Recollection

reCollection uses interactive AI to assemble and display synthetic collective memories based on language input. The AI system learns from Alzheimer patients’ visual and descriptive memories and then imagines new memories by interpreting real-time narratives from participants in the installation.

It offers an artistic approach and future prototype for cultural heritage reproduction and re-imagination and explores the tensions in the co-relations between visual representations, language, and narratives.

In our exploration of AI, biodata, and reconnection, we have paired ReCollection, an interactive AI art installation that blurs the boundaries between remembrance and imagination and Entanglement, where AI interprets forests into dreams and hallucinations.

ReCollection (2023) is an interactive AI art installation that assembles synthetic collective memories based on language input, blurring the boundaries between remembrance and imagination through AI system design and interactive experimental visualization. We developed our AI system by fine-tuning a pre-trained, transformer-based AI model to learn the documentaries of Alzheimer patients’ visual memories and their descriptions. The system imagines new memories by interpreting real-time narratives from participants in the installation. It offers an artistic approach and future prototype for cultural heritage reproduction and re-imagination and explores the tensions in the co-relations between visual representations, language, and narratives. Special thanks to our AI Technical Director Sam Green, Semiotic Labs

 


 

ARTIST BIO

Weidi Zhang: Weidi Zhang is a Los Angeles and Phoenix-based new media artist/designer and an assistant professor of immersive experience design at Arizona State University (US). Her interdisciplinary art and design research investigates A Speculative Assemblage at the intersection of immersive media design, experimental data visualization, and interactive AI art. Her works are featured in international awards, such as Red Dot Design Award, Best In Show Awards in SIGGRAPH, Honorary Mention in Prix Ars Electronica, Juried Selection in Japan Media Arts Festival, Lumen Prize shortlists, and others. Her works have been exhibited at international venues such as ISEA, Times Art Museum, Society For Arts and Technology [SAT], SwissNex Galler, Zeiss-Planetarium Berlin, and others. She holds her Ph.D. degree in Media Arts and Technology from the University of California, Santa Barbara.
Website: http://www.zhangweidi.com

Rodger(Jieliang) Luo:  Rodger (Jieliang) Luo is a Principal AI Research Scientist at the Autodesk AI Lab in San Francisco. He received his Ph.D. from UC Santa Barbara, where he explored the intersection of machine learning, robotics, and creativity. His current research focus is understanding how to learn complex behaviors with imitation and reinforcement learning and applying the insights for construction automation and architecture design. His work has been presented at SIGGRAPH, ICCV, ICRA, CoRL, IROS, ECCV, ICLR, and others.

Join Our Mailing List

Get the latest news about transformative, immersive works that will change the way you see the future.