公开(公告)号：US12008335B2

公开(公告)日：2024-06-11

申请号：US17018041

申请日：2020-09-11

Applicant: Yuichi Takamiya

Inventor： Yuichi Takamiya

IPC: G06F40/263 ,  G06F40/40 ,  G06F40/49 ,  G06F40/58 ,  G06V10/94 ,  G06V30/246 ,  H04L51/04 ,  H04L67/52 ,  H04L67/565 ,  G06F3/16 ,  G06V30/10 ,  G06V30/224 ,  G10L15/22 ,  G10L15/26

CPC classification number: G06F40/58 ,  G06F40/49 ,  G06V10/95 ,  G06V30/246 ,  G06F3/167 ,  G06V30/10 ,  G06V30/224 ,  G10L15/22 ,  G10L15/26

Abstract: An information processing system is communicable with a translation server through a network, and includes a receiver, circuitry, and a transmitter. The receiver receives content data indicating contents expressed in a first language and destination information indicating a destination to which the content data is to be transmitted. The circuitry determines, based on the destination information received by the receiver, a second language as a target language into which the contents expressed in the first language is to be translated. The transmitter transmits, to the destination indicated by the destination information, translated content data indicating contents that is translated by the translation server from the first language to the second language.

公开(公告)号：US20240185587A1

公开(公告)日：2024-06-06

申请号：US18556636

申请日：2021-08-16

Applicant: Baidu.com Times Technology (Beijing) Co., Ltd.

Inventor： Haofeng KOU ,  Xing LI ,  Huimeng ZHENG ,  Lei WANG ,  Zhen CHEN

IPC: G06V10/776 ,  G06V10/82 ,  G06V10/94

CPC classification number: G06V10/776 ,  G06V10/82 ,  G06V10/955

Abstract: Modem deep neural network (DNN) models have many layers with a single layer potentially involving large matrix multiplications. Such heavy calculation brings challenges to deploy such DNN models on a single edge device, which has relatively limited computation resources. Therefore, multiple and even heterogeneous edge devices may be required for applications with stringent latency requirements. Disclosed in the present patent documents are embodiments of a model scheduling framework that schedules multiple models on a heterogeneous platform. Two different approaches, model first scheduling (MFS) and hardware first scheduling (HFS), are presented to allocate a group of models for a service into corresponding heterogeneous edge devices, including CPU, VPU and GPU. Experimental results prove the effectiveness of the MFS and HFS methods for improving the inference speed of single and multiple AI-based services.

公开(公告)号：US12002291B2

公开(公告)日：2024-06-04

申请号：US17453634

申请日：2021-11-04

Applicant: Tata Consultancy Services Limited

Inventor： Sushovan Chanda ,  Gauri Deshpande ,  Sachin Patel

IPC: G06K9/00 ,  G06F18/214 ,  G06N3/08 ,  G06T7/73 ,  G06V10/94 ,  G06V20/40 ,  G06V40/16 ,  G06V40/20

CPC classification number: G06V40/20 ,  G06F18/214 ,  G06N3/08 ,  G06T7/73 ,  G06V10/95 ,  G06V20/46 ,  G06V40/171 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30201

Abstract: State of art techniques attempt in extracting insights from eye features, specifically pupil with focus on behavioral analysis than on confidence level detection. Embodiments of the present disclosure provide a method and system for confidence level detection from eye features using ML based approach. The method enables generating overall confidence level label based on the subject's performance during an interaction, wherein the interaction that is analyzed is captured as a video sequence focusing on face of the subject. For each frame facial features comprising an Eye-Aspect ratio, a mouth movement, Horizontal displacements, Vertical displacements, Horizontal Squeezes and Vertical Peaks, are computed, wherein HDs, VDs, HSs and VPs are features that are derived from points on eyebrow with reference to nose tip of the detected face. This is repeated for all frames in the window. A Bi-LSTM model is trained using the facial features to derive confidence level of the subject.

公开(公告)号：US12001513B2

公开(公告)日：2024-06-04

申请号：US17522226

申请日：2021-11-09

Applicant: NEC Laboratories America, Inc.

