Search

Your search keyword '"Martin Pierre"' showing total 261 results
Start Over Author "Martin Pierre" Publication Year Range Last 3 years
261 results on '"Martin Pierre"'

1. Promoting oil palm-based agroforestry systems: an asset for the sustainability of the sector

Author

Masure Alix, Martin Pierre, Lacan Xavier, and Rafflegeau Sylvain

Subjects
oil palm, agroforestry, agroecosystem, diversification, resilience, Agriculture (General), S1-972, Plant culture, SB1-1110
Abstract

Until recently, the massive development of industrial and smallholder oil palm (Elaeis guineensis Jacq.) plantations has generally been conducted according to the monocrop model. However, alternative cropping systems have emerged, based on more diversified systems that combine various crops within the oil palm plots. By giving this plant a status equivalent to that of a tree, these practices correspond to agroforestry systems. In the present study, 39 agroforestry systems were identified worldwide through a preliminary literature review, a review of NGO websites and expert surveys. Our results reveal five different types of oil palm agroforestry systems: (i) associations with livestock during the production phase of the oil palm; (ii) traditional African palm and food crop systems sustained over time; (iii) associations with food crops during the juvenile phase of the oil palm; (iv) systems developed by family farms that permanently associate other plants; and (v) prototype designs developed by research institutions, often at the request of local agricultural enterprises. The spatiotemporal description of these systems enabled us to identify associated ecosystem services. Building on various proposals of biodiversity insertion in a monoculture to convert it into an agroforestry system, the present study offers new perspectives for the sustainable development of palm oil production.

Published
2023
Full Text
View/download PDF

7. Dataset Generation and Bonobo Classification from Weakly Labelled Videos

Author

Martin, Pierre-Etienne

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

This paper presents a bonobo detection and classification pipeline built from the commonly used machine learning methods. Such application is motivated by the need to test bonobos in their enclosure using touch screen devices without human assistance. This work introduces a newly acquired dataset based on bonobo recordings generated semi-automatically. The recordings are weakly labelled and fed to a macaque detector in order to spatially detect the individual present in the video. Handcrafted features coupled with different classification algorithms and deep-learning methods using a ResNet architecture are investigated for bonobo identification. Performance is compared in terms of classification accuracy on the splits of the database using different data separation methods. We demonstrate the importance of data preparation and how a wrong data separation can lead to false good results. Finally, after a meaningful separation of the data, the best classification performance is obtained using a fine-tuned ResNet model and reaches 75% of accuracy., Comment: IntelliSys 2023 paper

Published
2023

8. Interactive infill topology optimisation guided by user drawn patterns

Author

Gillian Schiffer, Martin-Pierre Schmidt, Claus B. W. Pedersen, and Josephine V. Carstensen

Subjects
Topology optimisation, iterative user interaction, infill, appearance constraint, Science, Manufactures, TS1-2301
Abstract

Widespread use of topology optimisation as a design tool for additive manufacturing faces major inhibiting obstacles, such as high computational costs and complexity, concern for other failure modes, and manufacturability. Interactive infill topology optimisation presents an alternative approach to circumvent some of these barriers. The novel contribution of the present work prompts the user to draw a tailored infill pattern, specify regions of interest to locate the infill, and control how strictly the pattern is replicated in the material layout of the design using appearance constraints. This approach improves engineering metrics not directly included in the optimisation formulation by incorporating the user’s engineering experience, thereby avoiding increased computational costs, parameter tuning, and numerical artifacts associated with complex objective functions and constraints. Two 2D benchmark examples increase the linear buckling resistance and energy absorption, respectively, and a 2.5D example minimises compliance while reducing the quantity of overhang supports for additive manufacturing.

Published
2024
Full Text
View/download PDF

9. Fine-Grained Action Detection with RGB and Pose Information using Two Stream Convolutional Networks

Author

Hacker, Leonard, Bartels, Finn, and Martin, Pierre-Etienne

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Computer Science - Multimedia
Abstract

As participants of the MediaEval 2022 Sport Task, we propose a two-stream network approach for the classification and detection of table tennis strokes. Each stream is a succession of 3D Convolutional Neural Network (CNN) blocks using attention mechanisms. Each stream processes different 4D inputs. Our method utilizes raw RGB data and pose information computed from MMPose toolbox. The pose information is treated as an image by applying the pose either on a black background or on the original RGB frame it has been computed from. Best performance is obtained by feeding raw RGB data to one stream, Pose + RGB (PRGB) information to the other stream and applying late fusion on the features. The approaches were evaluated on the provided TTStroke-21 data sets. We can report an improvement in stroke classification, reaching 87.3% of accuracy, while the detection does not outperform the baseline but still reaches an IoU of 0.349 and mAP of 0.110., Comment: Working note paper of the sport task of MediaEval 2022 in Bergen, Norway, 12-13 Jan 2023

