Výsledky vyhledávání

Report

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

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

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 continuo

Externí odkaz: http://arxiv.org/abs/2204.08460

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Siamese Spatio-temporal convolutional neural network for stroke classification in Table Tennis games

Autor: Pierre-Etienne Martin, Benois-Pineau, J., Mansencal, B., Péteri, R., Morlier, J.

Publikováno v: MediaEval 2019 Workshop
MediaEval 2019 Workshop, Oct 2019, Sophia Antipolis, France
HAL
Scopus-Elsevier

International audience; This work presents a Table Tennis stroke classification approach through a siamese spatio-temporal convolutional neural network-SSTCNN. The videos are recorded at 120 frames per second with players performing in natural condit

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::1ff63f033ad79bc9b9c412d1644b54ee
https://hal.archives-ouvertes.fr/hal-02937668

Zobrazit plný text záznamu

Predicting Behavioural Patterns in Discussion Forums using Deep Learning on Hypergraphs

Autor: Arya, D., Rudinac, S., Worring, M., Gurrin, C., Jónsson, B.Þ., Péteri, R., Marchand-Maillet, S., Quénot, G., McGuinness, K., Guðmundsson, G.Þ., Little, S., Katsurai, M., Healy, G.

Publikováno v: 2019 International Conference on Content-Based Multimedia Indexing (CBMI): proceedings : September 4-6, 2019, held at: DCU All Hallows Campus, Dublin 9, Ireland, 210-215
STARTPAGE=210;ENDPAGE=215;TITLE=2019 International Conference on Content-Based Multimedia Indexing (CBMI)
CBMI

Online discussion forums provide open workspace allowing users to share information, exchange ideas, address problems, and form groups. These forums feature multimodal posts and analyzing them requires a framework that can integrate heterogeneous inf

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b5908e0080b449241def9795de767395
https://dare.uva.nl/personal/pure/en/publications/predicting-behavioural-patterns-in-discussion-forums-using-deep-learning-on-hypergraphs(b181bc7b-ceed-43c0-bc66-0b3b169a4e31).html

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání