--- _id: '7468' abstract: - lang: eng text: We present a new proximal bundle method for Maximum-A-Posteriori (MAP) inference in structured energy minimization problems. The method optimizes a Lagrangean relaxation of the original energy minimization problem using a multi plane block-coordinate Frank-Wolfe method that takes advantage of the specific structure of the Lagrangean decomposition. We show empirically that our method outperforms state-of-the-art Lagrangean decomposition based algorithms on some challenging Markov Random Field, multi-label discrete tomography and graph matching problems. article_number: 11138-11147 article_processing_charge: No author: - first_name: Paul full_name: Swoboda, Paul id: 446560C6-F248-11E8-B48F-1D18A9856A87 last_name: Swoboda - first_name: Vladimir full_name: Kolmogorov, Vladimir id: 3D50B0BA-F248-11E8-B48F-1D18A9856A87 last_name: Kolmogorov citation: ama: 'Swoboda P, Kolmogorov V. Map inference via block-coordinate Frank-Wolfe algorithm. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol 2019-June. IEEE; 2019. doi:10.1109/CVPR.2019.01140' apa: 'Swoboda, P., & Kolmogorov, V. (2019). Map inference via block-coordinate Frank-Wolfe algorithm. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Vol. 2019–June). Long Beach, CA, United States: IEEE. https://doi.org/10.1109/CVPR.2019.01140' chicago: Swoboda, Paul, and Vladimir Kolmogorov. “Map Inference via Block-Coordinate Frank-Wolfe Algorithm.” In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2019–June. IEEE, 2019. https://doi.org/10.1109/CVPR.2019.01140. ieee: P. Swoboda and V. Kolmogorov, “Map inference via block-coordinate Frank-Wolfe algorithm,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Long Beach, CA, United States, 2019, vol. 2019–June. ista: 'Swoboda P, Kolmogorov V. 2019. Map inference via block-coordinate Frank-Wolfe algorithm. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR: Conference on Computer Vision and Pattern Recognition vol. 2019–June, 11138–11147.' mla: Swoboda, Paul, and Vladimir Kolmogorov. “Map Inference via Block-Coordinate Frank-Wolfe Algorithm.” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2019–June, 11138–11147, IEEE, 2019, doi:10.1109/CVPR.2019.01140. short: P. Swoboda, V. Kolmogorov, in:, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE, 2019. conference: end_date: 2019-06-20 location: Long Beach, CA, United States name: 'CVPR: Conference on Computer Vision and Pattern Recognition' start_date: 2019-06-15 date_created: 2020-02-09T23:00:52Z date_published: 2019-06-01T00:00:00Z date_updated: 2023-09-07T14:54:24Z day: '01' department: - _id: VlKo doi: 10.1109/CVPR.2019.01140 ec_funded: 1 external_id: arxiv: - '1806.05049' isi: - '000542649304076' isi: 1 language: - iso: eng main_file_link: - open_access: '1' url: https://arxiv.org/abs/1806.05049 month: '06' oa: 1 oa_version: Preprint project: - _id: 25FBA906-B435-11E9-9278-68D0E5697425 call_identifier: FP7 grant_number: '616160' name: 'Discrete Optimization in Computer Vision: Theory and Practice' publication: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition publication_identifier: isbn: - '9781728132938' issn: - '10636919' publication_status: published publisher: IEEE quality_controlled: '1' scopus_import: '1' status: public title: Map inference via block-coordinate Frank-Wolfe algorithm type: conference user_id: c635000d-4b10-11ee-a964-aac5a93f6ac1 volume: 2019-June year: '2019' ... --- _id: '7415' article_processing_charge: No article_type: original author: - first_name: Jasmin full_name: Morandell, Jasmin id: 4739D480-F248-11E8-B48F-1D18A9856A87 last_name: Morandell - first_name: Armel full_name: Nicolas, Armel id: 2A103192-F248-11E8-B48F-1D18A9856A87 last_name: Nicolas - first_name: Lena A full_name: Schwarz, Lena A id: 29A8453C-F248-11E8-B48F-1D18A9856A87 last_name: Schwarz - first_name: Gaia full_name: Novarino, Gaia id: 3E57A680-F248-11E8-B48F-1D18A9856A87 last_name: Novarino orcid: 0000-0002-7673-7178 citation: ama: Morandell J, Nicolas A, Schwarz LA, Novarino G. S.16.05 Illuminating the role of the e3 ubiquitin ligase cullin3 in brain development and autism. European Neuropsychopharmacology. 