D2
Computer Vision and Machine Learning

Anna Kukleva (PhD Student)

MSc Anna Kukleva

Address
Max-Planck-Institut für Informatik
Saarland Informatics Campus
Campus E1 4
66123 Saarbrücken
Standort
E1 4 - 615
Telefon
+49 681 9325 2144
Fax
+49 681 9325 2099

Personal Information

Personal page

Publications

VidalMata, R. G., Scheirer, W. J., Kukleva, A., Cox, D., & Kuehne, H. (2021). Joint Visual-Temporal Embedding for Unsupervised Learning of Actions in Untrimmed Sequences. In IEEE Winter Conference on Applications of Computer Vision (WACV 2021). Virtual: Computer Vision Foundation.
[PuRe]
[BibTeX]
[pre-print version]
Links
[PuRe]
[BibTeX]
[pre-print version]
Export
BibTeX
@inproceedings{VidalMata_WACV21, TITLE = {Joint Visual-Temporal Embedding for Unsupervised Learning of Actions in Untrimmed Sequences}, AUTHOR = {VidalMata, Rosaura G. and Scheirer, Walter J. and Kukleva, Anna and Cox, David and Kuehne, Hilde}, LANGUAGE = {eng}, PUBLISHER = {Computer Vision Foundation}, YEAR = {2021}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {IEEE Winter Conference on Applications of Computer Vision (WACV 2021)}, PAGES = {1238--1247}, ADDRESS = {Virtual}, }
Endnote
%0 Conference Proceedings %A VidalMata, Rosaura G. %A Scheirer, Walter J. %A Kukleva, Anna %A Cox, David %A Kuehne, Hilde %+ External Organizations External Organizations Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society External Organizations External Organizations %T Joint Visual-Temporal Embedding for Unsupervised Learning of Actions in Untrimmed Sequences : %G eng %U http://hdl.handle.net/21.11116/0000-0008-4593-4 %D 2021 %B IEEE Winter Conference on Applications of Computer Vision %Z date of event: 2021-01-05 - 2021-01-09 %C Virtual %B IEEE Winter Conference on Applications of Computer Vision %P 1238 - 1247 %I Computer Vision Foundation
Kukleva, A., Kuehne, H., & Schiele, B. (2021). Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting. Retrieved from https://arxiv.org/abs/2108.08165
(arXiv: 2108.08165)
[arXiv]
[PuRe]
[BibTeX]
[pre-print version]
Abstract
Both generalized and incremental few-shot learning have to deal with three major challenges: learning novel classes from only few samples per class, preventing catastrophic forgetting of base classes, and classifier calibration across novel and base classes. In this work we propose a three-stage framework that allows to explicitly and effectively address these challenges. While the first phase learns base classes with many samples, the second phase learns a calibrated classifier for novel classes from few samples while also preventing catastrophic forgetting. In the final phase, calibration is achieved across all classes. We evaluate the proposed framework on four challenging benchmark datasets for image and video few-shot classification and obtain state-of-the-art results for both generalized and incremental few shot learning.
Links
[PuRe]
[arXiv]
[BibTeX]
[pre-print version]
Export
BibTeX
@online{Kukleva2108.08165, TITLE = {Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting}, AUTHOR = {Kukleva, Anna and Kuehne, Hilde and Schiele, Bernt}, LANGUAGE = {eng}, URL = {https://arxiv.org/abs/2108.08165}, EPRINT = {2108.08165}, EPRINTTYPE = {arXiv}, YEAR = {2021}, MARGINALMARK = {$\bullet$}, ABSTRACT = {Both generalized and incremental few-shot learning have to deal with three major challenges: learning novel classes from only few samples per class, preventing catastrophic forgetting of base classes, and classifier calibration across novel and base classes. In this work we propose a three-stage framework that allows to explicitly and effectively address these challenges. While the first phase learns base classes with many samples, the second phase learns a calibrated classifier for novel classes from few samples while also preventing catastrophic forgetting. In the final phase, calibration is achieved across all classes. We evaluate the proposed framework on four challenging benchmark datasets for image and video few-shot classification and obtain state-of-the-art results for both generalized and incremental few shot learning.}, }
Endnote
%0 Report %A Kukleva, Anna %A Kuehne, Hilde %A Schiele, Bernt %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society External Organizations Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting : %G eng %U http://hdl.handle.net/21.11116/0000-0009-810E-6 %U https://arxiv.org/abs/2108.08165 %D 2021 %X Both generalized and incremental few-shot learning have to deal with three major challenges: learning novel classes from only few samples per class, preventing catastrophic forgetting of base classes, and classifier calibration across novel and base classes. In this work we propose a three-stage framework that allows to explicitly and effectively address these challenges. While the first phase learns base classes with many samples, the second phase learns a calibrated classifier for novel classes from few samples while also preventing catastrophic forgetting. In the final phase, calibration is achieved across all classes. We evaluate the proposed framework on four challenging benchmark datasets for image and video few-shot classification and obtain state-of-the-art results for both generalized and incremental few shot learning. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV
Kukleva, A., Tapaswi, M., & Laptev, I. (2020). Learning Interactions and Relationships between Movie Characters. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020). Seattle, WA, USA (Virtual): IEEE. doi:10.1109/CVPR42600.2020.00987
[DOI]
[PuRe]
[BibTeX]
Links
[DOI]
[PuRe]
[BibTeX]
Export
BibTeX
@inproceedings{Kukleva_CVPR2020, TITLE = {Learning Interactions and Relationships between Movie Characters}, AUTHOR = {Kukleva, Anna and Tapaswi, Makarand and Laptev, Ivan}, LANGUAGE = {eng}, ISBN = {978-1-7281-7168-5}, DOI = {10.1109/CVPR42600.2020.00987}, PUBLISHER = {IEEE}, YEAR = {2020}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020)}, PAGES = {9846--9855}, ADDRESS = {Seattle, WA, USA (Virtual)}, }
Endnote
%0 Conference Proceedings %A Kukleva, Anna %A Tapaswi, Makarand %A Laptev, Ivan %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society External Organizations External Organizations %T Learning Interactions and Relationships between Movie Characters : %G eng %U http://hdl.handle.net/21.11116/0000-0008-458B-E %R 10.1109/CVPR42600.2020.00987 %D 2020 %B 33rd IEEE Conference on Computer Vision and Pattern Recognition %Z date of event: 2020-06-14 - 2020-06-19 %C Seattle, WA, USA (Virtual) %B IEEE/CVF Conference on Computer Vision and Pattern Recognition %P 9846 - 9855 %I IEEE %@ 978-1-7281-7168-5