Published
2023

10. Baseline Method for the Sport Task of MediaEval 2022 with 3D CNNs using Attention Mechanisms

Author

Martin, Pierre-Etienne

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Computer Science - Multimedia
Abstract

This paper presents the baseline method proposed for the Sports Video task part of the MediaEval 2022 benchmark. This task proposes two subtasks: stroke classification from trimmed videos, and stroke detection from untrimmed videos. This baseline addresses both subtasks. We propose two types of 3D-CNN architectures to solve the two subtasks. Both 3D-CNNs use Spatio-temporal convolutions and attention mechanisms. The architectures and the training process are tailored to solve the addressed subtask. This baseline method is shared publicly online to help the participants in their investigation and alleviate eventually some aspects of the task such as video processing, training method, evaluation and submission routine. The baseline method reaches 86.4% of accuracy with our v2 model for the classification subtask. For the detection subtask, the baseline reaches a mAP of 0.131 and IoU of 0.515 with our v1 model., Comment: Baseline paper for the sport Task of MediaEval 2022

Published
2023

11. Sport Task: Fine Grained Action Detection and Classification of Table Tennis Strokes from Videos for MediaEval 2022

Author

Martin, Pierre-Etienne, Calandre, Jordan, Mansencal, Boris, Benois-Pineau, Jenny, Péteri, Renaud, Mascarilla, Laurent, and Morlier, Julien

Subjects
Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Human-Computer Interaction, Computer Science - Machine Learning, Computer Science - Multimedia
Abstract

Sports video analysis is a widespread research topic. Its applications are very diverse, like events detection during a match, video summary, or fine-grained movement analysis of athletes. As part of the MediaEval 2022 benchmarking initiative, this task aims at detecting and classifying subtle movements from sport videos. We focus on recordings of table tennis matches. Conducted since 2019, this task provides a classification challenge from untrimmed videos recorded under natural conditions with known temporal boundaries for each stroke. Since 2021, the task also provides a stroke detection challenge from unannotated, untrimmed videos. This year, the training, validation, and test sets are enhanced to ensure that all strokes are represented in each dataset. The dataset is now similar to the one used in [1, 2]. This research is intended to build tools for coaches and athletes who want to further evaluate their sport performances., Comment: MediaEval 2022 Workshop, Jan 2023, Bergen, Norway. arXiv admin note: substantial text overlap with arXiv:2112.11384

Published
2023

12. Sepsis-trained macrophages promote antitumoral tissue-resident T cells

Author

Broquet, Alexis, Gourain, Victor, Goronflot, Thomas, Le Mabecque, Virginie, Sinha, Debajyoti, Ashayeripanah, Mitra, Jacqueline, Cédric, Martin, Pierre, Davieau, Marion, Boutin, Lea, Poulain, Cecile, Martin, Florian P., Fourgeux, Cynthia, Petrier, Melanie, Cannevet, Manon, Leclercq, Thomas, Guillonneau, Maeva, Chaumette, Tanguy, Laurent, Thomas, Harly, Christelle, Scotet, Emmanuel, Legentil, Laurent, Ferrières, Vincent, Corgnac, Stephanie, Mami-Chouaib, Fathia, Mosnier, Jean Francois, Mauduit, Nicolas, McWilliam, Hamish E. G., Villadangos, Jose A., Gourraud, Pierre Antoine, Asehnoune, Karim, Poschmann, Jeremie, and Roquilly, Antoine

Published
2024
Full Text
View/download PDF

13. FCAvizIR: Exploring Relational Data Set’s Implications Using Metrics and Topics

Author

Musslin, Lola, Bazin, Alexandre, Huchard, Marianne, Martin, Pierre, Poncelet, Pascal, Raveneau, Vincent, Sallaberry, Arnaud, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Cabrera, Inma P., editor, Ferré, Sébastien, editor, and Obiedkov, Sergei, editor

Published
2024
Full Text
View/download PDF

15. Computer Vision for Analyzing Children’s Lived Experiences

Author

Zahra, Anam, Martin, Pierre-Etienne, Bohn, Manuel, Haun, Daniel, Kacprzyk, Janusz, Series Editor, Gomide, Fernando, Advisory Editor, Kaynak, Okyay, Advisory Editor, Liu, Derong, Advisory Editor, Pedrycz, Witold, Advisory Editor, Polycarpou, Marios M., Advisory Editor, Rudas, Imre J., Advisory Editor, Wang, Jun, Advisory Editor, and Arai, Kohei, editor

