- BibTeXEndNoteBibSonomyCong, Y., Xu, M., Simon, C., Chen, S., Ren, J., Xie, Y., Perez-Rua, J.-M., Rosenhahn, B., Xiang, T., and He, S. (2024)FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing. In International Conference on Learning Representations (ICLR).
@inproceedings{ConXu2024a,
author = {Cong, Yuren and Xu, Mengmeng and Simon, Christian and Chen, Shoufa and Ren, Jiawei and Xie, Yanping and Perez-Rua, Juan-Manuel and Rosenhahn, Bodo and Xiang, Tao and He, Sen},
booktitle = {International Conference on Learning Representations (ICLR)},
keywords = {from:tntl3s},
title = {FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing},
year = 2024
}%0 Conference Paper
%1 ConXu2024a
%A Cong, Yuren
%A Xu, Mengmeng
%A Simon, Christian
%A Chen, Shoufa
%A Ren, Jiawei
%A Xie, Yanping
%A Perez-Rua, Juan-Manuel
%A Rosenhahn, Bodo
%A Xiang, Tao
%A He, Sen
%B International Conference on Learning Representations (ICLR)
%D 2024
%T FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing - BibTeXEndNoteBibSonomyKluger, F., and Rosenhahn, B. (2024)PARSAC: Accelerating Robust Multi-Model Fitting with Parallel Sample Consensus. In AAAI.
@inproceedings{KluRos2024a,
author = {Kluger, Florian and Rosenhahn, Bodo},
booktitle = {AAAI},
keywords = {PARSAC},
month = {02},
title = {PARSAC: Accelerating Robust Multi-Model Fitting with Parallel Sample Consensus},
year = 2024
}%0 Conference Paper
%1 KluRos2024a
%A Kluger, Florian
%A Rosenhahn, Bodo
%B AAAI
%D 2024
%T PARSAC: Accelerating Robust Multi-Model Fitting with Parallel Sample Consensus - BibTeXEndNoteBibSonomyKaiser, T., Reinders, C., and Rosenhahn, B. (2023)Compensation Learning in Semantic Segmentation. In Computer Vision and Pattern Recognition Workshops (CVPRW).
@inproceedings{KaiRei2023a,
author = {Kaiser, Timo and Reinders, Christoph and Rosenhahn, Bodo},
booktitle = {Computer Vision and Pattern Recognition Workshops (CVPRW)},
keywords = {Segmention},
month = {06},
title = {Compensation Learning in Semantic Segmentation},
year = 2023
}%0 Conference Paper
%1 KaiRei2023a
%A Kaiser, Timo
%A Reinders, Christoph
%A Rosenhahn, Bodo
%B Computer Vision and Pattern Recognition Workshops (CVPRW)
%D 2023
%T Compensation Learning in Semantic Segmentation - BibTeXEndNoteBibSonomySafikhani, P., and Broneske, D. (2023)Enhancing AutoNLP with fine-tuned BERT models: An evaluation of text representation methods for AutoPyTorch., International Conference on Machine Learning Techniques and NLP 13.
@article{SafBro2023,
author = {Safikhani, Parisa and Broneske, David},
journal = {International Conference on Machine Learning Techniques and NLP},
keywords = {BERT},
month = {09},
number = 16,
title = {Enhancing AutoNLP with fine-tuned BERT models: An evaluation of text representation methods for AutoPyTorch.},
volume = 13,
year = 2023
}%0 Journal Article
%1 SafBro2023
%A Safikhani, Parisa
%A Broneske, David
%D 2023
%J International Conference on Machine Learning Techniques and NLP
%N 16
%T Enhancing AutoNLP with fine-tuned BERT models: An evaluation of text representation methods for AutoPyTorch.
%V 13
%@ 978-1-923107-04-5 - URLBibTeXEndNoteBibSonomyNandy, A., Kapadnis, M. N., Goyal, P., and Ganguly, N. (2023)CLMSM: A Multi-Task Learning Framework for Pre-training on Procedural Text. In The 2023 Conference on Empirical Methods in Natural Language Processing.
@inproceedings{nandy2023textbfemphclmsm,
author = {Nandy, Abhilash and Kapadnis, Manav Nitin and Goyal, Pawan and Ganguly, Niloy},
booktitle = {The 2023 Conference on Empirical Methods in Natural Language Processing},
keywords = {pretraining},
title = {CLMSM: A Multi-Task Learning Framework for Pre-training on Procedural Text},
year = 2023
}%0 Conference Paper
%1 nandy2023textbfemphclmsm
%A Nandy, Abhilash
%A Kapadnis, Manav Nitin
%A Goyal, Pawan
%A Ganguly, Niloy
%B The 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%T CLMSM: A Multi-Task Learning Framework for Pre-training on Procedural Text
%U https://openreview.net/forum?id=SP8zIwanHD - URLBibTeXEndNoteBibSonomyAuer, S., Barone, D. A. C., Bartz, C., Cortes, E. G., Jaradeh, M. Y., Karras, O., Koubarakis, M., Mouromtsev, D., Pliukhin, D., Radyush, D., Shilin, I., Stocker, M., and Tsalapati, E. (2023, March)SciQA benchmark: Dataset and {RDF} dump (Version 5), Zenodo.
@misc{DBLP:data/10/AuerBBCJKKMPRSST23a,
author = {Auer, S{{ö}}ren and Barone, Dante A. C. and Bartz, Cassiano and Cortes, Eduardo G. and Jaradeh, Mohamad Yaser and Karras, Oliver and Koubarakis, Manolis and Mouromtsev, Dmitry and Pliukhin, Dmitrii and Radyush, Daniil and Shilin, Ivan and Stocker, Markus and Tsalapati, Eleni},
howpublished = {\url{https://doi.org/10.5281/zenodo.7727922}},
keywords = {leibnizailab},
month = {03},
note = {Accessed on YYYY-MM-DD.},
publisher = {Zenodo},
title = {SciQA benchmark: Dataset and {RDF} dump (Version 5)},
year = 2023
}%0 Generic
%1 DBLP:data/10/AuerBBCJKKMPRSST23a
%A Auer, S{{ö}}ren
%A Barone, Dante A. C.
%A Bartz, Cassiano
%A Cortes, Eduardo G.
%A Jaradeh, Mohamad Yaser
%A Karras, Oliver
%A Koubarakis, Manolis
%A Mouromtsev, Dmitry
%A Pliukhin, Dmitrii
%A Radyush, Daniil
%A Shilin, Ivan
%A Stocker, Markus
%A Tsalapati, Eleni
%D 2023
%I Zenodo
%R 10.5281/ZENODO.7727922
%T SciQA benchmark: Dataset and {RDF} dump (Version 5)
%U https://doi.org/10.5281/zenodo.7727922 - URLBibTeXEndNoteBibSonomyBenjamins, C., Eimer, T., Schubert, F., Mohan, A., D{ö}hler, S., Biedenkapp, A., Rosenhahn, B., Hutter, F., and Lindauer, M. (2023)Contextualize Me - The Case for Context in Reinforcement Learning, Transactions on Machine Learning Research.
@article{BenEim2023,
author = {Benjamins, Carolin and Eimer, Theresa and Schubert, Frederik and Mohan, Aditya and D{ö}hler, Sebastian and Biedenkapp, André and Rosenhahn, Bodo and Hutter, Frank and Lindauer, Marius},
journal = {Transactions on Machine Learning Research},
keywords = {reinforcement},
month = {06},
title = {Contextualize Me - The Case for Context in Reinforcement Learning},
year = 2023
}%0 Journal Article
%1 BenEim2023
%A Benjamins, Carolin
%A Eimer, Theresa
%A Schubert, Frederik
%A Mohan, Aditya
%A D{ö}hler, Sebastian
%A Biedenkapp, André
%A Rosenhahn, Bodo
%A Hutter, Frank
%A Lindauer, Marius
%D 2023
%J Transactions on Machine Learning Research
%T Contextualize Me - The Case for Context in Reinforcement Learning
%U https://arxiv.org/abs/2202.04500 - AbstractBibTeXEndNoteBibSonomyRoy, S., Wallat, J., Sundaram, S. S., Nejdl, W., and Ganguly, N. (2023)GENEMASK: Fast Pretraining of Gene Sequences to Enable Few-Shot Learning. In Frontiers in Artificial Intelligence and Applications, pp. 2002–2009.Large-scale language models such as DNABert and LOGO aim to learn optimal gene representations and are trained on the entire Human Reference Genome. However, standard tokenization schemes involve a simple sliding window of tokens like k-mers that do not leverage any gene-based semantics and thus may lead to (trivial) masking of easily predictable sequences, and subsequently inefficient Masked Language Modeling (MLM) training. Therefore, we propose a novel masking algorithm, GENEMASK, for MLM training of gene sequences, where we randomly identify positions in a gene sequence as mask centers and locally select the span around the mask center with the highest Normalized Pointwise Mutual Information (NPMI) to mask. We observe that in the absence of human-understandable semantics in the genomics domain (in contrast, semantic units like words and phrases are inherently available in NLP), GENEMASK-based models substantially outperform the SOTA models (DNABert and LOGO) over four benchmark gene sequence classification datasets in five few-shot settings (10 to 1000-shot). More significantly, the GENEMASK-based DNABert model is trained for less than one-tenth of the number of epochs of the original SOTA model. We also observe a strong correlation between top-ranked PMI tokens and conserved DNA sequence motifs, which may indicate the incorporation of latent genomic information. The codes (including trained models) and datasets are made publicly available at unmapped: uri https://github.com/roysoumya/GeneMask.
