Modèles d'attention visuelle pour l'analyse de scènes dynamiques

Autor: Muddamsetty, Satya Mahesh

De nombreuses applications de la vision par ordinateur requièrent la détection, la localisation et le suivi de régions ou d’objets d’intérêt dans une image ou une séquence d’images. De nombreux modèles d’attention visuelle, inspirés d

Externí odkaz: http://www.theses.fr/2014DIJOS067/document

Expert level evaluations for explainable AI (XAI) methods in the medical domain

Autor: Muddamsetty, Satya Mahesh, Jahromi, Mohammad Naser Sabet, Moeslund, Thomas B.

Publikováno v: Muddamsetty, S M, Jahromi, M N S & Moeslund, T B 2021, Expert level evaluations for explainable AI (XAI) methods in the medical domain . in A Del Bimbo, R Cucchiara, S Sclaroff, G M Farinella, T Mei, M Bertini, H J Escalante & R Vezzani (eds), Pattern Recognition. ICPR International Workshops and Challenges . vol. 12663, Springer Publishing Company, Lecture Notes in Computer Science, pp. 35-46, Pattern Recognition. ICPR International Workshops and Challenges, 10/01/2021 . https://doi.org/10.1007/978-3-030-68796-0_3

The recently emerged field of explainable artificial intelligence (XAI) attempts to shed lights on 'black box' Machine Learning (ML) models in understandable terms for human. As several explanation methods are developed alongside different applicatio

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::bbf20a484c81dbe56ec8d05e3d674692
https://vbn.aau.dk/da/publications/80e1b29a-b04c-4548-a8fc-06c35ae94308

Spatio-temporal saliency detection in dynamic scenes using color and texture features

Autor: Muddamsetty, Satya Mahesh

Visual saliency is an important research topic in the field of computer vision due to its numerouspossible applications. It helps to focus on regions of interest instead of processingthe whole image or video data. Detecting visual saliency in still i

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______3711::0eb22922ea33182bb9e78817742e1852
https://theses.hal.science/tel-01198664