2019;29(Supplement 6):S11-S12. doi:10.1016/j.euroneuro.2019.09.040 apa: Morandell, J., Nicolas, A., Schwarz, L. A., & Novarino, G. (2019). S.16.05 Illuminating the role of the e3 ubiquitin ligase cullin3 in brain development and autism. European Neuropsychopharmacology. Elsevier. https://doi.org/10.1016/j.euroneuro.2019.09.040 chicago: Morandell, Jasmin, Armel Nicolas, Lena A Schwarz, and Gaia Novarino. “S.16.05 Illuminating the Role of the E3 Ubiquitin Ligase Cullin3 in Brain Development and Autism.” European Neuropsychopharmacology. Elsevier, 2019. https://doi.org/10.1016/j.euroneuro.2019.09.040. ieee: J. Morandell, A. Nicolas, L. A. Schwarz, and G. Novarino, “S.16.05 Illuminating the role of the e3 ubiquitin ligase cullin3 in brain development and autism,” European Neuropsychopharmacology, vol. 29, no. Supplement 6. Elsevier, pp. S11–S12, 2019. ista: Morandell J, Nicolas A, Schwarz LA, Novarino G. 2019. S.16.05 Illuminating the role of the e3 ubiquitin ligase cullin3 in brain development and autism. European Neuropsychopharmacology. 29(Supplement 6), S11–S12. mla: Morandell, Jasmin, et al. “S.16.05 Illuminating the Role of the E3 Ubiquitin Ligase Cullin3 in Brain Development and Autism.” European Neuropsychopharmacology, vol. 29, no. Supplement 6, Elsevier, 2019, pp. S11–12, doi:10.1016/j.euroneuro.2019.09.040. short: J. Morandell, A. Nicolas, L.A. Schwarz, G. Novarino, European Neuropsychopharmacology 29 (2019) S11–S12. date_created: 2020-01-30T10:07:41Z date_published: 2019-12-13T00:00:00Z date_updated: 2023-09-07T14:56:17Z day: '13' department: - _id: GaNo - _id: LifeSc doi: 10.1016/j.euroneuro.2019.09.040 external_id: isi: - '000502657500021' intvolume: ' 29' isi: 1 issue: Supplement 6 language: - iso: eng month: '12' oa_version: None page: S11-S12 publication: European Neuropsychopharmacology publication_identifier: issn: - 0924-977X publication_status: published publisher: Elsevier quality_controlled: '1' status: public title: S.16.05 Illuminating the role of the e3 ubiquitin ligase cullin3 in brain development and autism type: journal_article user_id: c635000d-4b10-11ee-a964-aac5a93f6ac1 volume: 29 year: '2019' ... --- _id: '7414' article_processing_charge: No article_type: original author: - first_name: Lisa full_name: Knaus, Lisa id: 3B2ABCF4-F248-11E8-B48F-1D18A9856A87 last_name: Knaus - first_name: Dora-Clara full_name: Tarlungeanu, Dora-Clara id: 2ABCE612-F248-11E8-B48F-1D18A9856A87 last_name: Tarlungeanu - first_name: Gaia full_name: Novarino, Gaia id: 3E57A680-F248-11E8-B48F-1D18A9856A87 last_name: Novarino orcid: 0000-0002-7673-7178 citation: ama: Knaus L, Tarlungeanu D-C, Novarino G. S.16.03 A homozygous missense mutation in SLC7A5 leads to autism spectrum disorder and microcephaly. European Neuropsychopharmacology. 2019;29(Supplement 6):S11. doi:10.1016/j.euroneuro.2019.09.039 apa: Knaus, L., Tarlungeanu, D.-C., & Novarino, G. (2019). S.16.03 A homozygous missense mutation in SLC7A5 leads to autism spectrum disorder and microcephaly. European Neuropsychopharmacology. Elsevier. https://doi.org/10.1016/j.euroneuro.2019.09.039 chicago: Knaus, Lisa, Dora-Clara Tarlungeanu, and Gaia Novarino. “S.16.03 A Homozygous Missense Mutation in SLC7A5 Leads to Autism Spectrum Disorder and Microcephaly.” European Neuropsychopharmacology. Elsevier, 2019. https://doi.org/10.1016/j.euroneuro.2019.09.039. ieee: L. Knaus, D.-C. Tarlungeanu, and G. Novarino, “S.16.03 A homozygous missense mutation in SLC7A5 leads to autism spectrum disorder and microcephaly,” European Neuropsychopharmacology, vol. 29, no. Supplement 6. Elsevier, p. S11, 2019. ista: Knaus L, Tarlungeanu D-C, Novarino G. 2019. S.16.03 A homozygous missense mutation in SLC7A5 leads to autism spectrum disorder and microcephaly. European Neuropsychopharmacology. 29(Supplement 6), S11. mla: Knaus, Lisa, et al. “S.16.03 A Homozygous Missense Mutation in SLC7A5 Leads to Autism Spectrum Disorder and Microcephaly.” European Neuropsychopharmacology, vol. 29, no. Supplement 6, Elsevier, 2019, p. S11, doi:10.1016/j.euroneuro.2019.09.039. short: L. Knaus, D.-C. Tarlungeanu, G. Novarino, European Neuropsychopharmacology 29 (2019) S11. date_created: 2020-01-30T10:06:15Z date_published: 2019-12-13T00:00:00Z date_updated: 2023-09-07T14:55:23Z day: '13' department: - _id: GaNo doi: 10.1016/j.euroneuro.2019.09.039 external_id: isi: - '000502657500020' intvolume: ' 29' isi: 1 issue: Supplement 6 language: - iso: eng month: '12' oa_version: None page: S11 publication: European Neuropsychopharmacology publication_identifier: issn: - 0924-977X publication_status: published publisher: Elsevier quality_controlled: '1' status: public title: S.16.03 A homozygous missense mutation in SLC7A5 leads to autism spectrum disorder and microcephaly type: journal_article user_id: c635000d-4b10-11ee-a964-aac5a93f6ac1 volume: 29 year: '2019' ... --- _id: '7394' article_processing_charge: No article_type: letter_note author: - first_name: Eva full_name: Benková, Eva id: 38F4F166-F248-11E8-B48F-1D18A9856A87 last_name: Benková orcid: 0000-0002-8510-9739 - first_name: Yasin full_name: Dagdas, Yasin last_name: Dagdas citation: ama: 'Benková E, Dagdas Y. Editorial overview: Cell biology in the era of omics? Current Opinion in Plant Biology. 2019;52(12):A1-A2. doi:10.1016/j.pbi.2019.11.002' apa: 'Benková, E., & Dagdas, Y. (2019). Editorial overview: Cell biology in the era of omics? Current Opinion in Plant Biology. Elsevier. https://doi.org/10.1016/j.pbi.2019.11.002' chicago: 'Benková, Eva, and Yasin Dagdas. “Editorial Overview: Cell Biology in the Era of Omics?” Current Opinion in Plant Biology. Elsevier, 2019. https://doi.org/10.1016/j.pbi.2019.11.002.' ieee: 'E. Benková and Y. Dagdas, “Editorial overview: Cell biology in the era of omics?,” Current Opinion in Plant Biology, vol. 52, no. 12. Elsevier, pp. A1–A2, 2019.' ista: 'Benková E, Dagdas Y. 2019. Editorial overview: Cell biology in the era of omics? Current Opinion in Plant Biology. 52(12), A1–A2.' mla: 'Benková, Eva, and Yasin Dagdas. “Editorial Overview: Cell Biology in the Era of Omics?” Current Opinion in Plant Biology, vol. 52, no. 12, Elsevier, 2019, pp. A1–2, doi:10.1016/j.pbi.2019.11.002.' short: E. Benková, Y. Dagdas, Current Opinion in Plant Biology 52 (2019) A1–A2. date_created: 2020-01-29T16:00:07Z date_published: 2019-12-01T00:00:00Z date_updated: 2023-09-07T14:56:55Z day: '01' department: - _id: EvBe doi: 10.1016/j.pbi.2019.11.002 external_id: isi: - '000502890600001' pmid: - '31787165' intvolume: ' 52' isi: 1 issue: '12' language: - iso: eng month: '12' oa_version: None page: A1-A2 pmid: 1 publication: Current Opinion in Plant Biology publication_identifier: issn: - 1369-5266 publication_status: published publisher: Elsevier quality_controlled: '1' scopus_import: '1' status: public title: 'Editorial overview: Cell biology in the era of omics?' type: journal_article user_id: c635000d-4b10-11ee-a964-aac5a93f6ac1 volume: 52 year: '2019' ... --- _id: '7479' abstract: - lang: eng text: "Multi-exit architectures, in which a stack of processing layers is interleaved with early output layers, allow the processing of a test example to stop early and thus save computation time and/or energy. In this work, we propose a new training procedure for multi-exit architectures based on the principle of knowledge distillation. The method encourage searly exits to mimic later, more accurate exits, by matching their output probabilities.\r\nExperiments on CIFAR100 and \ ImageNet show that distillation-based training significantly improves the accuracy of early exits while maintaining state-of-the-art accuracy for late \ ones. The method is particularly beneficial when training data is limited \ and it allows a straightforward extension to semi-supervised learning,i.e. making use of unlabeled data at training time. Moreover, it takes only afew lines to implement and incurs almost no computational overhead at training time, and none at all at test time." article_processing_charge: No author: - first_name: Phuong full_name: Bui Thi Mai, Phuong id: 3EC6EE64-F248-11E8-B48F-1D18A9856A87 last_name: Bui Thi Mai - first_name: Christoph full_name: Lampert, Christoph id: 40C20FD2-F248-11E8-B48F-1D18A9856A87 last_name: Lampert orcid: 0000-0001-8622-7887 citation: ama: 'Phuong M, Lampert C. Distillation-based training for multi-exit architectures. In: IEEE International Conference on Computer Vision. Vol 2019-October. IEEE; 2019:1355-1364. doi:10.1109/ICCV.2019.00144' apa: 'Phuong, M., & Lampert, C. (2019). Distillation-based training for multi-exit architectures. In IEEE International Conference on Computer Vision (Vol. 2019–October, pp. 1355–1364). Seoul, Korea: IEEE. https://doi.org/10.1109/ICCV.2019.00144' chicago: Phuong, Mary, and Christoph Lampert. “Distillation-Based Training for Multi-Exit Architectures.” In IEEE International Conference on Computer Vision, 2019–October:1355–64. IEEE, 2019. https://doi.org/10.1109/ICCV.2019.00144. ieee: M. Phuong and C. Lampert, “Distillation-based training for multi-exit architectures,” in IEEE International Conference on Computer Vision, Seoul, Korea, 2019, vol. 2019–October, pp. 1355–1364. ista: 'Phuong M, Lampert C. 2019. Distillation-based training for multi-exit architectures. IEEE International Conference