@inproceedings{noauthororeditor,
abstract = {Large-scale language models such as DNABert and LOGO aim to learn optimal gene representations and are trained on the entire Human Reference Genome. However, standard tokenization schemes involve a simple sliding window of tokens like k-mers that do not leverage any gene-based semantics and thus may lead to (trivial) masking of easily predictable sequences, and subsequently inefficient Masked Language Modeling (MLM) training. Therefore, we propose a novel masking algorithm, GENEMASK, for MLM training of gene sequences, where we randomly identify positions in a gene sequence as mask centers and locally select the span around the mask center with the highest Normalized Pointwise Mutual Information (NPMI) to mask. We observe that in the absence of human-understandable semantics in the genomics domain (in contrast, semantic units like words and phrases are inherently available in NLP), GENEMASK-based models substantially outperform the SOTA models (DNABert and LOGO) over four benchmark gene sequence classification datasets in five few-shot settings (10 to 1000-shot). More significantly, the GENEMASK-based DNABert model is trained for less than one-tenth of the number of epochs of the original SOTA model. We also observe a strong correlation between top-ranked PMI tokens and conserved DNA sequence motifs, which may indicate the incorporation of latent genomic information. The codes (including trained models) and datasets are made publicly available at unmapped: uri https://github.com/roysoumya/GeneMask.},
author = {Roy, Soumyadeep and Wallat, Jonas and Sundaram, Sowmya S and Nejdl, Wolfgang and Ganguly, Niloy},
keywords = {l3s},
pages = {2002-2009},
series = {Frontiers in Artificial Intelligence and Applications},
title = {GENEMASK: Fast Pretraining of Gene Sequences to Enable Few-Shot Learning},
volume = 372,
year = 2023
}%0 Conference Paper
%1 noauthororeditor
%A Roy, Soumyadeep
%A Wallat, Jonas
%A Sundaram, Sowmya S
%A Nejdl, Wolfgang
%A Ganguly, Niloy
%B Frontiers in Artificial Intelligence and Applications
%D 2023
%P 2002-2009
%R 10.3233/FAIA230492
%T GENEMASK: Fast Pretraining of Gene Sequences to Enable Few-Shot Learning
%V 372
%X Large-scale language models such as DNABert and LOGO aim to learn optimal gene representations and are trained on the entire Human Reference Genome. However, standard tokenization schemes involve a simple sliding window of tokens like k-mers that do not leverage any gene-based semantics and thus may lead to (trivial) masking of easily predictable sequences, and subsequently inefficient Masked Language Modeling (MLM) training. Therefore, we propose a novel masking algorithm, GENEMASK, for MLM training of gene sequences, where we randomly identify positions in a gene sequence as mask centers and locally select the span around the mask center with the highest Normalized Pointwise Mutual Information (NPMI) to mask. We observe that in the absence of human-understandable semantics in the genomics domain (in contrast, semantic units like words and phrases are inherently available in NLP), GENEMASK-based models substantially outperform the SOTA models (DNABert and LOGO) over four benchmark gene sequence classification datasets in five few-shot settings (10 to 1000-shot). More significantly, the GENEMASK-based DNABert model is trained for less than one-tenth of the number of epochs of the original SOTA model. We also observe a strong correlation between top-ranked PMI tokens and conserved DNA sequence motifs, which may indicate the incorporation of latent genomic information. The codes (including trained models) and datasets are made publicly available at unmapped: uri https://github.com/roysoumya/GeneMask.
%@ 978-1-64368-437-6 - BibTeXEndNoteBibSonomyLee, C.-S., Wang, M.-H., Chen, C.-Y., Yang, F.-J., and Dockhorn, A. (2023)Genetic Assessment Agent for High-School Student and Machine Co-Learning Model Construction on Computational Intelligence Experience. In 2023 IEEE Congress on Evolutionary Computation, pp. 1–8.
@inproceedings{LeeWan2023,
author = {Lee, Chang-Shing and Wang, Mei-Hui and Chen, Chih-Yu and Yang, Fu-Jie and Dockhorn, Alexander},
booktitle = {2023 IEEE Congress on Evolutionary Computation},
keywords = {Student},
note = {(to be published)},
pages = {1-8},
title = {Genetic Assessment Agent for High-School Student and Machine Co-Learning Model Construction on Computational Intelligence Experience},
year = 2023
}%0 Conference Paper
%1 LeeWan2023
%A Lee, Chang-Shing
%A Wang, Mei-Hui
%A Chen, Chih-Yu
%A Yang, Fu-Jie
%A Dockhorn, Alexander
%B 2023 IEEE Congress on Evolutionary Computation
%D 2023
%P 1-8
%T Genetic Assessment Agent for High-School Student and Machine Co-Learning Model Construction on Computational Intelligence Experience - BibTeXEndNoteBibSonomyAwiszus, M., Dockhorn, A., Hoover, A. K., Liapis, A., Lucas, S. M., Eladhari, M. P., Schrum, J., and Volz, V. (2023)Language Models for Procedural Content Generation, Human-Game AI Interaction (Dagstuhl Seminar 22251) 12, 34–37.
@article{AwiDoc2023,
author = {Awiszus, Maren and Dockhorn, Alexander and Hoover, Amy K. and Liapis, Antonios and Lucas, Simon M. and Eladhari, Mirjam Palosaari and Schrum, Jacob and Volz, Vanessa},
journal = {Human-Game AI Interaction (Dagstuhl Seminar 22251)},
keywords = {Language},
month = {01},
number = 6,
pages = {34-37},
title = {Language Models for Procedural Content Generation},
volume = 12,
year = 2023
}%0 Journal Article
%1 AwiDoc2023
%A Awiszus, Maren
%A Dockhorn, Alexander
%A Hoover, Amy K.
%A Liapis, Antonios
%A Lucas, Simon M.
%A Eladhari, Mirjam Palosaari
%A Schrum, Jacob
%A Volz, Vanessa
%D 2023
%J Human-Game AI Interaction (Dagstuhl Seminar 22251)
%N 6
%P 34-37
%R 10.4230/DagRep.12.6.28
%T Language Models for Procedural Content Generation
%V 12 - BibTeXEndNoteBibSonomyDockhorn, A., Eberhardinger, M., Loiacono, D., Liebana, D. P., and Veltkamp, R. (2023)Pokegen, Human-Game AI Interaction (Dagstuhl Seminar 22251) 12, 39–42.
@article{DocEbe2023a,
author = {Dockhorn, Alexander and Eberhardinger, Manuel and Loiacono, Daniele and Liebana, Diego Perez and Veltkamp, Remco},
journal = {Human-Game AI Interaction (Dagstuhl Seminar 22251)},
keywords = {Pokegen},
month = {01},
number = 6,
pages = {39-42},
title = {Pokegen},
volume = 12,
year = 2023
}%0 Journal Article
%1 DocEbe2023a
%A Dockhorn, Alexander
%A Eberhardinger, Manuel
%A Loiacono, Daniele
%A Liebana, Diego Perez
%A Veltkamp, Remco
%D 2023
%J Human-Game AI Interaction (Dagstuhl Seminar 22251)
%N 6
%P 39-42
%R 10.4230/DagRep.12.6.28
%T Pokegen
%V 12 - BibTeXEndNoteBibSonomyAdhisantoso, Y. G., and Voges, J. (2023)Cross-check of M62859 Results on Updated CE Results for Annotation Data Indexing Using B-Tree, ISO/IEC JTC 1/SC 29/WG 8.
@article{AdhVog2023a,
author = {Adhisantoso, Yeremia Gunawan and Voges, Jan},
journal = {ISO/IEC JTC 1/SC 29/WG 8},
keywords = {M62859},
month = {04},
title = {Cross-check of M62859 Results on Updated CE Results for Annotation Data Indexing Using B-Tree},
year = 2023
}%0 Journal Article
%1 AdhVog2023a
%A Adhisantoso, Yeremia Gunawan
%A Voges, Jan
%D 2023
%J ISO/IEC JTC 1/SC 29/WG 8
%T Cross-check of M62859 Results on Updated CE Results for Annotation Data Indexing Using B-Tree - URLBibTeXEndNoteBibSonomyGrimm, E., Kuhnke, F., Gajdt, A., Ostermann, J., and Knoche, M. (2022)Accurate Quantification of Anthocyanin in Red Flesh Apples Using Digital Photography and Image Analysis, Horticulturae 8.
