Michaela Regneri
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Michaela Regneri has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
Alexis Palmer
3 shared publicationsBernt Schiele
Max Planck Institute for Informatics
3 shared publicationsManfred Pinkal
Saarland University
3 shared publicationsDiane King
2 shared publicationsMarcus Rohrbach
Max Planck Institute for Informatics, Saarbrücken, Germany
2 shared publicationsMykhaylo Andriluka
Max Planck Institute for Informatics
2 shared publications
Latest Publications
- 8 September 2026
- Published by Springer Nature
- p. 165-182
The Effect of Quantization on Memorization in Large Language Models
- 8 September 2026
- Published by Springer Nature
- p. 165-182
The Effect of Quantization on Memorization in Large Language Models
- Open Access
- 1 January 2016
- Published by Association for Computational Linguistics (ACL)
- p. 163-168
new/s/leak – Information Extraction and Visualization for Investigative Data Journalists
- 1 January 2016
- Published by Association for Computational Linguistics (ACL)
- p. 163-168
Open Accessnew/s/leak – Information Extraction and Visualization for Investigative Data Journalists
- 31 December 2015
- Published by Walter de Gruyter GmbH
- p. 173-186
Automatically Evaluating Atypical Language in Narratives by Children with Autistic Spectrum Disorder
- 31 December 2015
- Published by Walter de Gruyter GmbH
- p. 173-186
Automatically Evaluating Atypical Language in Narratives by Children with Autistic Spectrum Disorder
- 22 August 2015
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 119 (3) , 346-373
Recognizing Fine-Grained and Composite Activities Using Hand-Centric Features and Script Data
- 22 August 2015
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 119 (3) , 346-373
Recognizing Fine-Grained and Composite Activities Using Hand-Centric Features and Script Data
- 1 January 2014
- Published by Association for Computational Linguistics (ACL)
- p. 86-90
Short-Term Projects, Long-Term Benefits: Four Student NLP Projects for Low-Resource Languages
- 1 January 2014
- Published by Association for Computational Linguistics (ACL)
- p. 86-90
Short-Term Projects, Long-Term Benefits: Four Student NLP Projects for Low-Resource Languages
- Top Cited PapersOpen Access
- 1 December 2013
- Published by MIT Press in Transactions of the Association for Computational Linguistics
- Vol. 1, 25-36
Grounding Action Descriptions in Videos
Recent work has shown that the integration of visual information into text-based models can substantially improve model predictions, but so far only visual information extracted from static images has been used. In this paper, we consider the problem of grounding sentences describing actions in visual information extracted from videos. We present a general purpose corpus that aligns high quality videos with multiple natural language descriptions of the actions portrayed in the videos, together with an annotation of how similar the action descriptions are to each other. Experimental results demonstrate that a text-based model of similarity between actions improves substantially when combined with visual information from videos depicting the described actions.
- 1 December 2013
- Published by MIT Press in Transactions of the Association for Computational Linguistics
- Vol. 1, 25-36
Top Cited PapersOpen AccessGrounding Action Descriptions in Videos
Recent work has shown that the integration of visual information into text-based models can substantially improve model predictions, but so far only visual information extracted from static images has been used. In this paper, we consider the problem of grounding sentences describing actions in visual information extracted from videos. We present a general purpose corpus that aligns high quality videos with multiple natural language descriptions of the actions portrayed in the videos, together with an annotation of how similar the action descriptions are to each other. Experimental results demonstrate that a text-based model of similarity between actions improves substantially when combined with visual information from videos depicting the described actions.
- 1 January 2012
- Published by Springer Nature
- p. 144-157
Script Data for Attribute-Based Recognition of Composite Activities
- 1 January 2012
- Published by Springer Nature
- p. 144-157
Script Data for Attribute-Based Recognition of Composite Activities