Published
2024
Full Text
View/download PDF

16. Virtual Reality for the Preservation and Promotion of Historical Real Tennis

Author

Gaugne, Ronan, Saint-Auret, Sony, Duc-Martin, Pierre, Gouranton, Valérie, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Sheng, Bin, editor, Bi, Lei, editor, Kim, Jinman, editor, Magnenat-Thalmann, Nadia, editor, and Thalmann, Daniel, editor

Published
2024
Full Text
View/download PDF

17. Author Correction: Sepsis-trained macrophages promote antitumoral tissue-resident T cells

Author

Broquet, Alexis, Gourain, Victor, Goronflot, Thomas, Le Mabecque, Virginie, Sinha, Debajyoti, Ashayeripanah, Mitra, Jacqueline, Cédric, Martin, Pierre, Davieau, Marion, Boutin, Lea, Poulain, Cecile, Martin, Florian P., Fourgeux, Cynthia, Petrier, Melanie, Cannevet, Manon, Leclercq, Thomas, Guillonneau, Maeva, Chaumette, Tanguy, Laurent, Thomas, Harly, Christelle, Scotet, Emmanuel, Legentil, Laurent, Ferrières, Vincent, Corgnac, Stephanie, Mami-Chouaib, Fathia, Mosnier, Jean Francois, Mauduit, Nicolas, McWilliam, Hamish E. G., Villadangos, Jose A., Gourraud, Pierre Antoine, Asehnoune, Karim, Poschmann, Jeremie, and Roquilly, Antoine

Published
2024
Full Text
View/download PDF

18. Diagnostic yield of pediatric and prenatal exome sequencing in a diverse population

Author

Slavotinek, Anne, Rego, Shannon, Sahin-Hodoglugil, Nuriye, Kvale, Mark, Lianoglou, Billie, Yip, Tiffany, Hoban, Hannah, Outram, Simon, Anguiano, Beatrice, Chen, Flavia, Michelson, Jeremy, Cilio, Roberta M, Curry, Cynthia, Gallagher, Renata C, Gardner, Marisa, Kuperman, Rachel, Mendelsohn, Bryce, Sherr, Elliott, Shieh, Joseph, Strober, Jonathan, Tam, Allison, Tenney, Jessica, Weiss, William, Whittle, Amy, Chin, Garrett, Faubel, Amanda, Prasad, Hannah, Mavura, Yusuph, Van Ziffle, Jessica, Devine, W Patrick, Hodoglugil, Ugur, Martin, Pierre-Marie, Sparks, Teresa N, Koenig, Barbara, Ackerman, Sara, Risch, Neil, Kwok, Pui-Yan, and Norton, Mary E

Subjects
Health Disparities, Minority Health, Clinical Research, Congenital Structural Anomalies, Perinatal Period - Conditions Originating in Perinatal Period, Human Genome, Rare Diseases, Women's Health, Pediatric, Genetics, Medical biotechnology
Abstract

The diagnostic yield of exome sequencing (ES) has primarily been evaluated in individuals of European ancestry, with less focus on underrepresented minority (URM) and underserved (US) patients. We evaluated the diagnostic yield of ES in a cohort of predominantly US and URM pediatric and prenatal patients suspected to have a genetic disorder. Eligible pediatric patients had multiple congenital anomalies and/or neurocognitive disabilities and prenatal patients had one or more structural anomalies, disorders of fetal growth, or fetal effusions. URM and US patients were prioritized for enrollment and underwent ES at a single academic center. We identified definitive positive or probable positive results in 201/845 (23.8%) patients, with a significantly higher diagnostic rate in pediatric (26.7%) compared to prenatal patients (19.0%) (P = 0.01). For both pediatric and prenatal patients, the diagnostic yield and frequency of inconclusive findings did not differ significantly between URM and non-URM patients or between patients with US status and those without US status. Our results demonstrate a similar diagnostic yield of ES between prenatal and pediatric URM/US patients and non-URM/US patients for positive and inconclusive results. These data support the use of ES to identify clinically relevant variants in patients from diverse populations.