on Computer Vision. ICCV: International Conference on Computer Vision vol. 2019–October, 1355–1364.' mla: Phuong, Mary, and Christoph Lampert. “Distillation-Based Training for Multi-Exit Architectures.” IEEE International Conference on Computer Vision, vol. 2019–October, IEEE, 2019, pp. 1355–64, doi:10.1109/ICCV.2019.00144. short: M. Phuong, C. Lampert, in:, IEEE International Conference on Computer Vision, IEEE, 2019, pp. 1355–1364. conference: end_date: 2019-11-02 location: Seoul, Korea name: 'ICCV: International Conference on Computer Vision' start_date: 2019-10-27 date_created: 2020-02-11T09:06:57Z date_published: 2019-10-01T00:00:00Z date_updated: 2023-09-08T11:11:12Z day: '01' ddc: - '000' department: - _id: ChLa doi: 10.1109/ICCV.2019.00144 ec_funded: 1 external_id: isi: - '000531438101047' file: - access_level: open_access checksum: 7b77fb5c2d27c4c37a7612ba46a66117 content_type: application/pdf creator: bphuong date_created: 2020-02-11T09:06:39Z date_updated: 2020-07-14T12:47:59Z file_id: '7480' file_name: main.pdf file_size: 735768 relation: main_file file_date_updated: 2020-07-14T12:47:59Z has_accepted_license: '1' isi: 1 language: - iso: eng month: '10' oa: 1 oa_version: Submitted Version page: 1355-1364 project: - _id: 2532554C-B435-11E9-9278-68D0E5697425 call_identifier: FP7 grant_number: '308036' name: Lifelong Learning of Visual Scene Understanding publication: IEEE International Conference on Computer Vision publication_identifier: isbn: - '9781728148038' issn: - '15505499' publication_status: published publisher: IEEE quality_controlled: '1' related_material: record: - id: '9418' relation: dissertation_contains status: public scopus_import: '1' status: public title: Distillation-based training for multi-exit architectures type: conference user_id: c635000d-4b10-11ee-a964-aac5a93f6ac1 volume: 2019-October year: '2019' ... --- _id: '7542' abstract: - lang: eng text: We present a novel class of convolutional neural networks (CNNs) for set functions,i.e., data indexed with the powerset of a finite set. The convolutions are derivedas linear, shift-equivariant functions for various notions of shifts on set functions.The framework is fundamentally different from graph convolutions based on theLaplacian, as it provides not one but several basic shifts, one for each element inthe ground set. Prototypical experiments with several set function classificationtasks on synthetic datasets and on datasets derived from real-world hypergraphsdemonstrate the potential of our new powerset CNNs. article_processing_charge: No author: - first_name: Chris full_name: Wendler, Chris last_name: Wendler - first_name: Dan-Adrian full_name: Alistarh, Dan-Adrian id: 4A899BFC-F248-11E8-B48F-1D18A9856A87 last_name: Alistarh orcid: 0000-0003-3650-940X - first_name: Markus full_name: Püschel, Markus last_name: Püschel citation: ama: 'Wendler C, Alistarh D-A, Püschel M. Powerset convolutional neural networks. In: Vol 32. Neural Information Processing Systems Foundation; 2019:927-938.' apa: 'Wendler, C., Alistarh, D.-A., & Püschel, M. (2019). Powerset convolutional neural networks (Vol. 32, pp. 927–938). Presented at the NIPS: Conference on Neural Information Processing Systems, Vancouver, Canada: Neural Information Processing Systems Foundation.' chicago: Wendler, Chris, Dan-Adrian Alistarh, and Markus Püschel. “Powerset Convolutional Neural Networks,” 32:927–38. Neural Information Processing Systems Foundation, 2019. ieee: 'C. Wendler, D.-A. Alistarh, and M. Püschel, “Powerset convolutional neural networks,” presented at the NIPS: Conference on Neural Information Processing Systems, Vancouver, Canada, 2019, vol. 32, pp. 927–938.' ista: 'Wendler C, Alistarh D-A, Püschel M. 2019. Powerset convolutional neural networks. NIPS: Conference on Neural Information Processing Systems vol. 32, 927–938.' mla: Wendler, Chris, et al. Powerset Convolutional Neural Networks. Vol. 32, Neural Information Processing Systems Foundation, 2019, pp. 927–38. short: C. Wendler, D.