Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{169971,
        author = {Dhivya P},
        title = {Improving Retail Intelligence: A Unified Scale Invariant and Contrastive Learning Strategy for Enhanced Object Detection and Customer Behavior Analysis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {6},
        pages = {3767-3772},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=169971},
        abstract = {In today's information era, online stores seem to know the customer better than retail stores through advanced data analytics and tracking mechanisms. E-commerce have gained great insights into customer details such as their last purchase, customer preferences, shopping habits, and decision-making processes. To compete with the analytical potential of online stores, retail stores can indeed leverage scale-invariant object detection methods to better meet customer needs by enabling computers to interpret and understand visual information, just as humans do. The motivation of this paper is to detect and analyze customer behavior from video footage acquired by surveillance cameras by combining scale- invariant object detection algorithm and representation learning. With the help of scale invariant object detection method, we can exactly identify customers or objects irrespective of their distance from the surveillance cameras or variations in their appearance due to perspective changes. By exploiting contrastive feature learning, the system can extract selected features from customer interactions captured by the scale-invariant object detection process. This allows for a fine understanding of customer behavior beyond simple object detection. By accurately detecting and tracking customers at different scales provide detailed analysis of customer behavior such as store entry and navigation pattern, in-store dwell time, purchase decision, influence of promotions and marketing. These details will help the retail owners to make data driven decisions based on historical data and patterns such as optimize store layouts, product placements, marketing strategies, estimating busy hours, optimize the staff allocation, etc., leading to enhanced better customer experiences.},
        keywords = {Object detection, Scale-invariant object detection, Customer behavior, Contrastive feature learning, Data driven decision, Representation learning},
        month = {December},
        }