Inventor： Giuseppe Coviello ,  Yi Yang ,  Srimat Chakradhar

IPC: G06V10/00 ,  G06F9/50 ,  G06F18/21 ,  G06N3/08 ,  G06V10/94 ,  G06V20/40

CPC classification number: G06F18/217 ,  G06F9/5027 ,  G06N3/08 ,  G06V10/94 ,  G06V20/46

Abstract: A method for implementing a self-optimized video analytics pipeline is presented. The method includes decoding video files into a sequence of frames, extracting features of objects from one or more frames of the sequence of frames of the video files, employing an adaptive resource allocation component based on reinforcement learning (RL) to dynamically balance resource usage of different microservices included in the video analytics pipeline, employing an adaptive microservice parameter tuning component to balance accuracy and performance of a microservice of the different microservices, applying a graph-based filter to minimize redundant computations across the one or more frames of the sequence of frames, and applying a deep-learning-based filter to remove unnecessary computations resulting from mismatches between the different microservices in the video analytics pipeline.

公开(公告)号：US20240161334A1

公开(公告)日：2024-05-16

申请号：US17983841

申请日：2022-11-09

Applicant: Mohamed bin Zayed University of Artificial Intelligence

Inventor： Omkar THAWAKAR ,  Sanath NARAYAN ,  Hisham CHOLAKKAL ,  Rao Muhammad ANWER ,  Muhammad HARIS ,  Salman KHAN ,  Fahad KHAN

IPC: G06T7/73 ,  G06V10/26 ,  G06V10/77 ,  G06V10/774 ,  G06V10/94 ,  G06V20/58

CPC classification number: G06T7/73 ,  G06V10/26 ,  G06V10/7715 ,  G06V10/774 ,  G06V10/95 ,  G06V20/582 ,  G06T2207/30196 ,  G06T2207/30261

Abstract: A system, method, computer readable storage medium for a computer vision system includes at least one video camera, and video processor circuitry. The method includes inputting a stream of video data and generating a sequence of image frames, segmenting and tracking, by the video analysis apparatus, object instances in the stream of video data, including receiving the sequence of image frames, analyzing the sequence of image frames using a video instance segmentation transformer to obtain a video instance mask sequence from the sequence of image frames, the transformer having a backbone network, a transformer encoder-decoder, and an instance matching and segmentation block, The encoder contains a multi-scale spatio-temporal split attention module to capture spatio-temporal feature relationships at multiple scales across multiple frames. The decoder contains a temporal attention block for enhancing a temporal consistency of transformer queries. The method includes displaying the video instance mask sequence.

公开(公告)号：US11983946B2

公开(公告)日：2024-05-14

申请号：US17517434

申请日：2021-11-02

Applicant: Adobe Inc.

Inventor： Shripad Deshmukh ,  Milan Aggarwal ,  Mausoom Sarkar ,  Hiresh Gupta

IPC: G06V30/414 ,  G06F18/21 ,  G06N3/08 ,  G06V10/94 ,  G06V30/18 ,  G06V30/262

CPC classification number: G06V30/414 ,  G06F18/21 ,  G06N3/08 ,  G06V10/95 ,  G06V30/18 ,  G06V30/274

Abstract: In implementations of refining element associations for form structure extraction, a computing device implements a structure system to receive estimate data describing estimated associations of elements included in a form and a digital image depicting the form. An image patch is extracted from the digital image, and the image patch depicts a pair of elements of the elements included in the form. The structure system encodes an indication of whether the pair of elements have an association of the estimated associations. An indication is generated that the pair of elements have a particular association based at least partially on the encoded indication, bounding boxes of the pair of elements, and text depicted in the image patch.

公开(公告)号：US20240144001A1

公开(公告)日：2024-05-02

申请号：US18312692

申请日：2023-05-05

Applicant: NVIDIA Corporation

Inventor： Tero Tapani Karras ,  Timo Oskari Aila ,  Samuli Matias Laine

IPC: G06N3/08 ,  G06F18/21 ,  G06F18/2413 ,  G06N3/04 ,  G06N3/045 ,  G06N3/047 ,  G06V10/44 ,  G06V10/82 ,  G06V10/94 ,  G06V30/19

CPC classification number: G06N3/08 ,  G06F18/217 ,  G06F18/24143 ,  G06N3/04 ,  G06N3/045 ,  G06N3/047 ,  G06V10/454 ,  G06V10/82 ,  G06V10/955 ,  G06V30/1916 ,  G06V30/19173 ,  G10L25/30

Abstract: A method and system are disclosed for training a model that implements a machine-learning algorithm. The technique utilizes latent descriptor vectors to change a multiple-valued output problem into a single-valued output problem and includes the steps of receiving a set of training data, processing, by a model, the set of training data to generate a set of output vectors, and adjusting a set of model parameters and component values for at least one latent descriptor vector in the plurality of latent descriptor vectors based on the set of output vectors. The set of training data includes a plurality of input vectors and a plurality of desired output vectors, and each input vector in the plurality of input vectors is associated with a particular latent descriptor vector in a plurality of latent descriptor vectors. Each latent descriptor vector comprises a plurality of scalar values that are initialized prior to training the model.

