COBISS Co-operative Online Bibliographic system & services COBISS
Veljka Kočić
Personal bibliography for the year 2025
2025
1.
HOLZINGER, Andreas, LUKAČ, Niko, ROZAJAC, Dzemail, JOHNSTON, Emil, KOČIĆ, Veljka,
HOERL, Bernhard, GOLLOB, Christoph, NOTHDURFT, Arne, STAMPFER, Karl, SCHWENG, Stefan,
DEL SER, Javier. Enhancing trust in automated 3D point cloud data interpretation through
explainable counterfactuals. Information fusion. [Online ed.]. July 2025, vol. 119, [article no.] 103032, 15 str., ilustr. ISSN 1872-6305.
Digital Library of the University of Maribor – DLUM, DOI: 10.1016/j.inffus.2025.103032. [COBISS.SI-ID 228135939]
project: Andreas Holzinger acknowledges funding support from the Austrian Science Fund (FWF), Austria, Project: P-32554 explainable Artificial Intelligence; and of the Government of Lower Austria, Project GFF NÖ FTI-22-I-004 ‘‘Infrastructure for the realistic testing of AI-supported robot systems in demanding environments (e.g. forest) without direct energy connection, for multiple use cases (e.g. monitoring/maintenance of forest roads) - human–robot teaming’’. Niko Lukač acknowledges support from the Slovenian Research and Innovation Agency (Funding Nos. P2-0041 and J7-50095). Javier Del Ser acknowledges funding support from the Basque Government, Spain through the ELKARTEK program (BEREZ-IA project, KK-2023/00012) and the consolidated research group MATHMODE (ref. T1256-22). We would like to thank the International Society for Photogrammetry and Remote Sensing (ISPRS) working group III/4 and the German Society for Photogrammetry, Remote Sensing and Geoinformation (DGPF) for providing the Vaihingen dataset. We would like to thank the City of Surrey and Varney et al. from the University of Dayton for providing the DALES dataset.
project: Andreas Holzinger acknowledges funding support from the Austrian Science Fund (FWF), Austria, Project: P-32554 explainable Artificial Intelligence; and of the Government of Lower Austria, Project GFF NÖ FTI-22-I-004 ‘‘Infrastructure for the realistic testing of AI-supported robot systems in demanding environments (e.g. forest) without direct energy connection, for multiple use cases (e.g. monitoring/maintenance of forest roads) - human–robot teaming’’. Niko Lukač acknowledges support from the Slovenian Research and Innovation Agency (Funding Nos. P2-0041 and J7-50095). Javier Del Ser acknowledges funding support from the Basque Government, Spain through the ELKARTEK program (BEREZ-IA project, KK-2023/00012) and the consolidated research group MATHMODE (ref. T1256-22). We would like to thank the International Society for Photogrammetry and Remote Sensing (ISPRS) working group III/4 and the German Society for Photogrammetry, Remote Sensing and Geoinformation (DGPF) for providing the Vaihingen dataset. We would like to thank the City of Surrey and Varney et al. from the University of Dayton for providing the DALES dataset.
2.
KOČIĆ, Veljka, LUKAČ, Niko, ROZAJAC, Dzemail, SCHWENG, Stefan, GOLLOB, Christoph,
NOTHDURFT, Arne, STAMPFER, Karl, DEL SER, Javier, HOLZINGER, Andreas. LLM in the loop:
a framework for contextualizing counterfactual segment perturbations in point clouds.
IEEE access. 2025, vol. 13, str. 85507-85525, ilustr. ISSN 2169-3536. Digital Library of the University of Maribor – DLUM, DOI: 10.1109/ACCESS.2025.3568052. [COBISS.SI-ID 236009987]
project: Parts of this work have received funding from the Austrian Science Fund (FWF), Project: P-32554 (Explainable Artificial Intelligence), and of the Government of Lower Austria, Project GFF NÖ FTI-22-I-004 "Infrastructure for the realistic testing of AI-supported robot systems"; and from the Basque Government through ELKARTEK funding grants (KK-2024/00064) and the consolidated research group MATHMODE (IT1456-22).
project: Parts of this work have received funding from the Austrian Science Fund (FWF), Project: P-32554 (Explainable Artificial Intelligence), and of the Government of Lower Austria, Project GFF NÖ FTI-22-I-004 "Infrastructure for the realistic testing of AI-supported robot systems"; and from the Basque Government through ELKARTEK funding grants (KK-2024/00064) and the consolidated research group MATHMODE (IT1456-22).