-A. Alistarh, M. Püschel, in:, Neural Information Processing Systems Foundation, 2019, pp. 927–938. conference: end_date: 2019-12-14 location: Vancouver, Canada name: 'NIPS: Conference on Neural Information Processing Systems' start_date: 2019-12-08 date_created: 2020-02-28T10:03:24Z date_published: 2019-12-01T00:00:00Z date_updated: 2023-09-08T11:13:52Z day: '01' department: - _id: DaAl ec_funded: 1 external_id: arxiv: - '1909.02253' isi: - '000534424300084' intvolume: ' 32' isi: 1 language: - iso: eng main_file_link: - open_access: '1' url: http://papers.nips.cc/paper/8379-powerset-convolutional-neural-networks month: '12' oa: 1 oa_version: Published Version page: 927-938 project: - _id: 268A44D6-B435-11E9-9278-68D0E5697425 call_identifier: H2020 grant_number: '805223' name: Elastic Coordination for Scalable Machine Learning publication_identifier: issn: - 1049-5258 publication_status: published publisher: Neural Information Processing Systems Foundation quality_controlled: '1' status: public title: Powerset convolutional neural networks type: conference user_id: c635000d-4b10-11ee-a964-aac5a93f6ac1 volume: 32 year: '2019' ... --- _id: '7513' abstract: - lang: eng text: 'Social insects (i.e., ants, termites and the social bees and wasps) protect their colonies from disease using a combination of individual immunity and collectively performed defenses, termed social immunity. The first line of social immune defense is sanitary care, which is performed by colony members to protect their pathogen-exposed nestmates from developing an infection. If sanitary care fails and an infection becomes established, a second line of social immune defense is deployed to stop disease transmission within the colony and to protect the valuable queens, which together with the males are the reproductive individuals of the colony. Insect colonies are separated into these reproductive individuals and the sterile worker force, forming a superorganismal reproductive unit reminiscent of the differentiated germline and soma in a multicellular organism. Ultimately, the social immune response preserves the germline of the superorganism insect colony and increases overall fitness of the colony in case of disease. ' article_processing_charge: No author: - first_name: Sylvia full_name: Cremer, Sylvia id: 2F64EC8C-F248-11E8-B48F-1D18A9856A87 last_name: Cremer orcid: 0000-0002-2193-3868 - first_name: Megan full_name: Kutzer, Megan id: 29D0B332-F248-11E8-B48F-1D18A9856A87 last_name: Kutzer orcid: 0000-0002-8696-6978 citation: ama: 'Cremer S, Kutzer M. Social immunity. In: Choe J, ed. Encyclopedia of Animal Behavior. 2nd ed. Elsevier; 2019:747-755. doi:10.1016/B978-0-12-809633-8.90721-0' apa: Cremer, S., & Kutzer, M. (2019). Social immunity. In J. Choe (Ed.), Encyclopedia of Animal Behavior (2nd ed., pp. 747–755). Elsevier. https://doi.org/10.1016/B978-0-12-809633-8.90721-0 chicago: Cremer, Sylvia, and Megan Kutzer. “Social Immunity.” In Encyclopedia of Animal Behavior, edited by Jae Choe, 2nd ed., 747–55. Elsevier, 2019. https://doi.org/10.1016/B978-0-12-809633-8.90721-0. ieee: S. Cremer and M. Kutzer, “Social immunity,” in Encyclopedia of Animal Behavior, 2nd ed., J. Choe, Ed. Elsevier, 2019, pp. 747–755. ista: 'Cremer S, Kutzer M. 2019.Social immunity. In: Encyclopedia of Animal Behavior. , 747–755.' mla: Cremer, Sylvia, and Megan Kutzer. “Social Immunity.” Encyclopedia of Animal Behavior, edited by Jae Choe, 2nd ed., Elsevier, 2019, pp. 747–55, doi:10.1016/B978-0-12-809633-8.90721-0. short: S. Cremer, M. Kutzer, in:, J. Choe (Ed.), Encyclopedia of Animal Behavior, 2nd ed., Elsevier, 2019, pp. 747–755. date_created: 2020-02-23T23:00:36Z date_published: 2019-02-06T00:00:00Z date_updated: 2023-09-08T11:12:04Z day: '06' department: - _id: SyCr doi: 10.1016/B978-0-12-809633-8.90721-0 edition: '2' editor: - first_name: Jae full_name: Choe, Jae last_name: Choe external_id: isi: - '000248989500026' isi: 1 language: - iso: eng month: '02' oa_version: None page: 747-755 publication: Encyclopedia of Animal Behavior publication_identifier: eisbn: - '9780128132524' isbn: - '9780128132517' publication_status: published publisher: Elsevier quality_controlled: '1' scopus_import: '1' status: public title: Social immunity type: book_chapter user_id: c635000d-4b10-11ee-a964-aac5a93f6ac1 year: '2019' ... --- _id: '9261' abstract: - lang: eng text: 'Bending-active structures are able to efficiently produce complex curved shapes starting from flat panels. The desired deformation of the panels derives from the proper selection of their elastic properties. Optimized panels, called FlexMaps, are designed such that, once they are bent and assembled, the resulting static equilibrium configuration matches a desired input 3D shape. The FlexMaps elastic properties are controlled by locally varying spiraling geometric mesostructures, which are optimized in size and shape to match the global curvature (i.e., bending requests) of the