A5013998132- Advanced Image and Video Retrieval Techniques
- Advanced Neural Network Applications
- Recommender Systems and Techniques
- E-commerce and Technology Innovations
- Sentiment Analysis and Opinion Mining
- Advanced Technologies in Various Fields
- Text and Document Classification Technologies
- Advanced Measurement and Detection Methods
- Astronomical Observations and Instrumentation
- Educational Technology and Pedagogy
- Robotics and Sensor-Based Localization
- Video Surveillance and Tracking Methods
- Medical Image Segmentation Techniques
Home Depot (United States)
2020-2024
Southeast University
2024
CHN Energy (China)
2023
The traditional wheelchair focuses on the “human-chair” motor function interaction to ensure elderly and people with disabilities’ basic travel. For visual, hearing, physical disabilities, etc., current wheelchairs show shortcomings in terms of accessibility independent travel for this group. Therefore, paper develops an intelligent multimodal human–computer autonomous navigation technology. Firstly, it researches technology occupant gesture recognition, speech head posture recognition...
E-commerce click-stream data and product catalogs offer critical user behavior insights knowledge. This paper propose a multi-modal transformer termed as PINCER, that leverages the above sources to transform initial queries into pseudo-product representations. By tapping these external sources, our model can infer users' potential purchase intent from their limited capture query relevant features. We demonstrate model's superior performance over state-of-the-art alternatives on e-commerce...
Image segmentation is the task of associating pixels in an image with their respective object class labels. It has a wide range applications many industries including healthcare, transportation, robotics, fashion, home improvement, and tourism. Many deep learning-based approaches have been developed for image-level recognition pixel-level scene understanding - latter requiring much denser annotation scenes large set objects. This tutorial provides end-to-end pipeline performing using...
Automatically recommending visually compatible products to Home Decor shoppers is a challenging task for ecommerce companies in the home improvement domain. However, few satisfactory solutions have been proposed address this problem. In paper, we propose novel approach that uses room scene image as primary data source generate product recommendations. More specifically, first detect shown image. Then, use retrieval techniques (e.g. color matching and triplet contrastive learning) find most...
In automatic train operation, non-contact obstacle detection systems have replaced traditional manual sighting verification. One system usually combines multiple sensors including high-definition cameras, lasers, etc., and these require regular demarcation and/or calibration. However, displacement of would happen due to operational vibration, displaced need be figured out second calibrated during the maintenance. Some current methods special equipment experienced maintenance workers; hence...