Published
2023

19. 3D Convolutional Networks for Action Recognition: Application to Sport Gesture Recognition

Author

Martin, Pierre-Etienne, Benois-Pineau, J, Péteri, R, Zemmari, A, and Morlier, J

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

3D convolutional networks is a good means to perform tasks such as video segmentation into coherent spatio-temporal chunks and classification of them with regard to a target taxonomy. In the chapter we are interested in the classification of continuous video takes with repeatable actions, such as strokes of table tennis. Filmed in a free marker less ecological environment, these videos represent a challenge from both segmentation and classification point of view. The 3D convnets are an efficient tool for solving these problems with window-based approaches., Comment: Multi-faceted Deep Learning, 2021

Published
2022

26. Author Correction: Diagnostic yield of pediatric and prenatal exome sequencing in a diverse population

Author

Slavotinek, Anne, Rego, Shannon, Sahin-Hodoglugil, Nuriye, Kvale, Mark, Lianoglou, Billie, Yip, Tiffany, Hoban, Hannah, Outram, Simon, Anguiano, Beatrice, Chen, Flavia, Michelson, Jeremy, Cilio, Roberta M., Curry, Cynthia, Gallagher, Renata C., Gardner, Marisa, Kuperman, Rachel, Mendelsohn, Bryce, Sherr, Elliott, Shieh, Joseph, Strober, Jonathan, Tam, Allison, Tenney, Jessica, Weiss, William, Whittle, Amy, Chin, Garrett, Faubel, Amanda, Prasad, Hannah, Mavura, Yusuph, Van Ziffle, Jessica, Devine, W. Patrick, Hodoglugil, Ugur, Martin, Pierre-Marie, Sparks, Teresa N., Koenig, Barbara, Ackerman, Sara, Risch, Neil, Kwok, Pui-Yan, and Norton, Mary E.

Published
2023
Full Text
View/download PDF

28. Relational Concept Analysis in Practice: Capitalizing on Data Modeling Using Design Patterns

Author

Braud, Agnès, Dolques, Xavier, Huchard, Marianne, Le Ber, Florence, Martin, Pierre, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Dürrschnabel, Dominik, editor, and López Rodríguez, Domingo, editor

Published
2023
Full Text
View/download PDF

36. The MELD upgrade exception: a successful strategy to optimize access to liver transplantation for patients with high waiting list mortality

Author

Amico, Patrizia, Axel, Andres, Aubert, John-David, Banz, Vanessa, Sonja, Beckmann, Beldi, Guido, Benden, Christian, Berger, Christoph, Binet, Isabelle, Bochud, Pierre-Yves, Branca, Sanda, Bucher, Heiner, Carrel, Thierry, Catana, Emmanuelle, Chalandon, Yves, de Geest, Sabina, de Rougemont, Olivier, Dickenmann, Michael, Dreifuss, Joëlle L., Duchosal, Michel, Fehr, Thomas, Ferrari-Lacraz, Sylvie, Garzoni, Christian, Soccal, Paola G., Gaudet, Christophe, Giostra, Emiliano, Golshayan, Déla, Hadaya, Karine, Halter, Jörg, Hauri, Dimitri, Heim, Dominik, Hess, Christoph, Hillinger, Sven, Hirsch, Hans, Hirt, Patricia, Hofbauer, Günther, Huynh-Do, Uyen, Immer, Franz, Koller, Michael, Laesser, Bettina, Lang, Brian, Lehmann, Roger, Leichtle, Alexander, Lovis, Christian, Manuel, Oriol, Marti, Hans-Peter, Martin, Pierre Y., Martinelli, Michele, Mellac, Katell, Merçay, Aurélia, Mettler, Karin, Meylan, Pascal, Mueller, Nicolas, Müller, Antonia, Müller, Thomas, Müller-Arndt, Ulrike, Müllhaupt, Beat, Nägeli, Mirjam, Pascual, Manuel, Posfay-Barbe, Klara, Rick, Juliane, Rosselet, Anne, Rossi, Simona, Rothlin, Silvia, Ruschitzka, Frank, Schanz, Urs, Schaub, Stefan, Schnyder, Aurelia, Schuurmans, Macé, Simonetta, Federico, Staufer, Katharina, Stampf, Susanne, Steiger, Jürg, Stirniman, Guido, Stürzinger, Ueli, Toso, Christian, Van Delden, Christian, Venetz, Jean-Pierre, Villard, Jean, Vionnet, Julien, Wick, Madeleine, Wilhlem, Markus, Yerly, Patrick, Dirchwolf, Melisa, Becchetti, Chiara, Gschwend, Sarah G., Dutkowski, Philipp, Beyeler, Franziska, Schropp, Jonas, and Dufour, Jean-François

