公开(公告)号：US20210248467A1

公开(公告)日：2021-08-12

申请号：US17170745

申请日：2021-02-08

Applicant: QUALCOMM Incorporated

Inventor： Mirgahney Husham Awadelkareem MOHAMED ,  Gabriele CESA ,  Taco Sebastiaan COHEN ,  Max WELLING

IPC: G06N3/08 ,  G06K9/62 ,  G06F9/345

Abstract: Certain aspects of the present disclosure provide a method of performing machine learning, comprising: generating a neural network model; and training the neural network model for a task with a first set of input data, wherein: the training uses a total loss function total including an equivariance loss component equivarnace according to total=task+αequivarnace, and α>0.

公开(公告)号：US20240323415A1

公开(公告)日：2024-09-26

申请号：US18188070

申请日：2023-03-22

Applicant: QUALCOMM Incorporated

Inventor： David Wilson ROMERO GUZMAN ,  Gabriele CESA ,  Guillaume Konrad SAUTIERE ,  Yunfan ZHANG ,  Taco Sebastiaan COHEN ,  Auke Joris WIGGERS

IPC: H04N19/42 ,  G06T3/40 ,  H04N19/182

CPC classification number: H04N19/42 ,  G06T3/4046 ,  H04N19/182

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for encoding content using a neural network. An example method generally includes encoding video content into a latent space representation through an encoder implemented by a first machine learning model. A code is generated by upsampling the latent space representation of the video content. A prior is calculated based on a conditional probability of obtaining the upsampled latent space representation conditioned by the latent space representation of the video content. A compressed version of the video content is generated based on a probabilistic model implemented by a second machine learning model, the generated code, and the calculated prior, and the compressed version of the video content is output for transmission.

公开(公告)号：US20240144516A1

公开(公告)日：2024-05-02

申请号：US18485298

申请日：2023-10-11

Applicant: QUALCOMM Incorporated

Inventor： Gabriele CESA ,  Kumar PRATIK ,  Arash BEHBOODI

IPC: G06T7/70 ,  G06T17/00 ,  G06V10/24 ,  G06V20/69

CPC classification number: G06T7/70 ,  G06T17/00 ,  G06V10/24 ,  G06V20/69 ,  G06T2207/10056 ,  G06T2207/20084

Abstract: A computer-implemented method for estimating a pose of an object includes receiving, at a pose estimation model, image data comprising a plurality of two-dimensional (2D) images of an object. Each 2D image of the plurality of 2D images has a different pose. The pose estimation model aligns a first 2D image of the plurality of 2D images with a second 2D image of the plurality of 2D images based on geometric properties related to the first 2D image and the second 2D image. The pose estimation model estimates a pose of the first 2D image and the second 2D image based on the plurality of 2D images and a loss associated with a common line between the first 2D image and the second 2D image.