Document - VISIONE at VBS2019

2019

Conference article Open Access

VISIONE at VBS2019

Amato G., Bolettieri P., Carrara F., Debole F., Falchi F., Gennaro C., Vadicamo L., Vairo C.

Content-based video retrieval Video search Convolutional Neural Networks Known Item Search

This paper presents VISIONE, a tool for large-scale video search. The tool can be used for both known-item and ad-hoc video search tasks since it integrates several content-based analysis and re- trieval modules, including a keyword search, a spatial object-based search, and a visual similarity search. Our implementation is based on state-of- the-art deep learning approaches for the content analysis and leverages highly efficient indexing techniques to ensure scalability. Specifically, we encode all the visual and textual descriptors extracted from the videos into (surrogate) textual representations that are then efficiently indexed and searched using an off-the-shelf text search engine.

Source: MMM 2019 - 25th International Conference on Multimedia Modeling, pp. 591–596, Thessaloniki, Greece, 08-11/01/2019

Publisher: Springer International Publishing, CH-6330 Cham (ZG), CHE

Metrics

Back to previous page

Cite as

BibTeX entry

@inproceedings{oai:it.cnr:prodotti:403935,
	title = {VISIONE at VBS2019},
	author = {Amato G. and Bolettieri P. and Carrara F. and Debole F. and Falchi F. and Gennaro C. and Vadicamo L. and Vairo C.},
	publisher = {Springer International Publishing, CH-6330 Cham (ZG), CHE},
	doi = {10.1007/978-3-030-05716-9_51},
	booktitle = {MMM 2019 - 25th International Conference on Multimedia Modeling, pp. 591–596, Thessaloniki, Greece, 08-11/01/2019},
	year = {2019}
}