Presentation

<
Searchable.City: An Open-Vocabulary Semantic Atlas
SessionEmerging Technologies
DescriptionSearchable.City is an open-vocabulary semantic atlas, built by running a vision-language model (VLM) on millions of street-view images to create a searchable visual index of the city. It turns street-level imagery into a map of visual patterns, revealing where architectural styles, infrastructure, culture, and objects concentrate.
Contributor
Sean Hardesty Lewis
Cornell Tech
Event Type
Emerging Technologies
TimeMonday, 20 July 202610:30am - 5:00pm PDT
LocationConcourse Hall
Session TimeMonday, 20 July 202610:30am - 5:00pm PDTTuesday, 21 July 202610:00am - 5:00pm PDTWednesday, 22 July 202610:00am - 5:00pm PDTThursday, 23 July 202610:00am - 3:00pm PDT
LocationConcourse Hall
Interest Areas
Gaming & Interactive
Research & Education
Keywords
Art
Artificial Intelligence/Machine Learning
Computer Vision
Digital Twins
Education
Generative AI
Pipeline Tools and Work
Real-Time
Scientific Visualization
Spatial Computing
Registration Categories
Full Conference Supporter
Full Conference
Experience
Next PresentationNext PresentationShall We Dance? Resonance of Intentions with an Embodied Agent based on the Free Energy Principle
Similar Presentations
Hands-on Course: Dreaming in 4 dimensions: generating media with Gemini, Genie, and Veo
LatentScore: Sketching Soundscapes with LLM-Distilled Retrieval for Procedural Synthesis
From Human Vision to Machine Vision