A new Retrieval Engine for vitrivr
While the vitrivr stack has seen many changes in components over the years, its feature extraction and query processing engine traces its history back almost a decade. Some aspects of its architecture and operation are no longer current, limiting the entire stack’s applicability in various use cases. In this paper, we present the first glimpse into vitrivr’s next-generation retrieval engine and our plan to overcome previously identified limitations.
VBS 2024
This preprint has not undergone peer review (when applicable) or any post-submission improvements or corrections. The Version of Record of this contribution is published in MMM 2024 - The 30th International Conference on Multimedia Modeling, and is available online at https://doi.org/10.1007/978-3-031-53302-0_28.