How CV Helps Users Find Their Dream Product by Visual Example
summary
A presentation describes building a product that helps users find desired items by visual similarity using a question-driven interaction inspired by the Akinator game. It explains applying a guided-questions approach combined with computer vision (CV) to narrow down visual search results so users can locate their “dream” product.
AI-written summary · about
chapters (18)
- 0:00Introduction
- 1:08Dream product problem
- 3:36Akinator inspiration
- 5:22Lucky search mechanics
- 6:46Finding similar products
- 8:32Neural network training
- 10:39Training results
- 12:26First implementation
- 13:50Second iteration
- 17:02Tech stack details
- 19:51A/B test results
- 21:37Lucky search improvements
- 24:23Demo and availability
- 25:26ML unusual uses
- 26:09Q&A
- 31:58Team and timeline
- 33:01Metrics and attributes
- 34:25Summary
related talks
33mMachine Learning in Visual Search
41mSearching for Products by Photo
31mAI Search for Marketplaces: Experiences & Tech
29mDeveloping Visual AI Solutions for Online Marketplace
01h 26mBuilding an Image Search Engine with Generative Computer Vision Models
35mBeyond painting buttons: computer vision techniques
30mEvolving Search in Online Marketplaces: Practical Applications of AI
17mCalculating recommendations based on product images #bbuzz