Retrieval of Remote Sensing Images with Pattern Spectra Descriptors

Autor: Petra Bosilj, Erchan Aptoula, Sébastien Lefèvre, Ewa Kijak

Publikováno v: ISPRS International Journal of Geo-Information, Vol 5, Iss 12, p 228 (2016)

The rapidly increasing volume of visual Earth Observation data calls for effective content based image retrieval solutions, specifically tailored for their high spatial resolution and heterogeneous content. In this paper, we address this issue with a

Externí odkaz: https://doaj.org/article/85fdf6ec34994006824d7b59e9164d52

AIP: Adversarial Interaction Priors for Multi-Agent Physics-based Character Control

Autor: Mohamed Younes, Ewa Kijak, Simon Malinowski, Richard Kulpa, Franck Multon

Publikováno v: SIGGRAPH Asia 2022-15th ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia
SIGGRAPH Asia 2022-15th ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia, Dec 2022, Daegu, South Korea., pp.2, SIGGRAPH Asia 2022 Posters. ⟨10.1145/3550082.3564207⟩

International audience; We address the problem of controlling and simulating interactions between multiple physics-based characters, using short unlabeled motion clips. We propose Adversarial Interaction Priors (AIP), a multi-agents generative advers

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5d83a9b0069f48f950e8deb80aa2db4e
https://doi.org/10.1145/3550082.3564207

PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided MCTS Decoding

Autor: Antoine Chaffin, Vincent Claveau, Ewa Kijak

Publikováno v: NAACL 2022-Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
NAACL 2022-Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jul 2022, Hybrid: Seattle, Washington + Online, United States. pp.1-15

Large language models (LM) based on Transformers allow to generate plausible long texts. In this paper, we explore how this generation can be further controlled at decoding time to satisfy certain constraints (e.g. being non-toxic, conveying certain

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b9c42e0c2302ade11cb92c77d6e4302f

Combining convolutional side-outputs for road image segmentation

Autor: Felipe A. L. Reis, Zenilton Kleber Gonçalves do Patrocínio, Ewa Kijak, Silvio Jamil Ferzoli Guimarães, Simon Malinowski, Raquel Almeida

Publikováno v: IJCNN 2019-International Joint Conference on Neural Networks
IJCNN 2019-International Joint Conference on Neural Networks, Jul 2019, Budapest, Hungary. pp.1-8, ⟨10.1109/IJCNN.2019.8851843⟩
IJCNN

Image segmentation consists in creating partitions within an image into meaningful areas and objects. It can be used in scene understanding and recognition, in fields like biology, medicine, robotics, satellite imaging, amongst others. In this work w

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::014269cc6477c7e3748f46a20e07a642
https://hal.inria.fr/hal-02370834/document

Fusion-based multimodal detection of hoaxes in social networks

Autor: Ewa Kijak, Cédric Maigrot, Vincent Claveau

Publikováno v: WI 2018-Web Intelligence Chile IEEE/WIC/ACM International Conference on Web Intelligence
WI 2018-Web Intelligence Chile IEEE/WIC/ACM International Conference on Web Intelligence, Dec 2018, Santiago, Chile. pp.1-8
WI

International audience; Social networks make it possible to share information rapidly and massively. Yet, one of their major drawback comes from the absence of verification of the piece of information, especially with viral messages. This is the issu

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6bd37bfc14009ed8cad158ad62935651
https://hal.science/hal-01936720/file/Claveau_WI2018.pdf