公开(公告)号：US12229179B1

公开(公告)日：2025-02-18

申请号：US18515105

申请日：2023-11-20

Applicant: Amazon Technologies, Inc.

Inventor： Matthaeus Kleindessner ,  Christopher Michael Russell ,  Kailash Budhathoki ,  Ali Caner Turkmen ,  Siqi Deng ,  Varad Gunjal ,  Ashwin Swaminathan ,  Raghavan Manmatha ,  Hao Yang

IPC: G06F16/40 ,  G06F16/432 ,  G06F16/53

Abstract: The present disclosure generally relates to systems and methods for searching media content. In some implementation examples, a search system receives an input query, generates a query embedding of the input query, and generates a bias mitigation transformation associated with a sensitive attribute. Based on the query embedding and the bias mitigation transformation, the search system generates a transformed query embedding that suppresses at least a portion of the query embedding related to the sensitive attribute. Using the transformed query embedding, the search system executes a similarity search in a media embedding model to identify one or more media embeddings that are similar to the transformed query embedding and transmits the one or more media embeddings.

公开(公告)号：US20240152510A1

公开(公告)日：2024-05-09

申请号：US18544229

申请日：2023-12-18

Applicant: Amazon Technologies, Inc.

Inventor： Srikar Appalaraju ,  Raghavan Manmatha ,  Bhargava Urala Kota

IPC: G06F16/245 ,  G06N3/08 ,  G06V30/418

CPC classification number: G06F16/245 ,  G06N3/08 ,  G06V30/418 ,  G06V30/18

Abstract: Representations of sets of descriptors of reference objects are stored in a repository, with individual descriptors including information about entities identified in the reference objects. In response to a request to extract content from a particular data object, a reference object which satisfies a similarity criterion with respect to the particular data object is identified from the repository using the descriptors. A structural comparison of the particular data object and the reference object is performed to determine an entity related to another entity identified in the particular data object.

公开(公告)号：US11893012B1

公开(公告)日：2024-02-06

申请号：US17334188

申请日：2021-05-28

Applicant: Amazon Technologies, Inc.

Inventor： Srikar Appalaraju ,  Raghavan Manmatha ,  Bhargava Urala Kota

IPC: G06F16/245 ,  G06V30/418 ,  G06N3/08 ,  G06V30/18

CPC classification number: G06F16/245 ,  G06N3/08 ,  G06V30/418 ,  G06V30/18

Abstract: Representations of sets of descriptors of reference objects are stored in a repository, with individual descriptors including information about entities identified in the reference objects. In response to a request to extract content from a particular data object, a reference object which satisfies a similarity criterion with respect to the particular data object is identified from the repository using the descriptors. A structural comparison of the particular data object and the reference object is performed to determine an entity related to another entity identified in the particular data object.

公开(公告)号：US11308354B1

公开(公告)日：2022-04-19

申请号：US16834997

申请日：2020-03-30

Applicant: Amazon Technologies, Inc.

Inventor： Ron Litman ,  Oron Anschel ,  Shahar Tsiper ,  Roee Litman ,  Shai Mazor ,  Jonathan Wu ,  Raghavan Manmatha

IPC: G06K9/62 ,  G06K9/42

Abstract: Techniques for recognizing text in an image are described. An exemplary method may include receiving a request to recognize text in an image; extracting features from the image and generating a visual feature sequence from the extracted features; performing selective contextual refinement at least one selective contextual refinement block of a stack of selective contextual refinement blocks to generate a text prediction by: generating a contextual feature map and combining the contextual feature map with the visual feature sequence into a visual feature space, and applying a selective decoder that utilizes a two-step attention on the visual feature space to generate a text prediction, wherein the two-step attention includes performing a 1-D self-attention computation to generate attentional features and decoding the attentional features to generate the text prediction; and outputting the generated text prediction.

公开(公告)号：US10659787B1

公开(公告)日：2020-05-19

申请号：US16137398

申请日：2018-09-20

Applicant: Amazon Technologies, Inc.

Inventor： Ilya Vladimirovich Brailovskiy ,  Raghavan Manmatha

IPC: H04N19/136 ,  H04N19/124 ,  H04N19/13 ,  H04N19/625 ,  H04N19/179 ,  H04N19/51 ,  H04N19/172

Abstract: Techniques are generally described for enhanced compression of video data. In various examples, the techniques may include receiving first video data representing a scene in an environment. The techniques may further include generating illumination map data representing illumination of the scene in the first video data. The techniques may further comprise generating reflectance map data representing a reflectance of at least one object in the first video data. In some examples, the techniques may include sending, to a second computing device, the illumination map data and the reflectance map data. The techniques may further include receiving second video data representing the scene. The techniques may include determining a first illumination difference between the second video data and the first video data. The techniques may comprise sending, to the second computing device, the first illumination difference.