Pinpoint footage and surface patterns of identity, time, and location.
Supported by
In partnership with
Generate descriptions for terabytes of media and index it in hours, then collaboratively review the results.
Create analysis flows that adapt to each file’s content.
Find where the same faces and voices appear across files.
Identify likely GPS coordinates and addresses using context and visual clues.
Use natural language to search and find relevant images and video timestamps based on visual content and generated descriptions.
About us
Dean Issacharoff is a creative technologist and communications professional.
He works in AI safety and previously led communications for human rights NGOs and parliamentary parties.
He holds a Master's degree from NYU's Interactive Telecommunications Program, where he began building VSIN as his thesis.
Georgia Edwards is currently Training and Partnerships manager at WITNESS where she leads on visual investigations.
She has been working with VSIN on managing and developing community-led investigations for the analysis of large-scale video collections of human rights abuses.
Jasmine Nackash is a designer and creative technologist working on tools and experiences that aim to help people make sense of complex, layered information.
She holds a Master’s degree from NYU’s Interactive Telecommunications Program, where she recently completed a year-long postdoctoral research residency.