target shape. The design pipeline starts from a quad mesh representing the input 3D shape, which defines the edge size and the total amount of spirals: every quad will embed one spiral. Then, an optimization algorithm tunes the geometry of the spirals by using a simplified pre-computed rod model. This rod model is derived from a non-linear regression algorithm which approximates the non-linear behavior of solid FEM spiral models subject to hundreds of load combinations. This innovative pipeline has been applied to the project of a lightweight plywood pavilion named FlexMaps Pavilion, which is a single-layer piecewise twisted arc that fits a bounding box of 3.90x3.96x3.25 meters.' article_processing_charge: No author: - first_name: Francesco full_name: Laccone, Francesco last_name: Laccone - first_name: Luigi full_name: Malomo, Luigi last_name: Malomo - first_name: Jesus full_name: Perez Rodriguez, Jesus id: 2DC83906-F248-11E8-B48F-1D18A9856A87 last_name: Perez Rodriguez - first_name: Nico full_name: Pietroni, Nico last_name: Pietroni - first_name: Federico full_name: Ponchio, Federico last_name: Ponchio - first_name: Bernd full_name: Bickel, Bernd id: 49876194-F248-11E8-B48F-1D18A9856A87 last_name: Bickel orcid: 0000-0001-6511-9385 - first_name: Paolo full_name: Cignoni, Paolo last_name: Cignoni citation: ama: 'Laccone F, Malomo L, Perez Rodriguez J, et al. FlexMaps Pavilion: A twisted arc made of mesostructured flat flexible panels. In: IASS Symposium 2019 - 60th Anniversary Symposium of the International Association for Shell and Spatial Structures; Structural Membranes 2019 - 9th International Conference on Textile Composites and Inflatable Structures, FORM and FORCE. International Center for Numerical Methods in Engineering; 2019:509-515.' apa: 'Laccone, F., Malomo, L., Perez Rodriguez, J., Pietroni, N., Ponchio, F., Bickel, B., & Cignoni, P. (2019). FlexMaps Pavilion: A twisted arc made of mesostructured flat flexible panels. In IASS Symposium 2019 - 60th Anniversary Symposium of the International Association for Shell and Spatial Structures; Structural Membranes 2019 - 9th International Conference on Textile Composites and Inflatable Structures, FORM and FORCE (pp. 509–515). Barcelona, Spain: International Center for Numerical Methods in Engineering.' chicago: 'Laccone, Francesco, Luigi Malomo, Jesus Perez Rodriguez, Nico Pietroni, Federico Ponchio, Bernd Bickel, and Paolo Cignoni. “FlexMaps Pavilion: A Twisted Arc Made of Mesostructured Flat Flexible Panels.” In IASS Symposium 2019 - 60th Anniversary Symposium of the International Association for Shell and Spatial Structures; Structural Membranes 2019 - 9th International Conference on Textile Composites and Inflatable Structures, FORM and FORCE, 509–15. International Center for Numerical Methods in Engineering, 2019.' ieee: 'F. Laccone et al., “FlexMaps Pavilion: A twisted arc made of mesostructured flat flexible panels,” in IASS Symposium 2019 - 60th Anniversary Symposium of the International Association for Shell and Spatial Structures; Structural Membranes 2019 - 9th International Conference on Textile Composites and Inflatable Structures, FORM and FORCE, Barcelona, Spain, 2019, pp. 509–515.' ista: 'Laccone F, Malomo L, Perez Rodriguez J, Pietroni N, Ponchio F, Bickel B, Cignoni P. 2019. FlexMaps Pavilion: A twisted arc made of mesostructured flat flexible panels. IASS Symposium 2019 - 60th Anniversary Symposium of the International Association for Shell and Spatial Structures; Structural Membranes 2019 - 9th International Conference on Textile Composites and Inflatable Structures, FORM and FORCE. IASS: International Association for Shell and Spatial Structures, 509–515.' mla: 'Laccone, Francesco, et al. “FlexMaps Pavilion: A Twisted Arc Made of Mesostructured Flat Flexible Panels.” IASS Symposium 2019 - 60th Anniversary Symposium of the International Association for Shell and Spatial Structures; Structural Membranes 2019 - 9th International Conference on Textile Composites and Inflatable Structures, FORM and FORCE, International Center for Numerical Methods in Engineering, 2019, pp. 509–15.' short: F. Laccone, L. Malomo, J. Perez Rodriguez, N. Pietroni, F. Ponchio, B. Bickel, P. Cignoni, in:, IASS Symposium 2019 - 60th Anniversary Symposium of the International Association for Shell and Spatial Structures; Structural Membranes 2019 - 9th International Conference on Textile Composites and Inflatable Structures, FORM and FORCE, International Center