A9.com, Inc.

Ming Du

Arnab Sanat Kumar Dhua

Colin Jon Taylor

Aishwarya Natesh

Douglas Ryan Gray

Michael Patrick Cutter

Gautam Bhargava

Mehmet Nejat Tek

R Manmatha

Ketan Ramesh Deshpande

Wei-Hong Chuang

Dheeraj Soti

Maya Kabkab

Various embodiments provide methods and systems for providing a recommended volume level in presentation of media content. In some embodiments, volume adjustment events made by a user and/or similar users while watching media content can be detected and automatically recorded. The media content may include a plurality of segments. A normalized volume level for at least one segment of the media content can be determined by aggregating the recorded volume adjustment events corresponding to the at least one segment of the media content. When the media content is played back on a user device, at least some embodiments cause the at least one segment of the media content to be played back at a recommended volume level determined based at least in part upon one of the normalized audio level of the corresponding segment, the audio system of the user device, or historical data and personal profile of the user.

Crowdsourced audio normalization for presenting media content

Images may be analyzed to determine a visually cohesive color palette, for example by comparing a subset of the colors most frequently appearing in the image to a plurality of color schemes (e.g., complementary, analogous, etc.), and potentially modifying one or more of the subset of colors to more accurately fit the selected color scheme. Various regions of the image are selected and portions of the regions having one or more colors of the color palette are extracted and classified to generate and compare feature vectors of the patches to previously-determined feature vectors of items to identify visually similar items. The visually similar items are selected for presentation in various ways, such as by choosing an outfit of visually-similar apparel items based on the locations of the corresponding colors in the image, etc.

Item recommendation based on feature match

Approaches attempt to determine information that can help to produce more useful recommendations to be displayed in a situation where no, or little, information is available that indicates a relationship between content provided through an electronic marketplace or other content provider. For example, data available that relates to an item in a product catalog, for example color data, can be analyzed and aggregated in order to attempt to locate other items that are related and relevant to the item, at least as it relates to color and categorization of the content. Such approaches can include, for example, analyzing images, articles, and other sources of electronic content to attempt to locate items that might be relevant to the item of interest. In a clothing example, this can include accessory items that might be worn with an apparel item of interest, match the apparel item of interest, be frequently utilized or exhibited with the apparel item of interest, include a matching and/or complementary color to the apparel item of interest, etc.

Content recommendation based on color match

Training images can be synthesized in order to obtain enough data to train a convolutional neural network to recognize various classes of a type of item. Images can be synthesized by blending images of items labeled using those classes into selected background images. Catalog images can represent items against a solid background, which can be identified using connected components or other such approaches. Removing the background using such approaches can result in edge artifacts proximate the item region. To improve the results, one or more operations are performed, such as a morphological erosion operation followed by an opening operation. The isolated item portion then can be blended into a randomly selected background region in order to generate a synthesized training image. The training images can be used with real world images to train the neural network.

Synthesizing training data

A set of training images is obtained by analyzing text associated with various images to identify images likely demonstrating a visual attribute. Localization can be used to extract patches corresponding to these attributes, which can then have features or feature vectors determined to train, for example, a convolutional neural network. A query image can be received and analyzed using the trained network to determine a set of items whose images demonstrate visual similarity to the query image at least with respect to the attribute of interest. The similarity can be output from the network or determined using distances in attribute space. Content for at least a determined number of highest ranked, or most similar, items can then be provided in response to the query image.

Attribute similarity-based search

The accuracy of an image matching process can be improved by determining relevant swatch regions of the images, where those regions contain representative patterns of the items of interest represented in those images. Various processes examine a set of visual cues to determine at least one candidate object region, and then collate these regions to determine one or more representative swatch images. For apparel items, this can include locating regions such as an upper body region, torso region, clothing region, foreground region, and the like. Processes such as regression analysis or probability mapping can be used on the collated region data (along with confidence and/or probability values) to determine the appropriate swatch regions.

Growing community of inventors

Redwood City, CA, United States of America

Ming Du