Détail de l'auteur
Auteur Ning Wang |
Documents disponibles écrits par cet auteur (2)
![](./images/expand_all.gif)
![](./images/collapse_all.gif)
![Tris disponibles](./images/orderby_az.gif)
Unsupervised deep representation learning for real-time tracking / Ning Wang in International journal of computer vision, vol 129 n° 2 (February 2021)
![]()
[article]
Titre : Unsupervised deep representation learning for real-time tracking Type de document : Article/Communication Auteurs : Ning Wang, Auteur ; Wengang Zhou, Auteur ; Yibing Song, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 400 - 418 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] appariement d'images
[Termes IGN] apprentissage profond
[Termes IGN] classification non dirigée
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] détection de cible
[Termes IGN] filtre
[Termes IGN] objet mobile
[Termes IGN] oculométrie
[Termes IGN] reconnaissance d'objets
[Termes IGN] réseau neuronal siamois
[Termes IGN] temps réel
[Termes IGN] traçage
[Termes IGN] trajectoire (véhicule non spatial)
[Termes IGN] vision par ordinateurRésumé : (auteur) The advancement of visual tracking has continuously been brought by deep learning models. Typically, supervised learning is employed to train these models with expensive labeled data. In order to reduce the workload of manual annotation and learn to track arbitrary objects, we propose an unsupervised learning method for visual tracking. The motivation of our unsupervised learning is that a robust tracker should be effective in bidirectional tracking. Specifically, the tracker is able to forward localize a target object in successive frames and backtrace to its initial position in the first frame. Based on such a motivation, in the training process, we measure the consistency between forward and backward trajectories to learn a robust tracker from scratch merely using unlabeled videos. We build our framework on a Siamese correlation filter network, and propose a multi-frame validation scheme and a cost-sensitive loss to facilitate unsupervised learning. Without bells and whistles, the proposed unsupervised tracker achieves the baseline accuracy of classic fully supervised trackers while achieving a real-time speed. Furthermore, our unsupervised framework exhibits a potential in leveraging more unlabeled or weakly labeled data to further improve the tracking accuracy. Numéro de notice : A2021-353 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1007/s11263-020-01357-4 Date de publication en ligne : 21/09/2020 En ligne : https://doi.org/10.1007/s11263-020-01357-4 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97604
in International journal of computer vision > vol 129 n° 2 (February 2021) . - pp 400 - 418[article]A bootstrap test for constant coefficients in geographically weighted regression models / Chang-Lin Mei in International journal of geographical information science IJGIS, vol 30 n° 7- 8 (July - August 2016)
![]()
[article]
Titre : A bootstrap test for constant coefficients in geographically weighted regression models Type de document : Article/Communication Auteurs : Chang-Lin Mei, Auteur ; Min Xu, Auteur ; Ning Wang, Auteur Année de publication : 2016 Article en page(s) : pp 1622 - 1643 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Statistiques
[Termes IGN] base de données déductive
[Termes IGN] Bootstrap (EDI)
[Termes IGN] inférence statistique
[Termes IGN] modèle de régression
[Termes IGN] processeur
[Termes IGN] régression géographiquement pondérée
[Termes IGN] test de performanceRésumé : (Auteur) Statistical tests for whether some coefficients really vary over space play an important role in using the geographically weighted regression (GWR) to explore spatial non-stationarity of the regression relationship. In view of some shortcomings of the existing inferential methods, we propose a residual-based bootstrap test to detect the constant coefficients in a GWR model. The proposed test is free of the assumption that the model error term is normally distributed and admits some useful extensions for identifying more complicated spatial patterns of the coefficients. Some simulation with comparison to the existing test methods is conducted to assess the test performance, including the accuracy of the bootstrap approximation to the null distribution of the test statistic, the power in identifying spatially varying coefficients and the robustness to collinearity among the explanatory variables. The simulation results demonstrate that the bootstrap test works quite well. Furthermore, a real-world data set is analyzed to illustrate the application of the proposed test. Numéro de notice : A2016-320 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/INFORMATIQUE/MATHEMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2016.1149181 En ligne : http://dx.doi.org/10.1080/13658816.2016.1149181 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=80940
in International journal of geographical information science IJGIS > vol 30 n° 7- 8 (July - August 2016) . - pp 1622 - 1643[article]Exemplaires(2)
Code-barres Cote Support Localisation Section Disponibilité 079-2016042 RAB Revue Centre de documentation En réserve L003 Disponible 079-2016041 RAB Revue Centre de documentation En réserve L003 Disponible