WISE: A Multimodal Search Engine for Visual Scenes, Audio, Objects, Faces, Speech, and Metadata.

@inproceedings{sridhar-2026-wise, author = {Prasanna Sridhar and Horace Lee and David M. S. Pinto and Andrew Zisserman and Abhishek Dutta}, editor = {Hannah Bast and Alistair Moffat and Falk Scholer and Marc Najork and Min Zhang and Hannah Bast and Marc Najork and Min Zhang}, title = {{WISE: A Multimodal Search Engine for Visual Scenes, Audio, Objects, Faces, Speech, and Metadata}}, booktitle = {{Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2026, MelbourneVICAustralia, July 20-24, 2026}}, pages = {5230--5234}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805712.3808375}, doi = {https://doi.org/10.1145/3805712.3808375} }