@article{GriKuh2022,
author = {Grimm, Eckhard and Kuhnke, Felix and Gajdt, Anna and Ostermann, J{ö}rn and Knoche, Moritz},
journal = {Horticulturae},
keywords = {Flesh},
month = {01},
number = 2,
title = {Accurate Quantification of Anthocyanin in Red Flesh Apples Using Digital Photography and Image Analysis},
volume = 8,
year = 2022
}%0 Journal Article
%1 GriKuh2022
%A Grimm, Eckhard
%A Kuhnke, Felix
%A Gajdt, Anna
%A Ostermann, J{ö}rn
%A Knoche, Moritz
%D 2022
%J Horticulturae
%N 2
%R https://doi.org/10.3390/horticulturae8020145
%T Accurate Quantification of Anthocyanin in Red Flesh Apples Using Digital Photography and Image Analysis
%U https://www.mdpi.com/2311-7524/8/2/145
%V 8 - BibTeXEndNoteBibSonomyReinders, C., Schubert, F., and Rosenhahn, B. (2022)ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing. In Arxiv Preprint.
@inproceedings{ReiSch2022,
author = {Reinders, Christoph and Schubert, Frederik and Rosenhahn, Bodo},
booktitle = {Arxiv Preprint},
keywords = {Feature},
month = {03},
title = {ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing},
year = 2022
}%0 Conference Paper
%1 ReiSch2022
%A Reinders, Christoph
%A Schubert, Frederik
%A Rosenhahn, Bodo
%B Arxiv Preprint
%D 2022
%T ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing - BibTeXEndNoteBibSonomyParker-Holder, J., Rajan, R., Song, X., Biedenkapp, A., Miao, Y., Eimer, T., Zhang, B., Nguyen, V., Calandra, R., Faust, A., Hutter, F., and Lindauer, M. (2022)Automated Reinforcement Learning (AutoRL): A Survey and Open Problems, Journal of Artificial Intelligence Research 74 (2022) 517–568.
@article{2201.03916,
author = {Parker-Holder, Jack and Rajan, Raghu and Song, Xingyou and Biedenkapp, André and Miao, Yingjie and Eimer, Theresa and Zhang, Baohe and Nguyen, Vu and Calandra, Roberto and Faust, Aleksandra and Hutter, Frank and Lindauer, Marius},
journal = {Journal of Artificial Intelligence Research 74 (2022)},
keywords = {AutoML},
pages = {517-568},
title = {Automated Reinforcement Learning (AutoRL): A Survey and Open Problems},
year = 2022
}%0 Journal Article
%1 2201.03916
%A Parker-Holder, Jack
%A Rajan, Raghu
%A Song, Xingyou
%A Biedenkapp, André
%A Miao, Yingjie
%A Eimer, Theresa
%A Zhang, Baohe
%A Nguyen, Vu
%A Calandra, Roberto
%A Faust, Aleksandra
%A Hutter, Frank
%A Lindauer, Marius
%D 2022
%J Journal of Artificial Intelligence Research 74 (2022)
%P 517-568
%R 10.1613/jair.1.13596
%T Automated Reinforcement Learning (AutoRL): A Survey and Open Problems - BibTeXEndNoteBibSonomyAlshomary, M., El Baff, R., Gurcke, T., and Wachsmuth, H. (2022)The Moral Debater: A Study on the Computational Generation of Morally Framed Arguments. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, pp. 8782–8797.
@inproceedings{alshomary2022moral,
author = {Alshomary, Milad and El Baff, Roxanne and Gurcke, Timon and Wachsmuth, Henning},
booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics},
keywords = {leibnizailab},
pages = {8782–8797},
title = {The Moral Debater: A Study on the Computational Generation of Morally Framed Arguments},
year = 2022
}%0 Conference Paper
%1 alshomary2022moral
%A Alshomary, Milad
%A El Baff, Roxanne
%A Gurcke, Timon
%A Wachsmuth, Henning
%B Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics
%D 2022
%P 8782–8797
%T The Moral Debater: A Study on the Computational Generation of Morally Framed Arguments - BibTeXEndNoteBibSonomyBiedenkapp, A., Speck, D., Sievers, S., Hutter, F., Lindauer, M., and Seipp, J. (2022)Learning Domain-Independent Policies for Open List Selection. In Proceedings of the 3rd ICAPS workshop on Bridging the Gap Between AI Planning and Reinforcement Learning (PRL), pp. 1–9.
@inproceedings{BieSpe2022,
author = {Biedenkapp, André and Speck, David and Sievers, Silvan and Hutter, Frank and Lindauer, Marius and Seipp, Jendrik},
booktitle = {Proceedings of the 3rd ICAPS workshop on Bridging the Gap Between AI Planning and Reinforcement Learning (PRL)},
keywords = {leibnizailab},
pages = {1-9},
title = {Learning Domain-Independent Policies for Open List Selection},
year = 2022
}%0 Conference Paper
%1 BieSpe2022
%A Biedenkapp, André
%A Speck, David
%A Sievers, Silvan
%A Hutter, Frank
%A Lindauer, Marius
%A Seipp, Jendrik
%B Proceedings of the 3rd ICAPS workshop on Bridging the Gap Between AI Planning and Reinforcement Learning (PRL)
%D 2022
%P 1-9
%T Learning Domain-Independent Policies for Open List Selection - URLBibTeXEndNoteBibSonomyBenjamins, C., Jankovic, A., Raponi, E., van der Blom, K., Lindauer, M., and Doerr, C. (2022)Towards Automated Design of Bayesian Optimization via Exploratory Landscape Analysis. In Workshop on Meta-Learning (MetaLearn 2022).
@inproceedings{benjamins2022towards,
author = {Benjamins, Carolin and Jankovic, Anja and Raponi, Elena and van der Blom, Koen and Lindauer, Marius and Doerr, Carola},
booktitle = {Workshop on Meta-Learning (MetaLearn 2022)},
keywords = {leibnizailab},
title = {Towards Automated Design of Bayesian Optimization via Exploratory Landscape Analysis},
year = 2022
}%0 Conference Paper
%1 benjamins2022towards
%A Benjamins, Carolin
%A Jankovic, Anja
%A Raponi, Elena
%A van der Blom, Koen
%A Lindauer, Marius
%A Doerr, Carola
%B Workshop on Meta-Learning (MetaLearn 2022)
%D 2022
%T Towards Automated Design of Bayesian Optimization via Exploratory Landscape Analysis
%U https://www.ai.uni-hannover.de/de/forschung/publikationen/publikationen-detailansicht?tx_t3luhpublications_publications%5Baction%5D=show&tx_t3luhpublications_publications%5Bcontroller%5D=Publication&tx_t3luhpublications_publications%5Bpublication%5D=7783&cHash=04b8ffd50e56727ae4181c8e2a2261f1 - URLBibTeXEndNoteBibSonomySass, R., Bergman, E., Biedenkapp, A., Hutter, F., and Lindauer, M. (2022)DeepCAVE: An Interactive Analysis Tool for Automated Machine Learning. In ICML Workshop on Adaptive Experimental Design and Active Learning in the Real World (ReALML), arXiv.
@inproceedings{https://doi.org/10.48550/arxiv.2206.03493,
author = {Sass, René and Bergman, Eddie and Biedenkapp, André and Hutter, Frank and Lindauer, Marius},
booktitle = {ICML Workshop on Adaptive Experimental Design and Active Learning in the Real World (ReALML)},
keywords = {leibnizailab},
publisher = {arXiv},
title = {DeepCAVE: An Interactive Analysis Tool for Automated Machine Learning},
year = 2022
}%0 Conference Paper
%1 https://doi.org/10.48550/arxiv.2206.03493
%A Sass, René
%A Bergman, Eddie
%A Biedenkapp, André
%A Hutter, Frank
%A Lindauer, Marius
%B ICML Workshop on Adaptive Experimental Design and Active Learning in the Real World (ReALML)
%D 2022
%I arXiv
%R 10.48550/ARXIV.2206.03493
%T DeepCAVE: An Interactive Analysis Tool for Automated Machine Learning
%U https://arxiv.org/abs/2206.03493 - BibTeXEndNoteBibSonomyStahl, M., Spliethöver, M., and Wachsmuth, H. (2022)To Prefer or to Choose? Generating Agency and Power Counterfactuals Jointly for Gender Bias Mitigation. In Proceedings of the Fifth Workshop on Natural Language Processing and Computational Social Science.
