Search Results

Documents authored by Rossetto, Luca

Artifact
Software
DOI: 10.4230/artifacts.28092
MediaGraphOrg/MeGraS

Authors: Luca Rossetto, Florian Ruosch, and Jan Willi

Abstract
Cite as

Luca Rossetto, Florian Ruosch, Jan Willi. MediaGraphOrg/MeGraS (Software, System). Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)

Copy BibTex To Clipboard

@misc{dagstuhl-artifact-28092,
   title = {{MediaGraphOrg/MeGraS}}, 
   author = {Rossetto, Luca and Ruosch, Florian and Willi, Jan},
   note = {Software, swhId: \href{https://archive.softwareheritage.org/swh:1:dir:b0d522ad9603f43d5135aa393c24d74d7ea8a3d7;origin=https://github.com/MediaGraphOrg/MeGraS;visit=swh:1:snp:7fb6b90f79dcc0c44f37a8769abc5f8d5261aba6;anchor=swh:1:rev:85e9f85f70facd165353e2157d59c67985979db1}{\texttt{swh:1:dir:b0d522ad9603f43d5135aa393c24d74d7ea8a3d7}} (visited on 2026-09-30)},
   url = {https://github.com/MediaGraphOrg/MeGraS},
   doi = {10.4230/artifacts.28092},
}
Artifact
Dataset
DOI: 10.4230/artifacts.28093
MediaGraphOrg/MeGraS-SYNTH

Authors: Florian Ruosch and Luca Rossetto

Abstract
Cite as

Florian Ruosch, Luca Rossetto. MediaGraphOrg/MeGraS-SYNTH (Dataset). Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)

Copy BibTex To Clipboard

@misc{dagstuhl-artifact-28093,
   title = {{MediaGraphOrg/MeGraS-SYNTH}}, 
   author = {Ruosch, Florian and Rossetto, Luca},
   note = {Dataset, swhId: \href{https://archive.softwareheritage.org/swh:1:dir:98b200e81f058bd739629f0f2dca77cb7ea523e6;origin=https://github.com/MediaGraphOrg/MeGraS-SYNTH;visit=swh:1:snp:d3473160777661765bcf2be8e980d63bd8bed38d;anchor=swh:1:rev:ad173ba2f100aa0f1761a80ef3dc777d814c6f15}{\texttt{swh:1:dir:98b200e81f058bd739629f0f2dca77cb7ea523e6}} (visited on 2026-09-30)},
   url = {https://github.com/MediaGraphOrg/MeGraS-SYNTH},
   doi = {10.4230/artifacts.28093},
}
Document
Research
DOI: 10.4230/TGDK.4.3.3
A Hybrid Vector-Symbolic Data Model for Multimodal Knowledge Graphs

Authors: Florian Ruosch and Luca Rossetto

Published in: TGDK, Volume 4, Issue 3 (2026). Transactions on Graph Data and Knowledge, Volume 4, Issue 3

Abstract
In this article, we address the architectural and representational “schism” between symbolic knowledge graphs and sub-symbolic multimodal data. By formalizing the MediaGraph Data Model, we demonstrate that high-dimensional vectors and multimedia segments can be integrated as first-class citizens within a unified graph structure. This shift from treating vectors as opaque literals to queryable nodes enables “early-binding” query execution, allowing the SPARQL engine to jointly optimize over both structural relationships and perceptual similarity. Our implementation, MeGraS, provides a scalable engine that mitigates the long-standing N+1 query problem through batched execution. The experimental evaluation on both real-world lifelogging data and a synthetic dataset of 10⁷ triples confirms that our hybrid approach maintains high throughput and retrieval efficiency, even as the complexity of multimodal queries increases. Furthermore, the integration of the Unified Multimedia Segmentation Model ensures that media granularity is preserved, making complex spatiotemporal and content-aware querying possible within a single query framework. Ultimately, MeGraS provides a foundational infrastructure for the next generation of multimodal intelligent systems. By unifying the symbolic and sub-symbolic domains, we provide a pathway toward more expressive and efficient retrieval strategies that can keep pace with the explosion of heterogeneous digital media.
Cite as

Florian Ruosch and Luca Rossetto. A Hybrid Vector-Symbolic Data Model for Multimodal Knowledge Graphs. In Transactions on Graph Data and Knowledge (TGDK), Volume 4, Issue 3, pp. 3:1-3:28, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)