Published
2022
Full Text
View/download PDF

46. Fonctions des néologismes formels en français dans le contexte multilingue et multiethnique du Burkina Faso

Author

Zoumbara, Célestin, Martin, Pierre, Zoumbara, Célestin, and Martin, Pierre

Abstract

En tant qu'unités linguistiques spécifiques, les néologismes formels remplissent une diversité de fonctions selon que l'on s'intéresse au français contemporain hexagonal ou à une variété de contact, où le français interagit localement avec une multiplicité de langues. Au Burkina Faso, par exemple, le français, ancienne langue officielle devenue langue de travail, cohabite avec près de soixante langues nationales ou ethniques, dont trois ont un statut véhiculaire (le jula, le moore et le fulfulde), de même qu'avec d'autres langues non africaines telles que l'anglais, l'allemand, l'espagnol, le chinois, etc. L'étude des néologismes doit alors prendre en compte le contexte social multilingue et multiethnique. La présente contribution suit une approche d'extraction automatique des néologismes, appelée Extranéo. Extranéo combine l'étiqueteur morphosyntaxique TreeTagger avec les lexiques DELA et Morphalou 1 pour identifier les néologismes candidats puis extrait les contextes d'apparition à l'aide de patrons morphosyntaxiques basés sur des marqueurs de glose. Appliquée à un corpus de 50 000 articles tirés des journaux en ligne lefaso.net, sidwaya.info et lobservateur.bf, parus entre 2011 et 2019, elle a permis d'extraire une liste de néologismes qui ont ensuite fait l'objet d'une analyse linguistique. Celle-ci s'est appuyée sur les outils de la lexicologie, de la morphologie et de la sociolinguistique. Les résultats de l'étude montrent que, en contexte burkinabè, les néologismes formels reflètent une centralité des langues nationales dans les échanges communicationnels, un contact linguistique et un enrichissement du lexique du français. L'étude permet d'enrichir la description des néologismes dans le contexte du français pratiqué au Burkina Faso.

Published
2024

49. Investigating the footprint of post-domestication dispersal on the diversity of modern European, African and Asian goats.

Author

Petretto, Elena, Dettori, Maria Luisa, Luigi-Sierra, María Gracia, Noce, Antonia, Pazzola, Michele, Vacca, Giuseppe Massimo, Molina, Antonio, Martínez, Amparo, Goyache, Félix, Carolan, Sean, Kijas, James, Guldbrandtsen, Bernt, Kantanen, Juha, Duby, Dylan, Martin, Pierre, Danchin, Coralie, Duclos, Delphine, Allain, Daniel, Arquet, Rémy, and Mandonnet, Nathalie

Subjects
GOAT breeds, GOATS, MICROSATELLITE repeats, PRINCIPAL components analysis, GENETIC variation, GENETIC distance
Abstract

Background: Goats were domesticated in the Fertile Crescent about 10,000 years before present (YBP) and subsequently spread across Eurasia and Africa. This dispersal is expected to generate a gradient of declining genetic diversity with increasing distance from the areas of early livestock management. Previous studies have reported the existence of such genetic cline in European goat populations, but they were based on a limited number of microsatellite markers. Here, we have analyzed data generated by the AdaptMap project and other studies. More specifically, we have used the geographic coordinates and estimates of the observed (Ho) and expected (He) heterozygosities of 1077 European, 1187 African and 617 Asian goats belonging to 38, 43 and 22 different breeds, respectively, to find out whether genetic diversity and distance to Ganj Dareh, a Neolithic settlement in western Iran for which evidence of an early management of domestic goats has been obtained, are significantly correlated. Results: Principal component and ADMIXTURE analyses revealed an incomplete regional differentiation of European breeds, but two genetic clusters representing Northern Europe and the British-Irish Isles were remarkably differentiated from the remaining European populations. In African breeds, we observed five main clusters: (1) North Africa, (2) West Africa, (3) East Africa, (4) South Africa, and (5) Madagascar. Regarding Asian breeds, three well differentiated West Asian, South Asian and East Asian groups were observed. For European and Asian goats, no strong evidence of significant correlations between Ho and He and distance to Ganj Dareh was found. In contrast, in African breeds we detected a significant gradient of diversity, which decreased with distance to Ganj Dareh. Conclusions: The detection of a genetic cline associated with distance to the Ganj Dareh in African but not in European or Asian goat breeds might reflect differences in the post-domestication dispersal process and subsequent migratory movements associated with the management of caprine populations from these three continents. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results