@inproceedings{Stahl_Spliethöver_Wachsmuth,
author = {Stahl, Maja and Spliethöver, Maximilian and Wachsmuth, Henning},
booktitle = {Proceedings of the Fifth Workshop on Natural Language Processing and Computational Social Science},
keywords = {leibnizailab},
title = {To Prefer or to Choose? Generating Agency and Power Counterfactuals Jointly for Gender Bias Mitigation},
year = 2022
}%0 Conference Paper
%1 Stahl_Spliethöver_Wachsmuth
%A Stahl, Maja
%A Spliethöver, Maximilian
%A Wachsmuth, Henning
%B Proceedings of the Fifth Workshop on Natural Language Processing and Computational Social Science
%D 2022
%T To Prefer or to Choose? Generating Agency and Power Counterfactuals Jointly for Gender Bias Mitigation - BibTeXEndNoteBibSonomyChen, W.-F., Chen, M.-H., Mudgal, G., and Wachsmuth, H. (2022)Analyzing Culture-Specific Argument Structures in Learner Essays. In Proceedings of the 9th Workshop on Argument Mining (ArgMining 2022), pp. 51–61.
@inproceedings{Chen_Chen_Mudgal_Wachsmuth_2022,
author = {Chen, Wei-Fan and Chen, Mei-Hua and Mudgal, Garima and Wachsmuth, Henning},
booktitle = {Proceedings of the 9th Workshop on Argument Mining (ArgMining 2022)},
keywords = {leibnizailab},
pages = {51–61},
title = {Analyzing Culture-Specific Argument Structures in Learner Essays},
year = 2022
}%0 Conference Paper
%1 Chen_Chen_Mudgal_Wachsmuth_2022
%A Chen, Wei-Fan
%A Chen, Mei-Hua
%A Mudgal, Garima
%A Wachsmuth, Henning
%B Proceedings of the 9th Workshop on Argument Mining (ArgMining 2022)
%D 2022
%P 51–61
%T Analyzing Culture-Specific Argument Structures in Learner Essays - BibTeXEndNoteBibSonomyAlshomary, M., and Stahl, M. (2022)Argument Novelty and Validity Assessment via Multitask and Transfer Learning. In Proceedings of the 9th Workshop on Argument Mining, pp. 111–114, International Conference on Computational Linguistics.
@inproceedings{Alshomary_Stahl_2022,
author = {Alshomary, Milad and Stahl, Maja},
booktitle = {Proceedings of the 9th Workshop on Argument Mining},
keywords = {leibnizailab},
pages = {111–114},
publisher = {International Conference on Computational Linguistics},
title = {Argument Novelty and Validity Assessment via Multitask and Transfer Learning},
year = 2022
}%0 Conference Paper
%1 Alshomary_Stahl_2022
%A Alshomary, Milad
%A Stahl, Maja
%B Proceedings of the 9th Workshop on Argument Mining
%D 2022
%I International Conference on Computational Linguistics
%P 111–114
%T Argument Novelty and Validity Assessment via Multitask and Transfer Learning - URLBibTeXEndNoteBibSonomyNayak, T., Sharma, S., Butala, Y., Dasgupta, K., Goyal, P., and Ganguly, N. (2022)A Generative Approach for Financial Causality Extraction. In Companion Proceedings of the Web Conference 2022, {ACM}.
@inproceedings{Nayak_2022,
author = {Nayak, Tapas and Sharma, Soumya and Butala, Yash and Dasgupta, Koustuv and Goyal, Pawan and Ganguly, Niloy},
booktitle = {Companion Proceedings of the Web Conference 2022},
keywords = {"sys:relevantfor:l3s"},
month = {04},
publisher = {{ACM}},
title = {A Generative Approach for Financial Causality Extraction},
year = 2022
}%0 Conference Paper
%1 Nayak_2022
%A Nayak, Tapas
%A Sharma, Soumya
%A Butala, Yash
%A Dasgupta, Koustuv
%A Goyal, Pawan
%A Ganguly, Niloy
%B Companion Proceedings of the Web Conference 2022
%D 2022
%I {ACM}
%R 10.1145/3487553.3524633
%T A Generative Approach for Financial Causality Extraction
%U https://doi.org/10.1145%2F3487553.3524633 - URLBibTeXEndNoteBibSonomyEimer, T., Biedenkapp, A., Hutter, F., and Lindauer, M. (2021)Self-Paced Context Evaluation for Contextual Reinforcement Learning. In Proceedings of the international conference on machine learning (ICML).
@inproceedings{EimBie2021a,
author = {Eimer, Theresa and Biedenkapp, Andre and Hutter, Frank and Lindauer, Marius},
booktitle = {Proceedings of the international conference on machine learning (ICML)},
keywords = {Reinforcement},
month = {07},
note = {To appear},
title = {Self-Paced Context Evaluation for Contextual Reinforcement Learning},
year = 2021
}%0 Conference Paper
%1 EimBie2021a
%A Eimer, Theresa
%A Biedenkapp, Andre
%A Hutter, Frank
%A Lindauer, Marius
%B Proceedings of the international conference on machine learning (ICML)
%D 2021
%T Self-Paced Context Evaluation for Contextual Reinforcement Learning
%U https://arxiv.org/abs/2106.05110 - AbstractURLBibTeXEndNoteBibSonomyZhao, B., van der Aa, H., Nguyen, T. T., Nguyen, Q. V. H., and Weidlich, M. (2021){EIRES}: Efficient Integration of Remote Data in Event Stream Processing. In Proceedings of the 2021 International Conference on Management of Data, {ACM}.To support reactive and predictive applications, complex event processing (CEP) systems detect patterns in event streams based on predefined queries. To determine the events that constitute a query match, their payload data may need to be assessed together with data from remote sources. Such dependencies are problematic, since waiting for remote data to be fetched interrupts the processing of the stream. Yet, without event selection based on remote data, the query state to maintain may grow exponentially. In either case, the performance of the CEP system degrades drastically. To tackle these issues, we present EIRES, a framework for efficient integration of static data from remote sources in CEP. It employs a cost-model to determine when to fetch certain remote data elements and how long to keep them in a cache for future use. EIRES combines strategies for (i) prefetching that queries remote data based on anticipated use and (ii) lazy evaluation that postpones the event selection based on remote data without interrupting the stream processing. Our experiments indicate that the combination of these strategies improves the latency of query evaluation by up to 3,725x for synthetic data and 47x for real-world data.
@inproceedings{Zhao_2021,
abstract = {To support reactive and predictive applications, complex event processing (CEP) systems detect patterns in event streams based on predefined queries. To determine the events that constitute a query match, their payload data may need to be assessed together with data from remote sources. Such dependencies are problematic, since waiting for remote data to be fetched interrupts the processing of the stream. Yet, without event selection based on remote data, the query state to maintain may grow exponentially. In either case, the performance of the CEP system degrades drastically. To tackle these issues, we present EIRES, a framework for efficient integration of static data from remote sources in CEP. It employs a cost-model to determine when to fetch certain remote data elements and how long to keep them in a cache for future use. EIRES combines strategies for (i) prefetching that queries remote data based on anticipated use and (ii) lazy evaluation that postpones the event selection based on remote data without interrupting the stream processing. Our experiments indicate that the combination of these strategies improves the latency of query evaluation by up to 3,725x for synthetic data and 47x for real-world data.},
author = {Zhao, Bo and van der Aa, Han and Nguyen, Thanh Tam and Nguyen, Quoc Viet Hung and Weidlich, Matthias},
booktitle = {Proceedings of the 2021 International Conference on Management of Data},
keywords = {l3s},
month = {06},
publisher = {{ACM}},
title = {{EIRES}: Efficient Integration of Remote Data in Event Stream Processing},
year = 2021
}%0 Conference Paper
%1 Zhao_2021
%A Zhao, Bo
%A van der Aa, Han
%A Nguyen, Thanh Tam
%A Nguyen, Quoc Viet Hung
%A Weidlich, Matthias
%B Proceedings of the 2021 International Conference on Management of Data
%D 2021
%I {ACM}
%R 10.1145/3448016.3457304
%T {EIRES}: Efficient Integration of Remote Data in Event Stream Processing
%U https://doi.org/10.1145%2F3448016.3457304
%X To support reactive and predictive applications, complex event processing (CEP) systems detect patterns in event streams based on predefined queries. To determine the events that constitute a query match, their payload data may need to be assessed together with data from remote sources. Such dependencies are problematic, since waiting for remote data to be fetched interrupts the processing of the stream. Yet, without event selection based on remote data, the query state to maintain may grow exponentially. In either case, the performance of the CEP system degrades drastically. To tackle these issues, we present EIRES, a framework for efficient integration of static data from remote sources in CEP. It employs a cost-model to determine when to fetch certain remote data elements and how long to keep them in a cache for future use. EIRES combines strategies for (i) prefetching that queries remote data based on anticipated use and (ii) lazy evaluation that postpones the event selection based on remote data without interrupting the stream processing. Our experiments indicate that the combination of these strategies improves the latency of query evaluation by up to 3,725x for synthetic data and 47x for real-world data. - AbstractURLBibTeXEndNoteBibSonomyHolzapfel, C., Sag, S., Graf-Schindler, J., Fischer, M., Drabsch, T., Illig, T., Grallert, H., Stecher, L., Strack, C., Caterson, I., Jebb, S., Hauner, H., and Baessler, A. (2021)Association between single nucleotide polymorphisms and weight reduction in behavioural interventions—a pooled analysis, Nutrients, MDPI 13.Knowledge of the association between single nucleotide polymorphisms (SNPs) and weight loss is limited. The aim was to analyse whether selected obesity-associated SNPs within the fat mass and obesity-associated (FTO), transmembrane protein 18 (TMEM18), melanocortin-4 receptor (MC4R), SEC16 homolog B (SEC16B), and brain-derived neurotrophic factor (BDNF) gene are associated with anthropometric changes during behavioural intervention for weight loss. genetic and anthropometric data from 576 individuals with overweight and obesity from four lifestyle interventions were obtained. A genetic predisposition score (GPS) was calculated. Our results show that study participants had a mean age of 48.2 ± 12.6 years and a mean baseline body mass index of 33.9 ± 6.4 kg/m2. Mean weight reduction after 12 months was −7.7 ± 10.9 kg. After 12 months of intervention, the MC4R SNPs rs571312 and rs17782313 were significantly associated with a greater decrease in body weight and BMI (p = 0.012, p = 0.011, respectively). The investigated SNPs within the other four genetic loci showed no statistically significant association with changes in anthropometric parameters. The GPS showed no statistically significant association with weight reduction. In conclusion there was no consistent evidence for statistically significant associations of SNPs with anthropometric changes during a behavioural intervention. It seems that other factors play a more significant in weight management than the investigated SNPs.
