Document - VISIONE 5.0: enhanced user interface and AI models for VBS2024

2024

Conference article Open Access

VISIONE 5.0: enhanced user interface and AI models for VBS2024

Giuseppe Amato, Paolo Bolettieri, Fabio Carrara, Fabrizio Falchi, Claudio Gennaro, Nicola Messina, Lucia Vadicamo, Claudio Vairo

Video search Cross-modal retrieval Surrogate Text Representation Content-based video retrieval Multi-modal Retrieval Information Search and Retrieval

In this paper, we introduce the fifth release of VISIONE, an advanced video retrieval system offering diverse search functionalities. The user can search for a target video using textual prompts, drawing objects and colors appearing in the target scenes in a canvas, or images as query examples to search for video keyframes with similar content. Compared to the previous version of our system, which was runner-up at VBS 2023, the forthcoming release, set to participate in VBS 2024, showcases a refined user interface that enhances its usability and updated AI models for more effective video content analysis.

Source: LECTURE NOTES IN COMPUTER SCIENCE, vol. 14557, pp. 332-339. Amsterdam, NL, 29/01-2/02/2024

Metrics

Back to previous page

Cite as

BibTeX entry

@inproceedings{oai:iris.cnr.it:20.500.14243/485001,
	title = {VISIONE 5.0: enhanced user interface and AI models for VBS2024},
	author = {Giuseppe Amato and Paolo Bolettieri and Fabio Carrara and Fabrizio Falchi and Claudio Gennaro and Nicola Messina and Lucia Vadicamo and Claudio Vairo},
	doi = {10.1007/978-3-031-53302-0_29},
	booktitle = {LECTURE NOTES IN COMPUTER SCIENCE, vol. 14557, pp. 332-339. Amsterdam, NL, 29/01-2/02/2024},
	year = {2024}
}