Hybrid 3D Asset Retrieval via Contrastive Vision-Language Matching and Structured Prompt Parsing

Abstract

To use the dataset, the zip parts should be merged back together. This dataset was created for theme name, which was accepted at the IEEE Conference on Artificial Intelligence 2026. paper of the saThe paper will be presented on 9/5/26: https://www.ieeesmc.org/cai-2026/detailed-schedule/ When using this dataset, please cite this Zenodo record and the associated publication: Alkhaldi, Ahmad; Balla, Igli; El Bouazzaoui, Rahma; Chakravorty, Tirthendu Prosad; Rexha, Hergys; Lafond, Sebastien; Klempka, Tristan, Hybrid 3D Asset Retrieval Via Contrastive Vision-Language Matching and Structured Prompt Parsing, IEEE Conference on Artificial Intelligence 2026.