@article{holzapfel2021association,
abstract = {Knowledge of the association between single nucleotide polymorphisms (SNPs) and weight loss is limited. The aim was to analyse whether selected obesity-associated SNPs within the fat mass and obesity-associated (FTO), transmembrane protein 18 (TMEM18), melanocortin-4 receptor (MC4R), SEC16 homolog B (SEC16B), and brain-derived neurotrophic factor (BDNF) gene are associated with anthropometric changes during behavioural intervention for weight loss. genetic and anthropometric data from 576 individuals with overweight and obesity from four lifestyle interventions were obtained. A genetic predisposition score (GPS) was calculated. Our results show that study participants had a mean age of 48.2 ± 12.6 years and a mean baseline body mass index of 33.9 ± 6.4 kg/m2. Mean weight reduction after 12 months was −7.7 ± 10.9 kg. After 12 months of intervention, the MC4R SNPs rs571312 and rs17782313 were significantly associated with a greater decrease in body weight and BMI (p = 0.012, p = 0.011, respectively). The investigated SNPs within the other four genetic loci showed no statistically significant association with changes in anthropometric parameters. The GPS showed no statistically significant association with weight reduction. In conclusion there was no consistent evidence for statistically significant associations of SNPs with anthropometric changes during a behavioural intervention. It seems that other factors play a more significant in weight management than the investigated SNPs.},
author = {Holzapfel, C and Sag, S and Graf-Schindler, J and Fischer, M and Drabsch, T and Illig, T and Grallert, H and Stecher, L and Strack, C and Caterson, ID and Jebb, SA and Hauner, H and Baessler, A},
journal = {Nutrients},
keywords = {l3s},
number = 3,
publisher = {MDPI},
title = {Association between single nucleotide polymorphisms and weight reduction in behavioural interventions—a pooled analysis},
type = {Publication},
volume = 13,
year = 2021
}%0 Journal Article
%1 holzapfel2021association
%A Holzapfel, C
%A Sag, S
%A Graf-Schindler, J
%A Fischer, M
%A Drabsch, T
%A Illig, T
%A Grallert, H
%A Stecher, L
%A Strack, C
%A Caterson, ID
%A Jebb, SA
%A Hauner, H
%A Baessler, A
%D 2021
%I MDPI
%J Nutrients
%N 3
%R 10.3390/nu13030819
%T Association between single nucleotide polymorphisms and weight reduction in behavioural interventions—a pooled analysis
%U https://ora.ox.ac.uk/objects/uuid:98987391-ba79-4686-a819-5fbe2a79ff45
%V 13
%X Knowledge of the association between single nucleotide polymorphisms (SNPs) and weight loss is limited. The aim was to analyse whether selected obesity-associated SNPs within the fat mass and obesity-associated (FTO), transmembrane protein 18 (TMEM18), melanocortin-4 receptor (MC4R), SEC16 homolog B (SEC16B), and brain-derived neurotrophic factor (BDNF) gene are associated with anthropometric changes during behavioural intervention for weight loss. genetic and anthropometric data from 576 individuals with overweight and obesity from four lifestyle interventions were obtained. A genetic predisposition score (GPS) was calculated. Our results show that study participants had a mean age of 48.2 ± 12.6 years and a mean baseline body mass index of 33.9 ± 6.4 kg/m2. Mean weight reduction after 12 months was −7.7 ± 10.9 kg. After 12 months of intervention, the MC4R SNPs rs571312 and rs17782313 were significantly associated with a greater decrease in body weight and BMI (p = 0.012, p = 0.011, respectively). The investigated SNPs within the other four genetic loci showed no statistically significant association with changes in anthropometric parameters. The GPS showed no statistically significant association with weight reduction. In conclusion there was no consistent evidence for statistically significant associations of SNPs with anthropometric changes during a behavioural intervention. It seems that other factors play a more significant in weight management than the investigated SNPs. - BibTeXEndNoteBibSonomyPestel-Schiller, U., Hu, K., Gritzner, D., and Ostermann, J. (2021)Determination of Relevant Hyperspectral Bands Using a Spectrally Constrained CNN. In 11th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS), Paper 15.
@inproceedings{PesHu2021a,
author = {Pestel-Schiller, Ulrike and Hu, Kai and Gritzner, Daniel and Ostermann, J{ö}rn},
booktitle = {11th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS), Paper 15},
keywords = {Relevant},
month = {03},
title = {Determination of Relevant Hyperspectral Bands Using a Spectrally Constrained CNN},
year = 2021
}%0 Conference Paper
%1 PesHu2021a
%A Pestel-Schiller, Ulrike
%A Hu, Kai
%A Gritzner, Daniel
%A Ostermann, J{ö}rn
%B 11th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS), Paper 15
%D 2021
%T Determination of Relevant Hyperspectral Bands Using a Spectrally Constrained CNN - AbstractURLBibTeXEndNoteBibSonomyWu, W., Li, B., Luo, C., and Nejdl, W. (2021)Hashing-Accelerated Graph Neural Networks for Link Prediction. In .Networks are ubiquitous in the real world. Link prediction, as one of the key problems for network-structured data, aims to predict whether there exists a link between two nodes. The traditional approaches are based on the explicit similarity computation between the compact node representation by embedding each node into a low-dimensional space. In order to efficiently handle the intensive similarity computation in link prediction, the hashing technique has been successfully used to produce the node representation in the Hamming space. However, the hashing-based link prediction algorithms face accuracy loss from the randomized hashing techniques or inefficiency from the learning to hash techniques in the embedding process. Currently, the Graph Neural Network (GNN) framework has been widely applied to the graph-related tasks in an end-to-end manner, but it commonly requires substantial computational resources and memory costs due to massive parameter learning, which makes the GNN-based algorithms impractical without the help of a powerful workhorse. In this paper, we propose a simple and effective model called #GNN, which balances the trade-off between accuracy and efficiency. #GNN is able to efficiently acquire node representation in the Hamming space for link prediction by exploiting the randomized hashing technique to implement message passing and capture high-order proximity in the GNN framework. Furthermore, we characterize the discriminative power of #GNN in probability. The extensive experimental results demonstrate that the proposed #GNN algorithm achieves accuracy comparable to the learning-based algorithms and outperforms the randomized algorithm, while running significantly faster than the learning-based algorithms. Also, the proposed algorithm shows excellent scalability on a large-scale network with the limited resources.