公开(公告)号：US11966454B2

公开(公告)日：2024-04-23

申请号：US17513493

申请日：2021-10-28

Applicant: Shanghai United Imaging Intelligence Co., Ltd.

Inventor： Zhang Chen ,  Xiao Chen ,  Yikang Liu ,  Terrence Chen ,  Shanhui Sun

IPC: G06K9/00 ,  G01R33/56 ,  G06F18/214 ,  G06N3/08 ,  G06T3/40 ,  G06T5/70 ,  G06T7/00 ,  G06T11/00 ,  G06V10/94 ,  G16H30/20

CPC classification number: G06F18/2148 ,  G01R33/5608 ,  G06N3/08 ,  G06T3/40 ,  G06T5/70 ,  G06T7/0014 ,  G06T11/008 ,  G06V10/95 ,  G16H30/20 ,  G06T2207/10088 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30004

Abstract: A neural network system implements a model for generating an output image based on a received input image. The model is learned through a training process during which parameters associated with the model are adjusted so as to maximize a difference between a first image predicted using first parameter values of the model and a second image predicted using second parameter values of the model, and to minimize a difference between the second image and a ground truth image. During a first iteration of the training process the first image is predicted and during a second iteration the second image is predicted. The first parameter values are obtained during the first iteration by minimizing a difference between the first image and the ground truth image, and the second parameter values are obtained during the second iteration by maximizing the difference between the first image and the second image.

公开(公告)号：US20240127584A1

公开(公告)日：2024-04-18

申请号：US18526787

申请日：2023-12-01

Applicant: Torc Robotics, Inc.

Inventor： Emmanuel Luc Julien Onzon ,  Felix Heide ,  Maximilian Rufus Bömer ,  Fahim Mannan

IPC: G06V10/776 ,  G06T5/40 ,  G06T5/50 ,  G06T7/11 ,  G06V10/77 ,  G06V10/80 ,  G06V10/94 ,  G06V20/00

CPC classification number: G06V10/776 ,  G06T5/40 ,  G06T5/50 ,  G06T7/11 ,  G06V10/7715 ,  G06V10/806 ,  G06V10/955 ,  G06V20/38 ,  G06T2207/10144 ,  G06T2207/20161

Abstract: A computer-vision pipeline is organized as a closed loop of a sensor-processing phase, an image-processing phase, and an object-detection phase, each comprising a respective phase processor coupled to a master processor. The sensor-processing phase creates multiple exposure images, and derives multi-exposure multi-scale zonal illumination-distributions, to be processed independently in the image-processing phase. In a first implementation of the object-detection phase, extracted exposure-specific features are pooled prior to overall object detection. In a second implementation, exposure-specific objects, detected from the exposure-specific features, are fused to produce the sought objects of a scene under consideration. The two implementations enable detecting fine details of a scene under diverse illumination conditions. The master processor performs loss-function computations to derive updated training parameters of the processing phases. Several experiments applying a core method of operating the computer-vision pipelines, and variations thereof, ascertain performance gain under challenging illumination conditions.

公开(公告)号：US20240125603A1

公开(公告)日：2024-04-18

申请号：US18253700

申请日：2021-11-16

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Ye Leng

IPC: G01C21/30 ,  G06V10/10 ,  G06V10/94 ,  G06V20/56 ,  H04N5/265 ,  H04N7/18 ,  H04N23/661 ,  H04N23/80

CPC classification number: G01C21/30 ,  G06V10/16 ,  G06V10/94 ,  G06V20/588 ,  H04N5/265 ,  H04N7/181 ,  H04N23/661 ,  H04N23/80

Abstract: A method includes: when detecting a road recognition request, a first device sends, by using a DMSDP service, a control command to an entity camera corresponding to a virtual camera HAL, where the control command is for controlling the entity camera to capture a current image (S50); the first device receives, by using the DMSDP service, the current image returned by the entity camera in response to the control command; and the first device recognizes, based on the current image and road information that is obtained by a local navigation application, a road on which the first device is located.