Amazon Technologies, Inc.

Other

Sumit Negi

Arijit Biswas

Om Dadaji Deshmukh

Ankit Gandhi

Pooja Ashok Kumar

Yashal Shakti Kanungo

Brittney C Gannon

Shilpa Pundi Ananth

Lauren K Johnson

Sai Sree Harsha

Kuldeep Yadav

Aruna Rajan

Meghana S Shivanand Rajamane

Sanket Sanjay Barhate

Shiv Surya

Sahil Loomba

Amrith Rajagopal Setlur

Sonal S Patil

Devices, systems, and methods are provided for generating and selecting video clips for inclusion in video sequences based on still frame images. A method may include encoding first embeddings for a first video including first images of an item at a first scene, the first embeddings indicative of features of the first scene; encoding second embeddings for a second video including second images of the item at a second scene, the second embeddings indicative of features of the second scene; encoding third embeddings for the first video, the third embeddings indicative of features of a first type of camera shot used for the first images; encoding fourth embeddings for the second video, the fourth embeddings indicative of features of a second type of camera shot used for the second images; and generating, based on the first, second, third, and fourth embeddings, a video sequence for the item.

Enhanced generation and selection of video clips from still frame images

Technologies are provided for automated generation of directed content campaigns. The generated campaign can be optimized for performance. In some embodiments, a group of variations of attributes that define a directed content campaign can be generated and allocated traffic weights for respective impressions of the directed content campaign in a media outlet channel. The traffic weights can then be iteratively updated until a termination criterion is satisfied. At each iteration, the traffic weight can be updated by applying a machine-learning model to current performance metric values of respective impressions corresponding to the traffic weights. After termination of the updates to the traffic weights, a particular set of variations having traffic weights exceeding a threshold can be selected as directed content campaign having satisfactory performance. Those variations can be supplied to a requestor device for subsequent utilization.

Automated generation of directed content campaigns

Techniques are generally described for context aware text-to-image synthesis. First text data comprising a description of an object may be received. A recurrent neural network may determine a first semantic representation data representing the first text data. A generator trained using a first generative adversarial network (GAN) may determine first image data representing the object using the first semantic representation. An encoder of a second GAN may generate a first feature representation of the first image data. The first feature representation may be combined with a projection of the first semantic representation data. A decoder of the second GAN may generate second image data representing the first text data.

Context aware text-to-image synthesis

The disclosed embodiments illustrate methods of generation of a table of content by processing multimedia content. The method includes identifying a set of key-phrases from the multimedia content based on one or more external data sources. The method further includes determining one or more segments of the multimedia content, based on the identified set of key-phrases, wherein a segment of the determined one or more segments comprises a subset of key-phrases from the set of key-phrases. The method further includes selecting at least a key-phrase from the subset of key-phrases of each of the corresponding one or more segments. The method further includes generating the table of content based on the selected key-phrase from each of the one or more segments, wherein the selected key-phrase from each of the one or more segments in the generated table of content is utilized to navigate through the multimedia content.

Method and system for generation of a table of content by processing multimedia content

Features are extracted from visual and audio modalities of a video to infer the location of figures/tables/equations/graphs/flow-charts determined as video anchor points which are highlighted on the video timeline to enable quick navigation and provide a quick summary of the video. A voice-based mechanism navigates to a point-of-interest in the video. In case of bandwidth-constrained settings, videos are often played at a very low resolution (quality), and often users need to increase video resolution manually to understand content presented in the figures. Using the automatic identification of these aforementioned anchored points, the resolution can be changed dynamically during streaming a video, which will provide a better viewing experience.

System and methods to create multi-faceted index instructional videos

The disclosed embodiments illustrate method and system of processing multimedia content to generate a text transcript. The method includes segmenting each of a set of text frames to determine spatial regions. The method further includes extracting one or more keywords from each of the determined spatial regions. The method further includes determining the first set of keywords from the extracted one or more keywords based on filtering of one or more off-topic keywords from the extracted one or more keywords. The method further includes extracting a second set of keywords based on the determined first set of keywords. The method further includes generating a graph between each of a first set of keywords and one or more of a second set of keywords. The method further includes dynamically generating the text transcript of audio content in the multimedia content based on the generated graph.

Method and system for processing multimedia content to dynamically generate text transcript

Growing community of inventors

Bengaluru, India

Sumit Negi