SMC Faster R-CNN: Toward a scene-specialized multi-object detector

Autor: Mhalla, Ala, Chateau, Thierry, Maamatou, Houda, Gazzah, Sami, Amara, Najoua Essoukri Ben

Generally, the performance of a generic detector decreases significantly when it is tested on a specific scene due to the large variation between the source training dataset and the samples from the target scene. To solve this problem, we propose a n

Externí odkaz: http://arxiv.org/abs/1706.10217

Semi-supervised learning for multi-object detection in video sequences : Application to the analysis of urban flow

Autor: Maâmatou , Houda

Publikováno v: Vision par ordinateur et reconnaissance de formes [cs.CV]. Université Clermont Auvergne, 2017. Français. 〈NNT : 2017CLFAC015〉
Vision par ordinateur et reconnaissance de formes [cs.CV]. Université Clermont Auvergne [2017-2020]; Université de Sfax (Tunisie), 2017. Français. ⟨NNT : 2017CLFAC015⟩

Since 2000, a significant progress has been recorded in research work which has proposed to learn object detectors using large manually labeled and publicly available databases. However, when a generic object detector is applied on images of a specif

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::1da860941bee2461e2b32fee1611c175
https://tel.archives-ouvertes.fr/tel-01809530/document

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