for Numerical Methods in Engineering, 2019, pp. 509–515. conference: end_date: 2019-10-10 location: Barcelona, Spain name: 'IASS: International Association for Shell and Spatial Structures' start_date: 2019-10-07 date_created: 2021-03-21T23:01:21Z date_published: 2019-10-10T00:00:00Z date_updated: 2023-09-08T11:21:54Z day: '10' department: - _id: BeBi external_id: isi: - '000563497600059' isi: 1 language: - iso: eng month: '10' oa_version: None page: 509-515 publication: IASS Symposium 2019 - 60th Anniversary Symposium of the International Association for Shell and Spatial Structures; Structural Membranes 2019 - 9th International Conference on Textile Composites and Inflatable Structures, FORM and FORCE publication_identifier: isbn: - '9788412110104' issn: - 2518-6582 publication_status: published publisher: International Center for Numerical Methods in Engineering quality_controlled: '1' scopus_import: '1' status: public title: 'FlexMaps Pavilion: A twisted arc made of mesostructured flat flexible panels' type: conference user_id: c635000d-4b10-11ee-a964-aac5a93f6ac1 year: '2019' ... --- _id: '7640' abstract: - lang: eng text: We propose a new model for detecting visual relationships, such as "person riding motorcycle" or "bottle on table". This task is an important step towards comprehensive structured mage understanding, going beyond detecting individual objects. Our main novelty is a Box Attention mechanism that allows to model pairwise interactions between objects using standard object detection pipelines. The resulting model is conceptually clean, expressive and relies on well-justified training and prediction procedures. Moreover, unlike previously proposed approaches, our model does not introduce any additional complex components or hyperparameters on top of those already required by the underlying detection model. We conduct an experimental evaluation on two datasets, V-COCO and Open Images, demonstrating strong quantitative and qualitative results. article_number: 1749-1753 article_processing_charge: No author: - first_name: Alexander full_name: Kolesnikov, Alexander id: 2D157DB6-F248-11E8-B48F-1D18A9856A87 last_name: Kolesnikov - first_name: Alina full_name: Kuznetsova, Alina last_name: Kuznetsova - first_name: Christoph full_name: Lampert, Christoph id: 40C20FD2-F248-11E8-B48F-1D18A9856A87 last_name: Lampert orcid: 0000-0001-8622-7887 - first_name: Vittorio full_name: Ferrari, Vittorio last_name: Ferrari citation: ama: 'Kolesnikov A, Kuznetsova A, Lampert C, Ferrari V. Detecting visual relationships using box attention. In: Proceedings of the 2019 International Conference on Computer Vision Workshop. IEEE; 2019. doi:10.1109/ICCVW.2019.00217' apa: 'Kolesnikov, A., Kuznetsova, A., Lampert, C., & Ferrari, V. (2019). Detecting visual relationships using box attention. In Proceedings of the 2019 International Conference on Computer Vision Workshop. Seoul, South Korea: IEEE. https://doi.org/10.1109/ICCVW.2019.00217' chicago: Kolesnikov, Alexander, Alina Kuznetsova, Christoph Lampert, and Vittorio Ferrari. “Detecting Visual Relationships Using Box Attention.” In Proceedings of the 2019 International Conference on Computer Vision Workshop. IEEE, 2019. https://doi.org/10.1109/ICCVW.2019.00217. ieee: A. Kolesnikov, A. Kuznetsova, C. Lampert, and V. Ferrari, “Detecting visual relationships using box attention,” in Proceedings of the 2019 International Conference on Computer Vision Workshop, Seoul, South Korea, 2019. ista: 'Kolesnikov A, Kuznetsova A, Lampert C, Ferrari V. 2019. Detecting visual relationships using box attention. Proceedings of the 2019 International Conference on Computer Vision Workshop. ICCVW: International Conference on Computer Vision Workshop, 1749–1753.' mla: Kolesnikov, Alexander, et al. “Detecting Visual Relationships Using Box Attention.” Proceedings of the 2019 International Conference on Computer Vision Workshop, 1749–1753, IEEE, 2019, doi:10.1109/ICCVW.2019.00217. short: A. Kolesnikov, A. Kuznetsova, C. Lampert, V. Ferrari, in:, Proceedings of the 2019 International Conference on Computer Vision Workshop, IEEE, 2019. conference: end_date: 2019-10-28 location: Seoul, South Korea name: 'ICCVW: International Conference on Computer Vision Workshop' start_date: 2019-10-27 date_created: 2020-04-05T22:00:51Z date_published: 2019-10-01T00:00:00Z date_updated: 2023-09-08T11:18:37Z day: '01' department: - _id: ChLa doi: 10.1109/ICCVW.2019.00217 ec_funded: 1 external_id: arxiv: - '1807.02136' isi: - '000554591601098' isi: 1 language: - iso: eng main_file_link: - open_access: '1' url: https://arxiv.org/abs/1807.02136 month: '10' oa: 1 oa_version: Preprint project: - _id: 2532554C-B435-11E9-9278-68D0E5697425 call_identifier: FP7 grant_number: '308036' name: Lifelong Learning of Visual Scene Understanding publication: Proceedings of the 2019 International Conference on Computer Vision Workshop publication_identifier: isbn: - '9781728150239' publication_status: published publisher: IEEE quality_controlled: '1' scopus_import: '1' status: public title: Detecting visual relationships using box attention type: conference user_id: c635000d-4b10-11ee-a964-aac5a93f6ac1 year: '2019' ... --- _id: '7639' abstract: - lang: eng text: Deep neural networks (DNNs) have become increasingly important due to their excellent empirical performance on a wide range of problems. However, regularization is generally achieved by indirect means, largely due to the complex set of functions defined by a network and the difficulty in measuring function complexity. There exists no method in the literature for additive regularization based on a norm of the function, as is classically considered in statistical learning theory. In this work, we study the tractability of function norms for deep neural networks with ReLU activations. We provide, to the best of our knowledge, the first proof in the literature of the NP-hardness of computing function norms of DNNs of 3 or more layers. We also highlight a fundamental difference between shallow and deep networks. In the light on these results, we propose a new regularization strategy based on approximate function norms, and show its efficiency on a segmentation task with a DNN. article_number: 748-752 article_processing_charge: No author: - first_name: Amal full_name: Rannen-Triki, Amal last_name: Rannen-Triki - first_name: Maxim full_name: Berman, Maxim last_name: Berman - first_name: Vladimir full_name: Kolmogorov, Vladimir id: 3D50B0BA-F248-11E8-B48F-1D18A9856A87 last_name: Kolmogorov - first_name: Matthew B. full_name: Blaschko, Matthew B. last_name: Blaschko citation: ama: 'Rannen-Triki A, Berman M, Kolmogorov V, Blaschko MB. Function norms for neural networks. In: Proceedings of the 2019 International Conference on Computer Vision Workshop. IEEE; 2019. doi:10.1109/ICCVW.2019.00097' apa: 'Rannen-Triki, A., Berman, M., Kolmogorov, V., & Blaschko, M. B. (2019). Function norms for neural networks. In Proceedings of the 2019 International Conference on Computer Vision Workshop. Seoul, South Korea: IEEE. https://doi.org/10.1109/ICCVW.2019.00097' chicago: Rannen-Triki, Amal, Maxim Berman, Vladimir Kolmogorov, and Matthew B. Blaschko. “Function Norms for Neural Networks.” In Proceedings of the 2019 International Conference on Computer Vision Workshop. IEEE, 2019. https://doi.org/10.1109/ICCVW.2019.00097. ieee: A. Rannen-Triki, M. Berman, V. Kolmogorov, and M. B. Blaschko, “Function norms for neural networks,” in Proceedings of the 2019 International Conference on Computer Vision Workshop, Seoul, South Korea, 2019. ista: 'Rannen-Triki A, Berman M, Kolmogorov V, Blaschko MB. 2019. Function norms for neural networks. Proceedings of the 2019 International Conference on Computer Vision Workshop. ICCVW: International Conference on Computer Vision Workshop, 748–752.' mla: Rannen-Triki, Amal, et al. “Function Norms for Neural Networks.” Proceedings of the 2019 International Conference on Computer Vision Workshop, 748–752, IEEE, 2019, doi:10.1109/ICCVW.2019.00097. short: A. Rannen-Triki, M. Berman, V. Kolmogorov, M.B. Blaschko, in:, Proceedings of the 2019 International Conference on Computer Vision Workshop, IEEE, 2019. conference: end_date: 2019-10-28 location: Seoul, South Korea name: 'ICCVW: International Conference on Computer Vision Workshop' start_date: 2019-10-27 date_created: 2020-04-05T22:00:50Z date_published: 2019-10-01T00:00:00Z date_updated: 2023-09-08T11:19:12Z day: '01' department: - _id: VlKo doi: 10.1109/ICCVW.2019.00097 external_id: isi: - '000554591600090' isi: 1 language: - iso: eng month: '10' oa_version: None publication: Proceedings of the 2019 International Conference on Computer Vision Workshop publication_identifier: isbn: - '9781728150239' publication_status: published publisher: IEEE quality_controlled: '1' scopus_import: '1' status: public title: Function norms for neural networks type: conference user_id: c635000d-4b10-11ee-a964-aac5a93f6ac1 year: '2019' ...