Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Mojtaba Seyedhosseini"'
Publikováno v:
Neurocomputing. 218:276-285
Artificial neural networks are powerful pattern classifiers. They form the basis of the highly successful and popular Convolutional Networks which offer the state-of-the-art performance on several computer visions tasks. However, in many general and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::60a6a206f7d4101fa5ae17ed77e3c21a
https://doi.org/10.1016/j.neucom.2016.08.047
https://doi.org/10.1016/j.neucom.2016.08.047
Publikováno v:
IEEE Signal Processing Letters. 22:1011-1015
We introduce a novel general regression model that is based on a linear combination of a new set of non-local basis functions that forms an effective feature space. We propose a training algorithm that learns all the model parameters simultaneously a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::365035d31265f488ac1b2e2df25c9774
https://doi.org/10.1109/lsp.2014.2380791
https://doi.org/10.1109/lsp.2014.2380791
Autor:
Tolga Tasdizen, Mojtaba Seyedhosseini
Publikováno v:
Pattern Recognition. 48:976-983
We develop a novel supervised learning/classification method, called disjunctive normal random forest (DNRF). A DNRF is an ensemble of randomly trained disjunctive normal decision trees (DNDT). To construct a DNDT, we formulate each decision tree in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8dca9765735e7a09b6ba037a0504fccb
https://doi.org/10.1016/j.patcog.2014.08.023
https://doi.org/10.1016/j.patcog.2014.08.023
Autor:
Mojtaba Seyedhosseini, Tolga Tasdizen
Publikováno v:
IEEE Transactions on Image Processing. 22:4486-4496
Contextual information has been widely used as a rich source of information to segment multiple objects in an image. A contextual model uses the relationships between the objects in a scene to facilitate object detection and segmentation. Using conte
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7911e8562251bda85e21d0ae8a69eb88
https://doi.org/10.1109/tip.2013.2274388
https://doi.org/10.1109/tip.2013.2274388
Autor:
Dan Ciresan, Dmitry Laptev, H. Sebastian Seung, Albert Cardona, Radim Burget, Alessandro Giusti, Johannes Schindelin, Luca Maria Gambardella, Lee Kamentsky, Tolga Tasdizen, Joachim M. Buhmann, Mojtaba Seyedhosseini, Ignacio Arganda-Carreras, Mustafa Gökhan Uzunbas, Ting Liu, Jürgen Schmidhuber, Vaclav Uher, Tuan D. Pham, Changming Sun, Daniel R. Berger, Srinivas C. Turaga, Erhan Bas, Sarvesh Dwivedi, Xiao Tan
Publikováno v:
Frontiers in Neuroanatomy, Vol 9 (2015)
Frontiers in Neuroanatomy
Frontiers in Neuroanatomy, Frontiers, 2015, 9, pp.142. ⟨10.3389/fnana.2015.00142⟩
Frontiers in Neuroanatomy (9), 142. (2015)
Frontiers in Neuroanatomy, 9
Frontiers
Frontiers in Neuroanatomy
Frontiers in Neuroanatomy, Frontiers, 2015, 9, pp.142. ⟨10.3389/fnana.2015.00142⟩
Frontiers in Neuroanatomy (9), 142. (2015)
Frontiers in Neuroanatomy, 9
Frontiers
To stimulate progress in automating the reconstruction of neural circuits, we organized the first international challenge on 2D segmentation of electron microscopic (EM) images of the brain. Participants submitted boundary maps predicted for a test s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bc28170091bbaac2167bf8d717747565
Autor:
Mojtaba Seyedhosseini, Tolga Tasdizen
Semantic segmentation is the problem of assigning an object label to each pixel. It unifies the image segmentation and object recognition problems. The importance of using contextual information in semantic segmentation frameworks has been widely rea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::18faad6b8f8950fcfacee7d4c0691284
https://europepmc.org/articles/PMC4844369/
https://europepmc.org/articles/PMC4844369/
This paper investigates one of the most fundamental computer vision problems: image segmentation. We propose a supervised hierarchical approach to object-independent image segmentation. Starting with over-segmenting superpixels, we use a tree structu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e0eafc7b81a291adf116258d6035a9fd
Autor:
Bradley Greger, Tyler S. Davis, Tolga Tasdizen, S. Shushruth, Mojtaba Seyedhosseini, Paul A. House, Alessandra Angelucci, Jennifer M. Ichida
The local field potential (LFP) is of growing importance in neurophysiology as a metric of network activity and as a readout signal for use in brain-machine interfaces. However, there are uncertainties regarding the kind and visual field extent of in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eb8a47e77df97f740496dde88de3b4f2
https://europepmc.org/articles/PMC4346719/
https://europepmc.org/articles/PMC4346719/
Publikováno v:
ICIP
Automated electron microscopy (EM) image analysis techniques can be tremendously helpful for connectomics research. In this paper, we extend our previous work [1] and propose a fully automatic method to utilize inter-section information for intra-sec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0537497a3d242c3ca0d8cc77759d8a8a
https://pubmed.ncbi.nlm.nih.gov/25484631
https://pubmed.ncbi.nlm.nih.gov/25484631
Publikováno v:
ICCV
Contextual information plays an important role in solving vision problems such as image segmentation. However, extracting contextual information and using it in an effective way remains a difficult problem. To address this challenge, we propose a mul
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::11e913a7f093f8d2b4168cd32e522a1e
https://pubmed.ncbi.nlm.nih.gov/25419193
https://pubmed.ncbi.nlm.nih.gov/25419193