Attribute Detection and Visual Search in UGC Clothing Photos
summary
Describes a system for detecting clothing attributes and performing visual search over user-generated clothing photos. Covers using computer vision and machine learning to recognize item attributes (like type, color, style) in UGC images and to enable image-based product search for e-commerce.
AI-written summary · about
chapters (7)
- 0:00Introduction
- 10:05Image search problem
- 20:28Attribute classifier solution
- 30:15Clothing object localization
- 33:15Pose refinement for localization
- 34:41Model results and evaluation
- 35:34Q&A
related talks
33mMachine Learning in Visual Search
41mSearching for Products by Photo
28mVisual Search
22mHarnessing image and text data for product matching
46mImage Recognition with Deep Learning From prototype to production
42mProduct Recognition in Retail/E-Commerce with Azure AI
42mProduct Recognition in Retail/E-Commerce with Azure AI
14mComputer vision on edge devices