-
公开(公告)号：US12198046B2
公开(公告)日：2025-01-14
申请号：US17073147
申请日：2020-10-16
Applicant: Amazon Technologies, Inc.
Abstract: A visualization tool for machine learning models obtains metadata from a first training node at which a multi-layer machine learning model is being trained. The metadata includes a parameter of an internal layer of the model. The tool determines a plurality of metrics from the metadata, including respective loss function values corresponding to several training iterations of the model. The tool indicates the loss function values and the internal layer parameter values via a graphical interface.
-
公开(公告)号：US11423265B1
公开(公告)日：2022-08-23
申请号：US16917721
申请日：2020-06-30
Applicant: Amazon Technologies, Inc.
Inventor： Hao Chen , Hao Wu , Hao Li , Michael Quang Thai Lam , Xinyu Li , Kaustav Kundu , Meng Wang , Joseph P Tighe , Rahul Bhotika
Abstract: Methods, systems, and computer-readable media for content moderation using object detection and image classification are disclosed. A content moderation system performs object detection on an input image using one or more object detectors. The object detection finds one or more elements in the input image. The content moderation system performs classification based at least in part on the input image using one or more image classifiers. The classification determines one or more values indicative of one or more content types in the input image. The content moderation system determines one or more scores for one or more content labels corresponding to the one or more content types. At least one of the scores represents a finding of one or more of the content types in the input image. The content moderation system generates output indicating the finding of the one or more of the content types.
-
公开(公告)号：US10810491B1
公开(公告)日：2020-10-20
申请号：US15074203
申请日：2016-03-18
Applicant: Amazon Technologies, Inc.
Abstract: A visualization tool for machine learning models obtains metadata from a first training node at which a multi-layer machine learning model is being trained. The metadata includes a parameter of an internal layer of the model. The tool determines a plurality of metrics from the metadata, including respective loss function values corresponding to several training iterations of the model. The tool indicates the loss function values and the internal layer parameter values via a graphical interface.
-
公开(公告)号：US10572760B1
公开(公告)日：2020-02-25
申请号：US15810991
申请日：2017-11-13
Applicant: Amazon Technologies, Inc.
Inventor： Hao Wu , Jonathan Wu , Meng Wang , Wei Xia
Abstract: A method and system for analyzing text in an image is disclosed. A text localization and classification system accesses an annotated image comprising a plurality of text location identifiers for a given item of text. A neural network predicts the location of the given item of text using at least a first location identifier and a second location identifier. Optionally, the first location identifier comprises a first shape and the second location identifier comprises a second shape. A first loss is generated using a first loss function, the first loss corresponding to the predicated location using the first location identifier. A second loss is generated using a second loss function, the second loss corresponding to the predicated location using the second location identifier. The neural network is enhanced with backpropagation using the first loss and the second loss.
-
公开(公告)号：US10467290B1
公开(公告)日：2019-11-05
申请号：US14982816
申请日：2015-12-29
Applicant: Amazon Technologies, Inc.
IPC: G06F16/901 , G06F16/58
Abstract: A knowledge graph (KG) is generated and refined. The generated KG describes direct relationships between different words associated with a particular classification. Initially, a semantic data source, such as a lexical database, is accessed to identify words that are similarly grouped and express a distinct concept. A KG generator creates a sparse KG that provides a direct connection between a seed word and other words. The sparse KG is used by a dense KG generator to create a dense KG. The dense KG generator creates a dense KG that joins each of the different words directly with the seed word for the category. At different points during the creation and refinement of the KG, a user may add or remove one or more connections that affect the creation of the KG.
-
Patent Agency Ranking
公开(公告)号：US10176196B2
公开(公告)日：2019-01-08
申请号：US14747232
申请日：2015-06-23
Applicant: Amazon Technologies, Inc.
Inventor： Yi Li , Tianqiang Liu , Hao Chen , Meng Wang
Abstract: An image processing system for recognizing the scene type of an input image generates an image distance metric from a set of images. The image processing system further extracts image features from the input image and each image in the set of images. Based on the distance metric and the extracted image features, the image processing system computes image feature distances for selecting a subset of images. The image processing system derives a scene type from the scene type of the subset of images. In one embodiment, the image processing system is a cloud computing system.
-
公开(公告)号：US20180349370A9
公开(公告)日：2018-12-06
申请号：US14747232
申请日：2015-06-23
Applicant: Amazon Technologies, Inc.
Inventor： Yi Li , Tianqiang Liu , Hao Chen , Meng Wang
CPC classification number: G06F17/3028 , G06F17/30244 , G06F17/30424 , G06F17/30864 , G06K9/00248 , G06K9/00268 , G06K9/00288 , G06K9/00302 , G06K9/00624 , G06K9/00684 , G06K9/00979 , G06K9/52 , G06K9/6201 , G06K9/6267
Abstract: An image processing system for recognizing the scene type of an input image generates an image distance metric from a set of images. The image processing system further extracts image features from the input image and each image in the set of images. Based on the distance metric and the extracted image features, the image processing system computes image feature distances for selecting a subset of images. The image processing system derives a scene type from the scene type of the subset of images. In one embodiment, the image processing system is a cloud computing system.
-
公开(公告)号：US11875250B1
公开(公告)日：2024-01-16
申请号：US15627330
申请日：2017-06-19
Applicant: Amazon Technologies, Inc.
IPC: G06N3/08 , G06N3/04 , G06F16/583
CPC classification number: G06N3/08 , G06F16/583 , G06N3/04
Abstract: An indication of semantic relationships among classes is obtained. A neural network whose loss function is based at least partly on the semantic relationships is trained. The trained neural network is used to identify one or more classes to which an input observation belongs.
-
公开(公告)号：US11308155B2
公开(公告)日：2022-04-19
申请号：US16363955
申请日：2019-03-25
Applicant: Amazon Technologies, Inc.
Inventor： Yi Li , Yuxin Wu , Yushan Chen , Meng Wang
IPC: G06F16/58 , G06F16/9535 , G06F16/438 , G06V20/30 , G06V40/16
Abstract: Images are intelligently selected to create image narratives. Instead of a user having to manually search and locate images to view, the images to associate with a particular image narrative are programmatically determined. Many different types of image narratives may be created. For example, one image narrative may show images that include both a first user and a second user over some period of time. Another image narrative may show images that relate to an activity that a first user enjoys or an event that included the user (e.g., a graduation). The tags and metadata associated with the images of the user are analyzed to determine the tags that are important to the user. For example, the importance might be determined based on the frequency of the tags within the images. After creation, the user may select one of the image narratives to view the associated images.
-
公开(公告)号：US10962939B1
公开(公告)日：2021-03-30
申请号：US15607183
申请日：2017-05-26
Applicant: Amazon Technologies, Inc.
Inventor： Ranju Das , Wei Xia , Hao Chen , Meng Wang , Venkatesh Bagaria , Jonathan Andrew Hedley
Abstract: The present disclosure provides for customizable content moderation using neural networks with fine-grained and dynamic image classification ontology. A content moderation system of the present disclosure may provide a plurality of image categories in which a subset of of image categories may be designated as restricted categories. The restricted categories may be chosen by a content provider or an end-user. The content moderation system may utilize a neural network to classify image data (e.g., still images, video, etc.) into one or more of the plurality of image categories, and determine that an image is a restricted image upon classifying the image into one of the restricted categories. The restricted image may by flagged, rejected, removed, or otherwise filtered upon being classified as a restricted image.
-
-
-
-
-
-
-
-
-
Search Results
24
records
(took 0.075 seconds)