@conference{wu2021hashingaccelerated,
abstract = {Networks are ubiquitous in the real world. Link prediction, as one of the key problems for network-structured data, aims to predict whether there exists a link between two nodes. The traditional approaches are based on the explicit similarity computation between the compact node representation by embedding each node into a low-dimensional space. In order to efficiently handle the intensive similarity computation in link prediction, the hashing technique has been successfully used to produce the node representation in the Hamming space. However, the hashing-based link prediction algorithms face accuracy loss from the randomized hashing techniques or inefficiency from the learning to hash techniques in the embedding process. Currently, the Graph Neural Network (GNN) framework has been widely applied to the graph-related tasks in an end-to-end manner, but it commonly requires substantial computational resources and memory costs due to massive parameter learning, which makes the GNN-based algorithms impractical without the help of a powerful workhorse. In this paper, we propose a simple and effective model called #GNN, which balances the trade-off between accuracy and efficiency. #GNN is able to efficiently acquire node representation in the Hamming space for link prediction by exploiting the randomized hashing technique to implement message passing and capture high-order proximity in the GNN framework. Furthermore, we characterize the discriminative power of #GNN in probability. The extensive experimental results demonstrate that the proposed #GNN algorithm achieves accuracy comparable to the learning-based algorithms and outperforms the randomized algorithm, while running significantly faster than the learning-based algorithms. Also, the proposed algorithm shows excellent scalability on a large-scale network with the limited resources.},
author = {Wu, Wei and Li, Bin and Luo, Chuan and Nejdl, Wolfgang},
keywords = {l3s},
note = {cite arxiv:2105.14280},
title = {Hashing-Accelerated Graph Neural Networks for Link Prediction},
year = 2021
}%0 Generic
%1 wu2021hashingaccelerated
%A Wu, Wei
%A Li, Bin
%A Luo, Chuan
%A Nejdl, Wolfgang
%D 2021
%R 10.1145/3442381.3449884
%T Hashing-Accelerated Graph Neural Networks for Link Prediction
%U http://arxiv.org/abs/2105.14280
%X Networks are ubiquitous in the real world. Link prediction, as one of the key problems for network-structured data, aims to predict whether there exists a link between two nodes. The traditional approaches are based on the explicit similarity computation between the compact node representation by embedding each node into a low-dimensional space. In order to efficiently handle the intensive similarity computation in link prediction, the hashing technique has been successfully used to produce the node representation in the Hamming space. However, the hashing-based link prediction algorithms face accuracy loss from the randomized hashing techniques or inefficiency from the learning to hash techniques in the embedding process. Currently, the Graph Neural Network (GNN) framework has been widely applied to the graph-related tasks in an end-to-end manner, but it commonly requires substantial computational resources and memory costs due to massive parameter learning, which makes the GNN-based algorithms impractical without the help of a powerful workhorse. In this paper, we propose a simple and effective model called #GNN, which balances the trade-off between accuracy and efficiency. #GNN is able to efficiently acquire node representation in the Hamming space for link prediction by exploiting the randomized hashing technique to implement message passing and capture high-order proximity in the GNN framework. Furthermore, we characterize the discriminative power of #GNN in probability. The extensive experimental results demonstrate that the proposed #GNN algorithm achieves accuracy comparable to the learning-based algorithms and outperforms the randomized algorithm, while running significantly faster than the learning-based algorithms. Also, the proposed algorithm shows excellent scalability on a large-scale network with the limited resources. - BibTeXEndNoteBibSonomyBenjak, M., Meuel, H., Laude, T., and Ostermann, J. (2021)Enhanced Machine Learning-based Inter Coding for VVC. In 2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) (ICAIIC 2021).
@inproceedings{BenMeu2021,
author = {Benjak, Martin and Meuel, Holger and Laude, Thorsten and Ostermann, J{ö}rn},
booktitle = {2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) (ICAIIC 2021)},
keywords = {for},
month = {04},
note = {accepted for publication},
title = {Enhanced Machine Learning-based Inter Coding for VVC},
year = 2021
}%0 Conference Paper
%1 BenMeu2021
%A Benjak, Martin
%A Meuel, Holger
%A Laude, Thorsten
%A Ostermann, J{ö}rn
%B 2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) (ICAIIC 2021)
%D 2021
%T Enhanced Machine Learning-based Inter Coding for VVC - URLBibTeXEndNoteBibSonomySchubert, F., Awiszus, M., and Rosenhahn, B. (2021)TOAD-GAN: a Flexible Framework for Few-Shot Level Generation in Token-Based Games, IEEE Transactions on Games.
@article{SchAwi2021,
author = {Schubert, Frederik and Awiszus, Maren and Rosenhahn, Bodo},
journal = {IEEE Transactions on Games},
keywords = {TOAD-GAN},
month = {03},
note = {10 pages, 14 figures.},
title = {TOAD-GAN: a Flexible Framework for Few-Shot Level Generation in Token-Based Games},
year = 2021
}%0 Journal Article
%1 SchAwi2021
%A Schubert, Frederik
%A Awiszus, Maren
%A Rosenhahn, Bodo
%D 2021
%J IEEE Transactions on Games
%R 10.1109/TG.2021.3069833
%T TOAD-GAN: a Flexible Framework for Few-Shot Level Generation in Token-Based Games
%U https://ieeexplore.ieee.org/document/9390320 - URLBibTeXEndNoteBibSonomyHutter, F., Fuks, L., Lindauer, M., and Awad, N. (2021)Method, device and computer program for producing a strategy for a robot.
@article{HutFuk2021,
author = {Hutter, Frank and Fuks, Lior and Lindauer, Marius and Awad, Noor},
keywords = {strategy},
title = {Method, device and computer program for producing a strategy for a robot},
year = 2021
}%0 Journal Article
%1 HutFuk2021
%A Hutter, Frank
%A Fuks, Lior
%A Lindauer, Marius
%A Awad, Noor
%D 2021
%T Method, device and computer program for producing a strategy for a robot
%U https://patentimages.storage.googleapis.com/8b/43/4d/a2876517a8f945/US20210008718A1.pdf - BibTeXEndNoteBibSonomyKluger, F., Ackermann, H., Brachmann, E., Yang, M. Y., and Rosenhahn, B. (2021)Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images. In CVPR.
@inproceedings{KluAck2021a,
author = {Kluger, Florian and Ackermann, Hanno and Brachmann, Eric and Yang, Michael Ying and Rosenhahn, Bodo},
booktitle = {CVPR},
keywords = {Cuboids},
month = {06},
title = {Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images},
year = 2021
}%0 Conference Paper
%1 KluAck2021a
%A Kluger, Florian
%A Ackermann, Hanno
%A Brachmann, Eric
%A Yang, Michael Ying
%A Rosenhahn, Bodo
%B CVPR
%D 2021
%T Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images - URLBibTeXEndNoteBibSonomyGuerrero-Viu, J., Hauns, S., Izquierdo, S., Miotto, G., Schrodi, S., Biedenkapp, A., Elsken, T., Deng, D., Lindauer, M., and Hutter, F. (2021)Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization. In Proceedings of the international workshop on Automated Machine Learning (AutoML) at ICML’21.
@inproceedings{GueHau2021a,
author = {Guerrero-Viu, Julia and Hauns, Sven and Izquierdo, Sergio and Miotto, Guilherme and Schrodi, Simon and Biedenkapp, Andre and Elsken, Thomas and Deng, Difan and Lindauer, Marius and Hutter, Frank},
booktitle = {Proceedings of the international workshop on Automated Machine Learning (AutoML) at ICML'21},
keywords = {Optimization},
month = {07},
title = {Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization},
year = 2021
}%0 Conference Paper
%1 GueHau2021a
%A Guerrero-Viu, Julia
%A Hauns, Sven
%A Izquierdo, Sergio
%A Miotto, Guilherme
%A Schrodi, Simon
%A Biedenkapp, Andre
%A Elsken, Thomas
%A Deng, Difan
%A Lindauer, Marius
%A Hutter, Frank
%B Proceedings of the international workshop on Automated Machine Learning (AutoML) at ICML'21
%D 2021
%T Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization
%U https://arxiv.org/abs/2105.01015 - URLBibTeXEndNoteBibSonomyNarisetti, N., Henke, M., Seiler, C., Junker, A., Ostermann, J., Altmann, T., and Gladilin, E. (2021)Fully-automated root image analysis (faRIA), Scientific Reports 11.
@article{NarHen2021,
author = {Narisetti, Narendra and Henke, Michael and Seiler, Christiane and Junker, Astrid and Ostermann, J{ö}rn and Altmann, Thomas and Gladilin, Evgeny},
journal = {Scientific Reports},
keywords = {analysis},
month = {08},
title = {Fully-automated root image analysis (faRIA)},
volume = 11,
year = 2021
}%0 Journal Article
%1 NarHen2021
%A Narisetti, Narendra
%A Henke, Michael
%A Seiler, Christiane
%A Junker, Astrid
%A Ostermann, J{ö}rn
%A Altmann, Thomas
%A Gladilin, Evgeny
%D 2021
%J Scientific Reports
%R https://doi.org/10.1038/s41598-021-95480-y
%T Fully-automated root image analysis (faRIA)
%U https://www.nature.com/articles/s41598-021-95480-y
%V 11 - URLBibTeXEndNoteBibSonomySchubert, F., Eimer, T., Rosenhahn, B., and Lindauer, M. (2021)Towards Automatic Risk Adaption in Distributional Reinforcement Learning. In Reinforcement Learning for Real Life (RL4RealLife) Workshop in the 38th International Conference on Machine Learning (ICML).
