公开(公告)号：US20160307029A1

公开(公告)日：2016-10-20

申请号：US14686798

申请日：2015-04-15

Applicant: Cisco Technology, Inc.

Inventor： Aviva VAKNIN ,  Gal Moshitch

IPC: G06K9/00 ,  G06K9/62

CPC classification number: G06K9/00288 ,  G06K9/00234 ,  G06K9/00261 ,  G06K9/00281 ,  G06K9/00711 ,  G06K9/00926 ,  G06K9/6215

Abstract: In one embodiment, a method for detecting faces in video image frames is implemented on a computing device including: comparing current image frames to previously processed image frames to determine similarity, if a current image frame and a previously processed image frame are dissimilar, comparing a location within the current image frame for at least one detected facial image to a location within an associated image frame for at least one most recently stored facial image stored in a most recently used (MRU) cache, if the compared locations are dissimilar, comparing the at least one detected facial image to the at least one most recently stored facial image stored in the MRU cache to determine similarity, and storing the at least one detected facial image in the MRU cache if the at least one detected facial image and the at least one most recently stored facial image are not dissimilar.

Abstract translation: 在一个实施例中，在计算设备上实现用于检测视频图像帧中的面部的方法，包括：将当前图像帧与先前处理的图像帧进行比较，以确定相似度，如果当前图像帧和先前处理的图像帧不相似， 如果所比较的位置不相似，则将用于至少一个检测到的面部图像的当前图像帧内的位置存储到存储在最近使用（MRU）高速缓存中的至少一个最近存储的面部图像的相关图像帧内的位置， 至少一个检测到的面部图像到存储在MRU缓存中的至少一个最近存储的面部图像以确定相似性，并且如果至少一个检测到的面部图像和至少一个检测到的面部图像，将该至少一个检测到的面部图像存储在MRU缓存中 一个最近存储的面部图像是不相似的。

公开(公告)号：US20230229734A1

公开(公告)日：2023-07-20

申请号：US17580061

申请日：2022-01-20

Applicant: Cisco Technology, Inc.

Inventor： Chiara Troiani ,  Aviva VAKNIN ,  Frank MICHAUD

IPC: G06K9/62 ,  G06N20/00

CPC classification number: G06K9/6256 ,  G06N20/00 ,  G06K9/627 ,  G06K9/6253

Abstract: In one embodiment, a device receives a request for a machine learning model to make an inference about input data included in the request. The device retrieves metadata regarding training data used to train the machine learning model from a ledger associated with the machine learning model. The device assesses bias of the machine learning model by comparing the input data in the request to the metadata from the ledger. The device provides an indication of the bias of the machine learning model for display.

公开(公告)号：US20160073170A1

公开(公告)日：2016-03-10

申请号：US14716929

申请日：2015-05-20

Applicant: Cisco Technology, Inc.

Inventor： Pete RAI ,  Eynav COHEN ,  Ronnie DAN ,  Ahuva LEVKOWITZ ,  Tal MAOZ ,  Aviva VAKNIN ,  Reuven WACHTFOGEL

IPC: H04N21/482 ,  H04N21/438 ,  H04N21/431 ,  G06K9/00 ,  H04N21/44 ,  H04N21/222 ,  H04N21/81 ,  H04N21/237 ,  H04N21/43

CPC classification number: H04N21/4312 ,  G06K9/00228 ,  H04N21/2221 ,  H04N21/23418 ,  H04N21/237 ,  H04N21/26603 ,  H04N21/4126 ,  H04N21/42224 ,  H04N21/431 ,  H04N21/4314 ,  H04N21/4316 ,  H04N21/4383 ,  H04N21/44008 ,  H04N21/472 ,  H04N21/482 ,  H04N21/8153

Abstract: In one embodiment, a method for selecting video channels is implemented on a computing device and includes: presenting at least one set of detected facial images, detecting user selection of a selected set of detected facial images, where each of the at least one set is associated with one of the video channels; and sending a video channel switching command to a video channel playing device, where the video channel switching command indicates a switch to the video channel associated with the selected set of detected facial images.

Abstract translation: 在一个实施例中，在计算设备上实现用于选择视频频道的方法，并且包括：呈现至少一组检测到的面部图像，检测所选择的一组检测到的面部图像的用户选择，其中至少一个组中的每一个 与其中一个视频频道相关联; 并向视频通道播放设备发送视频频道切换命令，其中视频频道切换命令指示切换到与所选择的所检测的面部图像组相关联的视频频道。