EnMcGAN: Adversarial Ensemble Learning for 3D Complete Renal Structures Segmentation - Université de Rennes Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

EnMcGAN: Adversarial Ensemble Learning for 3D Complete Renal Structures Segmentation

Résumé

Unlabelled - Analysts of social media differ in their emphasis on the effects of message content versus social network structure. The balance of these factors may change substantially across time. When a major event occurs, initial independent reactions may give way to more social diffusion of interpretations of the event among different communities, including those committed to disinformation. Here, we explore these dynamics through a case study analysis of the Russian-language Twitter content emerging from Belarus before and after its presidential election of August 9, 2020. From these Russian-language tweets, we extracted a set of topics that characterize the social media data and construct networks to represent the sharing of these topics before and after the election. The case study in Belarus reveals how misinformation can be re-invigorated in discourse through the novelty of a major event. More generally, it suggests how audience networks can shift from influentials dispensing information before an event to a de-centralized sharing of information after it. Supplementary information - The online version contains supplementary material available at 10.1007/s43545-022-00330-x.

Dates et versions

hal-03334184 , version 1 (03-09-2021)

Identifiants

Citer

Y. He, R. Ge, X. Qi, G. Yang, Y. Chen, et al.. EnMcGAN: Adversarial Ensemble Learning for 3D Complete Renal Structures Segmentation. 27th International Conference on Information Processing in Medical Imaging, IPMI 2021, Jun 2021, Bornholm, Denmark. pp.465-477, ⟨10.1007/978-3-030-78191-0_36⟩. ⟨hal-03334184⟩
18 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More