. In some examples, a graphical user interface (GUI) may display an image of a first product comprising a plurality of visual attributes. In some further examples, the GUI may display at least a first control button with data identifying a first visual attribute of the plurality of visual attributes. In some cases, a first selection of the first control button may be received. In some examples, a first plurality of products may be determined based at least in part on the first selection of the first control button. The first plurality of products may be determined based on a visual similarity to the first product, and a visual dissimilarity to the first product with respect to the first visual attribute. In some examples, the first plurality of products may be displayed on the GUI.

Attribute-based content selection and search

Devices and techniques are generally described for determining localized visual similarity. In some examples, a selection of a first location of interest on a first image data depicting at least one article of clothing may be received. In some examples, a first machine learning model may generate a feature map representing the first image data. In some examples, a reduced feature map may be generated based at least in part on a mapping of the first location of interest to the feature map. In some examples, a second image depicting at least a second article of clothing may be determined based at least in part on the reduced feature map.

Localized visual similarity

Techniques are generally described for interactive image retrieval using visual semantic matching. Image data and text data are encoded into a single shared visual semantic embedding space. A prediction model is trained using reference inputs, target outputs, and modification text describing changes to the reference inputs to obtain the target outputs. The prediction model can be used to perform image-to-text, text-to-image, and interactive retrieval.

Interactive retrieval using visual semantic matching

Systems and techniques are generally described for generating visually blended recommendation grids. In some examples, a selection of a first item and a second item displayed on a display may be received. In various examples, the first item may be displayed in a first element of a grid and the second item may be displayed in a second element of the grid. In some examples, a third element of the grid that is disposed between the first element and the second element along an axis of the grid may be determined. In various examples, a third item may be determined for display in the third element of the grid based at least in part on a blended representation of an embedding of the first item and an embedding of the second item. The third item may be displayed in the third element of the grid.

Visual blending of content

Techniques are generally described for automatic scoring of alt-text for image data. In various examples, first image data and first text data describing the first image data may be received. A feature representation of the first image data may be determined using an encoder machine learning model. A hidden state representation may be determined using a decoder machine learning model based on the feature representation and a first word of the first text data. In some examples, a first score may be determined using the hidden state representation. The first score may include an indication of a descriptive capability of the first text data with respect to the first image data.

Machine learning system to score alt-text in image data

Techniques are described for a content rating system that allows for automatic assignment of maturity ratings for media content.

Automated video ratings

Growing community of inventors

Berlin, Germany

Loris Bazzani