Invention Publication
- Patent Title: CONTEXT-DRIVEN LEARNING OF HUMAN-OBJECT INTERACTIONS
-
Application No.: US17769269Application Date: 2020-11-14
-
Publication No.: US20240135712A1Publication Date: 2024-04-25
- Inventor: Mert KILICKAYA , Noureldien Mahmoud Elsayed HUSSEIN , Efstratios GAVVES , Arnold Wilhelmus Maria SMEULDERS
- Applicant: QUALCOMM Technologies, Inc.
- Applicant Address: US CA San Diego
- Assignee: QUALCOMM Technologies, Inc.
- Current Assignee: QUALCOMM Technologies, Inc.
- Current Assignee Address: US CA San Diego
- Priority: GR 190100515 2019.11.15
- International Application: PCT/US20/60626 2020.11.14
- Date entered country: 2022-04-13
- Main IPC: G06V20/52
- IPC: G06V20/52 ; G06V10/75 ; G06V10/764 ; G06V10/778 ; G06V10/80 ; G06V10/82

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.
Public/Granted literature
- US12249138B2 Context-driven learning of human-object interactions Public/Granted day:2025-03-11
Information query