公开(公告)号：US20220301311A1

公开(公告)日：2022-09-22

申请号：US17696797

申请日：2022-03-16

Applicant: QUALCOMM Incorporated

Inventor： Davide ABATI ,  Amirhossein HABIBIAN ,  Amir GHODRATI

IPC: G06V20/40 ,  G06V10/74 ,  G06V10/82 ,  G06T3/40

Abstract: A processor-implemented method for processing a video includes receiving the video as an input at an artificial neural network (ANN). The video includes a sequence of frames. A set of features of a current frame of the video and a prior frame of the video are extracted. The set of features including a set of support features for a set of pixels of the prior frame to be aligned with a set of reference features of the current frame. A similarity between a support feature for each pixel in the set of pixels of the set of support features of the prior frame and a corresponding reference feature of the current frame is computed. An attention map is generated based on the similarity. An output including a reconstruction of the current frame is generated based on the attention map.

公开(公告)号：US20250166133A1

公开(公告)日：2025-05-22

申请号：US18596543

申请日：2024-03-05

Applicant: QUALCOMM Incorporated

Inventor： Kumara KAHATAPITIYA ,  Davide ABATI ,  Amirhossein HABIBIAN ,  Yuki ASANO

IPC: G06T5/60 ,  G06T5/50

Abstract: Systems and techniques are described herein for modifying video data. For instance, a method for modifying video data is provided. The method may include obtaining first tokens based on a first frame of video data, wherein each of the first tokens comprises a feature vector corresponding to a respective location within the first frame of video data; obtaining second tokens based on a second frame of video data, wherein each of the second tokens comprises a feature vector corresponding to a respective location within the second frame of video data; determining a destination token from among the first tokens; determining candidate tokens from among the second tokens based on respective relationships between the candidate tokens and the destination token; merging the candidate tokens with the destination token resulting in modified second tokens; and processing the modified second tokens using a diffusion model.

公开(公告)号：US20250119561A1

公开(公告)日：2025-04-10

申请号：US18984662

申请日：2024-12-17

Applicant: QUALCOMM Incorporated

Inventor： Amirhossein HABIBIAN ,  Davide ABATI ,  Babak EHTESHAMI BEJNORDI

IPC: G06T5/20 ,  G06V10/46 ,  G06V10/75

Abstract: A method for video processing via an artificial neural network includes receiving a video stream as an input at the artificial neural network. A residual is computed based on a difference between a first feature of a current frame of the video stream and a second feature of a previous frame of the video stream. One or more portions of the current frame of the video stream are processed based on the residual. Additionally, processing is skipped for one or more portions of the current frame of the video based on the residual.

公开(公告)号：US20230154169A1

公开(公告)日：2023-05-18

申请号：US18054274

申请日：2022-11-10

Applicant: QUALCOMM Incorporated

Inventor： Amirhossein HABIBIAN ,  Davide ABATI ,  Haitam BEN YAHIA

IPC: G06V10/778 ,  G06V20/40 ,  G06V10/77 ,  G06V10/82

CPC classification number: G06V10/7792 ,  G06V20/46 ,  G06V20/48 ,  G06V10/7715 ,  G06V10/82 ,  G06V20/41 ,  G06V20/49

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for processing video content using an artificial neural network. An example method generally includes receiving a video data stream including at least a first frame and a second frame. First features are extracted from the first frame using a teacher neural network. A difference between the first frame and the second frame is determined. Second features are extracted from at least the difference between the first frame and the second frame using a student neural network. A feature map for the second frame is generated based a summation of the first features and the second features. An inference is generated for at least the second frame of the video data stream based on the generated feature map for the second feature.

公开(公告)号：US20220159278A1

公开(公告)日：2022-05-19

申请号：US17527659

申请日：2021-11-16

Applicant: QUALCOMM Incorporated

Inventor： Amirhossein HABIBIAN ,  Davide ABATI ,  Babak EHTESHAMI BEJNORDI

IPC: H04N19/196 ,  H04N19/184 ,  H04N19/172 ,  G06N3/02

Abstract: A method for video processing via an artificial neural network includes receiving a video stream as an input at the artificial neural network. A residual is computed based on a difference between a first feature of a current frame of the video stream and a second feature of a previous frame of the video stream. One or more portions of the current frame of the video stream are processed based on the residual. Additionally, processing is skipped for one or more portions of the current frame of the video based on the residual.

公开(公告)号：US20250157207A1

公开(公告)日：2025-05-15

申请号：US18506018

申请日：2023-11-09

Applicant: QUALCOMM Incorporated

Inventor： Davide ABATI ,  Amirhossein HABIBIAN ,  Auke Joris WIGGERS ,  Jens PETERSEN

IPC: G06V10/82 ,  G06V10/774

Abstract: A method includes generating a synthetic dataset with a generative model. The method also includes tuning the generative model based on feedback from a task network that receives the synthetic dataset as input. The task network may perform image recognition. The synthetic dataset may be generated based on a set of classes and labels of the classes. The method may iteratively generate the synthetic dataset and tune the generative model, based on feedback from the task network.

公开(公告)号：US20240169708A1

公开(公告)日：2024-05-23

申请号：US18338184

申请日：2023-06-20

Applicant: QUALCOMM Incorporated

Inventor： Davide ABATI ,  Amirhossein HABIBIAN ,  Markus NAGEL

IPC: G06V10/776 ,  G06V10/77 ,  G06V20/40 ,  G06V10/82

CPC classification number: G06V10/776 ,  G06V10/7715 ,  G06V20/46 ,  G06V10/82

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for delta quantization for video processing and other data streams with temporal content. An example method generally includes receiving image data including at least a first frame and a second frame, generating a first convolutional output based on a first frame using a machine learning model, generating a second convolutional output based on a difference between the first frame and the second frame using one or more quantizers of the machine learning model, generating a third convolutional output associated with the second frame as a combination of the first convolutional output and the second convolutional output, and performing image processing based on the first convolutional output and the third convolutional output.

公开(公告)号：US20210150345A1

公开(公告)日：2021-05-20

申请号：US17097811

申请日：2020-11-13

Applicant: QUALCOMM Incorporated

Inventor： Davide ABATI ,  Babak EHTESHAMI BEJNORDI ,  Jakub Mikolaj TOMCZAK ,  Tijmen Pieter Frederik BLANKEVOORT

IPC: G06N3/08 ,  G06N3/063 ,  G06K9/62

Abstract: Various aspects provide methods for learning, such as continual learning, that support task-incremental learning using a multi-head classification architecture. Various aspects may enable conditional computing to support multi-head classification. Various aspects provide methods for learning, such as continual learning, that support class-incremental learning using a single-head classification architecture. Various aspects may enable conditional computing to support single-head classification by predicting the task associated with a given test input and selecting an associated classification head based at least in part on the task prediction.