18153166. WEIGHTED FACTORIZATION FOR HUMAN-OBJECT-INTERACTION DETECTION simplified abstract (Accenture Global Solutions Limited)
Contents
WEIGHTED FACTORIZATION FOR HUMAN-OBJECT-INTERACTION DETECTION
Organization Name
Accenture Global Solutions Limited
Inventor(s)
David Nguyen of Newark CA (US)
WEIGHTED FACTORIZATION FOR HUMAN-OBJECT-INTERACTION DETECTION - A simplified explanation of the abstract
This abstract first appeared for US patent application 18153166 titled 'WEIGHTED FACTORIZATION FOR HUMAN-OBJECT-INTERACTION DETECTION
The abstract of this patent application describes a method that involves receiving an image, extracting features from the image, identifying potential human-object interactions (HOIs) in the image, assigning feature scores to each HOI, and selecting the most relevant HOI based on final scores calculated using a set of weights generated by machine learning models.
- Receiving an image
- Extracting features from the image
- Identifying potential human-object interactions (HOIs)
- Assigning feature scores to each HOI
- Generating sets of weights using machine learning models
- Calculating final scores for each HOI based on feature scores and weights
- Selecting the most relevant HOI for the image
Potential Applications: - Image recognition and classification systems - Human-computer interaction technologies - Augmented reality applications
Problems Solved: - Enhancing image understanding and interpretation - Improving the accuracy of object recognition in images - Facilitating the development of intelligent systems
Benefits: - Increased efficiency in image analysis - Enhanced user experience in interactive applications - Advanced capabilities in computer vision technology
Commercial Applications: Title: Advanced Image Recognition Technology for Enhanced User Experience This technology can be utilized in various industries such as: - E-commerce for product recommendation systems - Security and surveillance for threat detection - Healthcare for medical image analysis
Questions about the technology: 1. How does this technology improve the accuracy of object recognition in images? 2. What are the potential implications of using machine learning models to generate sets of weights in image analysis?
Original Abstract Submitted
Implementations include actions of receiving an image, providing a set of features for the image, determining a set of HOIs including one or more HOIs that are potentially represented in the image, providing sets of feature scores by, for each HOI in the set of HOIs, determining, by a first ML model, a set of feature scores for respective features in the set of features, generating, by a second ML model, sets of weights based on the set of HOIs, providing a set of final scores by, for each HOI in the set of HOIs, determining a final score based on a respective set of weights and the set of feature scores, each final score corresponding to a respective HOI in the set of HOIs, and selecting an output HOI for the image from the set of HOIs based on the set of final scores.