@inproceedings{SchEim2021b,
author = {Schubert, Frederik and Eimer, Theresa and Rosenhahn, Bodo and Lindauer, Marius},
booktitle = {Reinforcement Learning for Real Life (RL4RealLife) Workshop in the 38th International Conference on Machine Learning (ICML)},
keywords = {Reinforcement},
month = {07},
title = {Towards Automatic Risk Adaption in Distributional Reinforcement Learning},
year = 2021
}%0 Conference Paper
%1 SchEim2021b
%A Schubert, Frederik
%A Eimer, Theresa
%A Rosenhahn, Bodo
%A Lindauer, Marius
%B Reinforcement Learning for Real Life (RL4RealLife) Workshop in the 38th International Conference on Machine Learning (ICML)
%D 2021
%T Towards Automatic Risk Adaption in Distributional Reinforcement Learning
%U https://arxiv.org/abs/2106.06317 - BibTeXEndNoteBibSonomyRumberg, L., Ehlert, H., L{ü}dtke, U., and Ostermann, J. (2021)Age-Invariant Training for End-to-End Child Speech Recognition using Adversarial Multi-Task Learning. In Proceedings INTERSPEECH 2021 -- 22th Annual Conference of the International Speech Communication Association.
@inproceedings{RumEhl2021,
author = {Rumberg, Lars and Ehlert, Hanna and L{ü}dtke, Ulrike and Ostermann, J{ö}rn},
booktitle = {Proceedings INTERSPEECH 2021 -- 22th Annual Conference of the International Speech Communication Association},
keywords = {Recognition},
month = {08},
title = {Age-Invariant Training for End-to-End Child Speech Recognition using Adversarial Multi-Task Learning},
year = 2021
}%0 Conference Paper
%1 RumEhl2021
%A Rumberg, Lars
%A Ehlert, Hanna
%A L{ü}dtke, Ulrike
%A Ostermann, J{ö}rn
%B Proceedings INTERSPEECH 2021 -- 22th Annual Conference of the International Speech Communication Association
%D 2021
%T Age-Invariant Training for End-to-End Child Speech Recognition using Adversarial Multi-Task Learning - BibTeXEndNoteBibSonomyBenjamins, C., Eimer, T., Schubert, F., Biedenkapp, A., Rosenhahn, B., Hutter, F., and Lindauer, M. (2021)CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning. In NeurIPS 2021 Workshop on Ecological Theory of Reinforcement Learning.
@inproceedings{BenEim2021a,
author = {Benjamins, Carolin and Eimer, Theresa and Schubert, Frederik and Biedenkapp, André and Rosenhahn, Bodo and Hutter, Frank and Lindauer, Marius},
booktitle = {NeurIPS 2021 Workshop on Ecological Theory of Reinforcement Learning},
keywords = {Reinforcement},
month = 12,
title = {CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning},
year = 2021
}%0 Conference Paper
%1 BenEim2021a
%A Benjamins, Carolin
%A Eimer, Theresa
%A Schubert, Frederik
%A Biedenkapp, André
%A Rosenhahn, Bodo
%A Hutter, Frank
%A Lindauer, Marius
%B NeurIPS 2021 Workshop on Ecological Theory of Reinforcement Learning
%D 2021
%T CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning - URLBibTeXEndNoteBibSonomyHachmann, H., Kr{ü}ger, B., Rosenhahn, B., and Nogueira, W. (2021)Localization of Cochlear Implant Electrodes from Cone Beam Computed Tomography using Particle Belief Propagation. In International Symposium on Biomedical Imaging, ISBI.
@inproceedings{HacKru2021a,
author = {Hachmann, Hendrik and Kr{ü}ger, Benjamin and Rosenhahn, Bodo and Nogueira, Waldo},
booktitle = {International Symposium on Biomedical Imaging, ISBI},
keywords = {Computed},
month = {04},
title = {Localization of Cochlear Implant Electrodes from Cone Beam Computed Tomography using Particle Belief Propagation},
year = 2021
}%0 Conference Paper
%1 HacKru2021a
%A Hachmann, Hendrik
%A Kr{ü}ger, Benjamin
%A Rosenhahn, Bodo
%A Nogueira, Waldo
%B International Symposium on Biomedical Imaging, ISBI
%D 2021
%T Localization of Cochlear Implant Electrodes from Cone Beam Computed Tomography using Particle Belief Propagation
%U https://arxiv.org/abs/2103.10434 - URLBibTeXEndNoteBibSonomyEggensperger, K., M{ü}ller, P., Mallik, N., Feurer, M., Sass, R., Klein, A., Awad, N., Lindauer, M., and Hutter, F. (2021)HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO. In Proceedings of the international conference on Neural Information Processing Systems (NeurIPS) (Datasets and Benchmarks Track).
@inproceedings{EggMue2021,
author = {Eggensperger, Katharina and M{ü}ller, Philipp and Mallik, Neeratyoy and Feurer, Matthias and Sass, René and Klein, Aaron and Awad, Noor and Lindauer, Marius and Hutter, Frank},
booktitle = {Proceedings of the international conference on Neural Information Processing Systems (NeurIPS) (Datasets and Benchmarks Track)},
keywords = {HPOBench},
month = 12,
title = {HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO},
year = 2021
}%0 Conference Paper
%1 EggMue2021
%A Eggensperger, Katharina
%A M{ü}ller, Philipp
%A Mallik, Neeratyoy
%A Feurer, Matthias
%A Sass, René
%A Klein, Aaron
%A Awad, Noor
%A Lindauer, Marius
%A Hutter, Frank
%B Proceedings of the international conference on Neural Information Processing Systems (NeurIPS) (Datasets and Benchmarks Track)
%D 2021
%T HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO
%U https://arxiv.org/abs/2109.06716 - URLBibTeXEndNoteBibSonomyKnura, M., Kluger, F., Zahtila, M., Schiewe, J., Rosenhahn, B., and Burghardt, D. (2021)Using Object Detection on Social Media Images for Urban Bicycle Infrastructure Planning: A Case Study of Dresden, ISPRS International Journal of Geo-Information.
@article{KnuKlu2021,
author = {Knura, Martin and Kluger, Florian and Zahtila, Moris and Schiewe, Jochen and Rosenhahn, Bodo and Burghardt, Dirk},
journal = {ISPRS International Journal of Geo-Information},
keywords = {Bicycle},
month = 10,
title = {Using Object Detection on Social Media Images for Urban Bicycle Infrastructure Planning: A Case Study of Dresden},
year = 2021
}%0 Journal Article
%1 KnuKlu2021
%A Knura, Martin
%A Kluger, Florian
%A Zahtila, Moris
%A Schiewe, Jochen
%A Rosenhahn, Bodo
%A Burghardt, Dirk
%D 2021
%J ISPRS International Journal of Geo-Information
%R 10.3390/ijgi10110733
%T Using Object Detection on Social Media Images for Urban Bicycle Infrastructure Planning: A Case Study of Dresden
%U https://doi.org/10.3390%2Fijgi10110733 - URLBibTeXEndNoteBibSonomyLindauer, M., Eggensperger, K., Feurer, M., Biedenkapp, A., Deng, D., Benjamins, C., Sass, R., and Hutter, F. (2021)SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization. In ArXiv: 2109.09831.
@inproceedings{LinEgg2021,
author = {Lindauer, Marius and Eggensperger, Katharina and Feurer, Matthias and Biedenkapp, André and Deng, Difan and Benjamins, Carolin and Sass, René and Hutter, Frank},
booktitle = {ArXiv: 2109.09831},
keywords = {SMAC3},
title = {SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization},
year = 2021
}%0 Conference Paper
%1 LinEgg2021
%A Lindauer, Marius
%A Eggensperger, Katharina
%A Feurer, Matthias
%A Biedenkapp, André
%A Deng, Difan
%A Benjamins, Carolin
%A Sass, René
%A Hutter, Frank
%B ArXiv: 2109.09831
%D 2021
%T SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization
%U https://arxiv.org/abs/2109.09831 - URLBibTeXEndNoteBibSonomyHornakova*, A., Kaiser*, T., Rolinek, M., Rosenhahn, B., Swoboda, P., Henschel, R., and equal contribution), (*. (2021)Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths. In International Conference on Computer Vision (ICCV).
