公开(公告)号：US12249138B2

公开(公告)日：2025-03-11

申请号：US17769269

申请日：2020-11-14

Applicant: QUALCOMM Technologies, Inc.

Inventor： Mert Kilickaya ,  Noureldien Mahmoud Elsayed Hussein ,  Efstratios Gavves ,  Arnold Wilhelmus Maria Smeulders

IPC: G06V10/00 ,  G06V10/44 ,  G06V10/75 ,  G06V10/764 ,  G06V10/778 ,  G06V10/80 ,  G06V10/82 ,  G06V20/00 ,  G06V20/52 ,  G06V40/10

Abstract: A method for classifying a human-object interaction includes identifying a human-object interaction in the input. Context features of the input are identified. Each identified context feature is compared with the identified human-object interaction. An importance of the identified context feature is determined for the identified human-object interaction. The context feature is fused with the identified human-object interaction when the importance is greater than a threshold.

公开(公告)号：US11270425B2

公开(公告)日：2022-03-08

申请号：US16686007

申请日：2019-11-15

Applicant: QUALCOMM Technologies, Inc.

Inventor： Shuai Liao ,  Efstratios Gavves ,  Cornelis Snoek

IPC: G06T7/00 ,  G06N20/10 ,  G06N3/08 ,  G06N3/04

Abstract: A method for labeling a spherical target includes receiving an input including a representation of an object. The method also includes estimating unconstrained coordinates corresponding to the object. The method further includes estimating coordinates on a sphere by applying a spherical exponential activation function to the unconstrained coordinates. The method also associates the input with a set of values corresponding to a spherical target based on the estimated coordinates on the sphere.

公开(公告)号：US11842279B2

公开(公告)日：2023-12-12

申请号：US16945625

申请日：2020-07-31

Applicant: QUALCOMM Technologies, Inc.

Inventor： Changyong Oh ,  Efstratios Gavves ,  Jakub Mikolaj Tomczak ,  Max Welling

IPC: G06N3/082 ,  G06F18/20 ,  G06F18/10 ,  G06F18/21 ,  G06N7/01

CPC classification number: G06N3/082 ,  G06F18/10 ,  G06F18/217 ,  G06F18/29 ,  G06N7/01

Abstract: Certain aspects provide a method for determining a solution to a combinatorial optimization problem, including: determining a plurality of subgraphs, wherein each subgraph of the plurality of subgraphs corresponds to a combinatorial variable of the plurality of combinatorial variables; determining a combinatorial graph based on the plurality of subgraphs; determining evaluation data comprising a set of vertices in the combinatorial graph and evaluations on the set of vertices; fitting a Gaussian process to the evaluation data; determining an acquisition function for vertices in the combinatorial graph using a predictive mean and a predictive variance from the fitted Gaussian process; optimizing the acquisition function on the combinatorial graph to determine a next vertex to evaluate; evaluating the next vertex; updating the evaluation data with a tuple of the next vertex and its evaluation; and determining a solution to the problem, wherein the solution comprises a vertex of the combinatorial graph.

公开(公告)号：US11481576B2

公开(公告)日：2022-10-25

申请号：US16827592

申请日：2020-03-23

Applicant: QUALCOMM Technologies, Inc.

Inventor： Mert Kilickaya ,  Efstratios Gavves ,  Arnold Wilhelmus Maria Smeulders

IPC: G06K9/00 ,  G06K9/62 ,  G06N3/08

Abstract: A method for processing an image is presented. The method locates a subject and an object of a subject-object interaction in the image. The method determines relative weights of the subject, the object, and a context region for classification. The method further classifies the subject-object interaction based on a classification of a weighted representation of the subject, a weighted representation of the object, and a weighted representation of the context region.

公开(公告)号：US11443514B2

公开(公告)日：2022-09-13

申请号：US16827342

申请日：2020-03-23

Applicant: QUALCOMM Technologies, Inc.

Inventor： Noureldien Mahmoud Elsayed Hussein ,  Efstratios Gavves ,  Arnold Wilhelmus Maria Smeulders

IPC: G06K9/62 ,  G06V20/40 ,  G06N3/04

Abstract: A method for classifying subject activities in videos includes learning latent (previously generated) concepts that are analogous to nodes of a graph to be generated for an activity in a video. The method also includes receiving video segments of the video. A similarity between the video segments and the previously generated concepts is measured to obtain segment representations as a weighted set of latent concepts. The method further includes determining a relationship between the segment representations and their transitioning pattern over time to determine a reduced set of nodes and/or edges for the graph. The graph of the activity in the video represented by the video segments is generated based on the reduced set of nodes and/or edges. The nodes of the graph are represented by the latent concepts. Subject activities in the video are classified based on the graph.