ITERATIVE APPROACH FOR WEAKLY-SUPERVISED ACTION LOCALIZATION

Patent №

US 11,257,222

Granted

2022-02-22

Filed 2019

Owner

INTERNATIONAL BUSINESS MACHINES CORPORATION

AI components

4

ml · vision · kr · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16292847

Embodiments of the present invention are directed to a computer-implemented method for action localization. A non-limiting example of the computer-implemented method includes receiving, by a processor, a video and segmenting, by the processor, the video into a set of video segments. The computer-implemented method classifies, by the processor, each video segment into a class and calculates, by the processor, importance scores for each video segment of a class within the set of video segments. The computer-implemented method determines, by the processor, a winning video segment of the class within the set of video segments based on the importance scores for each video segment within the class, stores, by the processor, the winning video segment from the set of video segments, and removes the winning video segment from the set of video segments.

Machine learningVisionKnowledge representationAI hardwareG06F 16/75G06F 18/2431G06N 3/04G06N 3/0464G06N 3/0895G06N 20/00G06T 7/215G06V 10/764+6 more

AI classification

Vision1.00
Knowledge representation1.00
Machine learning1.00
AI hardware0.96
Natural language0.30
Evolutionary computation0.03
Planning0.01
Speech0.00

Ownership

INTERNATIONAL BUSINESS MACHINES CORPORATION

assignment · 485070105

Assignors

GAN, CHUANG, ZHANG, YANG, LIU, SIJIA, WANG, DAKUO

On an employer assignment, the assignors are typically the inventors.

From the same owner

© 2026 NYSGPT2525 LLC