@inproceedings{HorKai2021,
author = {Hornakova*, Andrea and Kaiser*, Timo and Rolinek, Michal and Rosenhahn, Bodo and Swoboda, Paul and Henschel, Roberto and equal contribution), (*},
booktitle = {International Conference on Computer Vision (ICCV)},
keywords = {Scalable},
month = 10,
title = {Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths},
year = 2021
}%0 Conference Paper
%1 HorKai2021
%A Hornakova*, Andrea
%A Kaiser*, Timo
%A Rolinek, Michal
%A Rosenhahn, Bodo
%A Swoboda, Paul
%A Henschel, Roberto
%A equal contribution), (*
%B International Conference on Computer Vision (ICCV)
%D 2021
%T Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths
%U https://arxiv.org/abs/2108.10606 - URLBibTeXEndNoteBibSonomyEimer, T., Biedenkapp, A., Reimer, M., Adriaensen, S., Hutter, F., and Lindauer, M. (2021)DACBench: A Benchmark Library for Dynamic Algorithm Configuration. In Proceedings of the international joint conference on artificial intelligence (IJCAI).
@inproceedings{EimBie2021b,
author = {Eimer, Theresa and Biedenkapp, André and Reimer, Maximilian and Adriaensen, Steven and Hutter, Frank and Lindauer, Marius},
booktitle = {Proceedings of the international joint conference on artificial intelligence (IJCAI)},
keywords = {leibnizailab},
month = {08},
note = {To appear.},
title = {DACBench: A Benchmark Library for Dynamic Algorithm Configuration},
year = 2021
}%0 Conference Paper
%1 EimBie2021b
%A Eimer, Theresa
%A Biedenkapp, André
%A Reimer, Maximilian
%A Adriaensen, Steven
%A Hutter, Frank
%A Lindauer, Marius
%B Proceedings of the international joint conference on artificial intelligence (IJCAI)
%D 2021
%T DACBench: A Benchmark Library for Dynamic Algorithm Configuration
%U https://arxiv.org/abs/2105.08541 - URLBibTeXEndNoteBibSonomyOstermann, J., and Hinrichs, R. (2020)Links und rechts verbinden, Unimagazin.
@article{OstHin2020a,
author = {Ostermann, J{ö}rn and Hinrichs, Reemt},
journal = {Unimagazin},
keywords = {und},
month = {06},
number = 1,
title = {Links und rechts verbinden},
year = 2020
}%0 Journal Article
%1 OstHin2020a
%A Ostermann, J{ö}rn
%A Hinrichs, Reemt
%D 2020
%J Unimagazin
%N 1
%T Links und rechts verbinden
%U https://anyflip.com/cjox/dool/ - BibTeXEndNoteBibSonomySamayoa, Y., and Ostermann, J. (2020)Parameter Selection for a Video Communication System based on HEVC and Channel Coding. In IEEE Latin-American Conference on Communications (LATINCOM 2020), p. 5.
@inproceedings{SamOst2020,
author = {Samayoa, Yasser and Ostermann, J{ö}rn},
booktitle = {IEEE Latin-American Conference on Communications (LATINCOM 2020)},
keywords = {System},
month = 11,
pages = 5,
title = {Parameter Selection for a Video Communication System based on HEVC and Channel Coding},
year = 2020
}%0 Conference Paper
%1 SamOst2020
%A Samayoa, Yasser
%A Ostermann, J{ö}rn
%B IEEE Latin-American Conference on Communications (LATINCOM 2020)
%D 2020
%P 5
%T Parameter Selection for a Video Communication System based on HEVC and Channel Coding - URLBibTeXEndNoteBibSonomyAwiszus, M., Schubert, F., and Rosenhahn, B. (2020)TOAD-GAN: Coherent Style Level Generation from a Single Example. In AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment Best Student Paper Award.
@inproceedings{AwiSch2020,
author = {Awiszus, Maren and Schubert, Frederik and Rosenhahn, Bodo},
booktitle = {AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment Best Student Paper Award},
keywords = {TOAD-GAN},
month = 10,
note = {7 pages, 7 figures.},
title = {TOAD-GAN: Coherent Style Level Generation from a Single Example},
year = 2020
}%0 Conference Paper
%1 AwiSch2020
%A Awiszus, Maren
%A Schubert, Frederik
%A Rosenhahn, Bodo
%B AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment Best Student Paper Award
%D 2020
%T TOAD-GAN: Coherent Style Level Generation from a Single Example
%U /brokenurl#AAAI, github, arxiv, Award - BibTeXEndNoteBibSonomyJ{ü}rgens, H., Hinrichs, R., and Ostermann, J. (2020)Recognizing Guitar Effects and Their Parameter Settings. In Proceedings of the DAFx2020 (Vol I).
@inproceedings{JueHin2020,
author = {J{ü}rgens, Henrik and Hinrichs, Reemt and Ostermann, J{ö}rn},
booktitle = {Proceedings of the DAFx2020 (Vol I)},
keywords = {Settings},
title = {Recognizing Guitar Effects and Their Parameter Settings},
year = 2020
}%0 Conference Paper
%1 JueHin2020
%A J{ü}rgens, Henrik
%A Hinrichs, Reemt
%A Ostermann, J{ö}rn
%B Proceedings of the DAFx2020 (Vol I)
%D 2020
%T Recognizing Guitar Effects and Their Parameter Settings - URLBibTeXEndNoteBibSonomyGra{{\"s}}hof, S., Ackermann, H., Brandt, S., and Ostermann, J. (2020)Multilinear Modelling of Faces and Expressions, Transactions on Pattern Analysis and Machine Intelligence (TPAMI).
@article{GraAck2020,
author = {Gra{{\"s}}hof, Stella and Ackermann, Hanno and Brandt, Sami and Ostermann, J{ö}rn},
journal = {Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
keywords = {Faces},
month = {04},
note = {early access},
title = {Multilinear Modelling of Faces and Expressions},
year = 2020
}%0 Journal Article
%1 GraAck2020
%A Gra{{\"s}}hof, Stella
%A Ackermann, Hanno
%A Brandt, Sami
%A Ostermann, J{ö}rn
%D 2020
%J Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
%T Multilinear Modelling of Faces and Expressions
%U https://ieeexplore.ieee.org/document/9067086 - URLBibTeXEndNoteBibSonomyHu, T., Iosifidis, V., Liao, W., Zhang, H., Yang, M. Y., Ntoutsi, E., and Rosenhahn, B. (2020)FairNN - Conjoint Learning of Fair Representations for Fair Decisions.. In Discovery Science, pp. 581–595, Springer International Publishing.
@incollection{Hu_2020,
author = {Hu, Tongxin and Iosifidis, Vasileios and Liao, Wentong and Zhang, Hang and Yang, Michael Ying and Ntoutsi, Eirini and Rosenhahn, Bodo},
booktitle = {Discovery Science},
keywords = {l3s},
pages = {581-595},
publisher = {Springer International Publishing},
series = {Lecture Notes in Computer Science},
title = {FairNN - Conjoint Learning of Fair Representations for Fair Decisions.},
type = {Publication},
volume = 12323,
year = 2020
}%0 Book Section
%1 Hu_2020
%A Hu, Tongxin
%A Iosifidis, Vasileios
%A Liao, Wentong
%A Zhang, Hang
%A Yang, Michael Ying
%A Ntoutsi, Eirini
%A Rosenhahn, Bodo
%B Discovery Science
%D 2020
%I Springer International Publishing
%P 581-595
%R 10.1007/978-3-030-61527-7_38
%T FairNN - Conjoint Learning of Fair Representations for Fair Decisions.
%U https://doi.org/10.1007%2F978-3-030-61527-7_38
%V 12323 - BibTeXEndNoteBibSonomyHu, T., Iosifidis, V., Wentong, L., Hang, Z., Yang, M. Y., Ntoutsi, E., and Rosenhahn, B. (2020)FairNN - Conjoint Learning of Fair Representations for Fair Decisions. In 23rd International Conference on Discovery Science.
@inproceedings{HuIos2020,
author = {Hu, Tongxin and Iosifidis, Vasileios and Wentong, Liao and Hang, Zhang and Yang, Michael Ying and Ntoutsi, Eirini and Rosenhahn, Bodo},
booktitle = {23rd International Conference on Discovery Science},
keywords = {for},
month = 10,
note = {Code available: https://github.com/wtliao/FairNN},
title = {FairNN - Conjoint Learning of Fair Representations for Fair Decisions},
year = 2020
}%0 Conference Paper
%1 HuIos2020
%A Hu, Tongxin
%A Iosifidis, Vasileios
%A Wentong, Liao
%A Hang, Zhang
%A Yang, Michael Ying
%A Ntoutsi, Eirini
%A Rosenhahn, Bodo
%B 23rd International Conference on Discovery Science
%D 2020
%T FairNN - Conjoint Learning of Fair Representations for Fair Decisions