Copy BibTex To Clipboard

@Article{ruosch_et_al:TGDK.4.3.3,
  author =	{Ruosch, Florian and Rossetto, Luca},
  title =	{{A Hybrid Vector-Symbolic Data Model for Multimodal Knowledge Graphs}},
  journal =	{Transactions on Graph Data and Knowledge},
  pages =	{3:1--3:28},
  ISSN =	{2942-7517},
  year =	{2026},
  volume =	{4},
  number =	{3},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/TGDK.4.3.3},
  URN =		{urn:nbn:de:0030-drops-280880},
  doi =		{10.4230/TGDK.4.3.3},
  annote =	{Keywords: Multimodal Knowledge Graphs, Graph Store, Multimodal Media Segmentation}
}
Artifact
Software
DOI: 10.4230/artifacts.22622
lucaro/MeGraS

Authors: Luca Rossetto and Jan Willi

Abstract
Cite as

Luca Rossetto, Jan Willi. lucaro/MeGraS (Software). Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@misc{dagstuhl-artifact-22622,
   title = {{lucaro/MeGraS}}, 
   author = {Rossetto, Luca and Willi, Jan},
   note = {Software, swhId: \href{https://archive.softwareheritage.org/swh:1:dir:d2dfb84bd390d27ad96190f973dfa484b9e68bc0;origin=https://github.com/lucaro/MeGraS;visit=swh:1:snp:223a0c5b2c4d4793f3e3d8b25cefeeafd8a41c11;anchor=swh:1:rev:0bd62c1f4848ca23d1164d35916eaaaddf8645f5}{\texttt{swh:1:dir:d2dfb84bd390d27ad96190f973dfa484b9e68bc0}} (visited on 2024-12-18)},
   url = {https://github.com/lucaro/MeGraS},
   doi = {10.4230/artifacts.22622},
}
Artifact
Audiovisual
DOI: 10.4230/artifacts.22623
lucaro/Unified-Media-Segmentation-Test-Suite

Authors: Luca Rossetto

Abstract
Cite as

Luca Rossetto. lucaro/Unified-Media-Segmentation-Test-Suite (Audiovisual). Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@misc{dagstuhl-artifact-22623,
   title = {{lucaro/Unified-Media-Segmentation-Test-Suite}}, 
   author = {Rossetto, Luca},
   note = {Audiovisual (visited on 2024-12-18)},
   url = {https://github.com/lucaro/Unified-Media-Segmentation-Test-Suite},
   doi = {10.4230/artifacts.22623},
}
Document
DOI: 10.4230/TGDK.2.3.1
Unified Multimedia Segmentation - A Comprehensive Model for URI-based Media Segment Representation

Authors: Jan Willi, Abraham Bernstein, and Luca Rossetto

Published in: TGDK, Volume 2, Issue 3 (2024). Transactions on Graph Data and Knowledge, Volume 2, Issue 3

Abstract
In multimedia annotation, referencing specific segments of a document is often desired due to its richness and multimodality, but no universal representation for such references exists. This significantly hampers the usage of multimedia content in knowledge graphs, as it is modeled as one large atomic information container. Unstructured data - such as text, audio, images, and video - can commonly be decomposed into its constituent parts, as such documents rarely contain only one semantic concept. Hence, it is reasonable to assume that these advances will make it possible to decompose these previous atomic components into logical segments. To be processable by the knowledge graph stack, however, one needs to break the atomic nature of multimedia content, providing a mechanism to address media segments. This paper proposes a Unified Segmentation Model capable of depicting arbitrary segmentations on any media document type. The work begins with a formal analysis of multimedia and segmentation, exploring segmentation operations and how to describe them. Building on this analysis, it then develops a practical scheme for expressing segmentation in Uniform Resource Identifiers (URIs). Given that this approach makes segments of multimedia content referencable, it breaks their atomic nature and makes them first-class citizens within knowledge graphs. The proposed model is implemented as a proof of concept in the MediaGraph Store, a multimedia knowledge graph storage and querying engine.
Cite as

Jan Willi, Abraham Bernstein, and Luca Rossetto. Unified Multimedia Segmentation - A Comprehensive Model for URI-based Media Segment Representation. In Transactions on Graph Data and Knowledge (TGDK), Volume 2, Issue 3, pp. 1:1-1:34, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@Article{willi_et_al:TGDK.2.3.1,
  author =	{Willi, Jan and Bernstein, Abraham and Rossetto, Luca},
  title =	{{Unified Multimedia Segmentation - A Comprehensive Model for URI-based Media Segment Representation}},
  journal =	{Transactions on Graph Data and Knowledge},
  pages =	{1:1--1:34},
  ISSN =	{2942-7517},
  year =	{2024},
  volume =	{2},
  number =	{3},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/TGDK.2.3.1},
  URN =		{urn:nbn:de:0030-drops-225953},
  doi =		{10.4230/TGDK.2.3.1},
  annote =	{Keywords: Multimodal Knowledge Graphs, Multimedia Segmentation, Multimedia Representation}
}

Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2026 Schloss Dagstuhl – LZI GmbH Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact