Zobrazeno 1 - 10
of 231
pro vyhledávání: '"Rüger, Stefan"'
Despite the impressive capability of large language models (LLMs), knowing when to trust their generations remains an open challenge. The recent literature on uncertainty quantification of natural language generation (NLG) utilises a conventional nat
Externí odkaz:
http://arxiv.org/abs/2406.03158
Publikováno v:
2023
Failure detection (FD) in AI systems is a crucial safeguard for the deployment for safety-critical tasks. The common evaluation method of FD performance is the Risk-coverage (RC) curve, which reveals the trade-off between the data coverage rate and t
Externí odkaz:
http://arxiv.org/abs/2308.03179
Publikováno v:
2023
Proper confidence calibration of deep neural networks is essential for reliable predictions in safety-critical tasks. Miscalibration can lead to model over-confidence and/or under-confidence; i.e., the model's confidence in its prediction can be grea
Externí odkaz:
http://arxiv.org/abs/2308.03172
Despite the great success of state-of-the-art deep neural networks, several studies have reported models to be over-confident in predictions, indicating miscalibration. Label Smoothing has been proposed as a solution to the over-confidence problem an
Externí odkaz:
http://arxiv.org/abs/2301.12589
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Pickering, Marcus J, Rüger, Stefan
Publikováno v:
In Computer Vision and Image Understanding 2003 92(2):217-235
Autor:
Overell, Simon1 (AUTHOR) simon.overell01@imperial., Rüger, Stefan1,2 (AUTHOR)
Publikováno v:
International Journal of Geographical Information Science. Mar2008, Vol. 22 Issue 3, p265-287. 23p. 6 Diagrams, 5 Charts, 1 Graph.
Autor:
Rüger, Stefan
Publikováno v:
Advanced Topics in Information Retrieval ISBN: 9783642209451
Information Retrieval: Searching in the 21st Century
Information Retrieval
Information Retrieval: Searching in the 21st Century
Information Retrieval
This chapter examines the challenges and opportunities of Multimedia Information Retrieval and corresponding search engine applications. Computer technology has changed our access to information tremendously: We used to search authors or titles (whic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dc97b202b9bd25318cbc53dbc344b6d9
https://doi.org/10.1007/978-3-642-20946-8_7
https://doi.org/10.1007/978-3-642-20946-8_7
Autor:
Aly, Robin, Doherty, Aiden, Hiemstra, Djoerd, Smeaton, Alan, Gurrin, Cathal, He, Yulan, Kazai, Gabriella, Kruschwitz, Udo, Little, Suzanne, Roelleke, Thomas, Rüger, Stefan, van Rijsbergen, Keith
Publikováno v:
Proceedings of the 32nd European Conference on IR Research (ECIR 2010), 241-252
STARTPAGE=241;ENDPAGE=252;TITLE=Proceedings of the 32nd European Conference on IR Research (ECIR 2010)
Lecture Notes in Computer Science ISBN: 9783642122743
ECIR
Aly, Robin, Doherty, Aiden R. ORCID: 0000-0003-1840-0451, Hiemstra, Djoerd and Smeaton, Alan F. ORCID: 0000-0003-1028-8389 (2010) Beyond shot retrieval: searching for broadcast news items using language models of concepts. In: ECIR 2010-32nd European Conference on Information Retrieval, 28-31 March 2010, Milton Keynes, UK. ISBN 978-3-642-12274-3
STARTPAGE=241;ENDPAGE=252;TITLE=Proceedings of the 32nd European Conference on IR Research (ECIR 2010)
Lecture Notes in Computer Science ISBN: 9783642122743
ECIR
Aly, Robin, Doherty, Aiden R. ORCID: 0000-0003-1840-0451
Current video search systems commonly return video shots as results. We believe that users may better relate to longer, semantic video units and propose a retrieval framework for news story items, which consist of multiple shots. The framework is div
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::80f83ea015b1c40f8d634c1905f24798
https://research.utwente.nl/en/publications/01d4f6b2-27e2-45ab-b340-4b517d7bc6b7
https://research.utwente.nl/en/publications/01d4f6b2-27e2-45ab-b340-4b517d7bc6b7