Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Mahdi Abavisani"'
Autor:
Vishal M. Patel, Mahdi Abavisani
Publikováno v:
IEEE Signal Processing Letters. 26:948-952
We present a transductive deep learning-based formulation for the sparse representation-based classification (SRC) method. The proposed network consists of a convolutional autoencoder along with a fully connected layer. The role of the autoencoder ne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f847d1840825cc4c544bb0cd756b4068
https://doi.org/10.1109/lsp.2019.2913022
https://doi.org/10.1109/lsp.2019.2913022
Autor:
Vishal M. Patel, Mahdi Abavisani
Publikováno v:
ICIP
In this paper, we present a deep sparse representation based fusion method for classifying multimodal signals. Our proposed model consists of multimodal encoders and decoders with a shared fully-connected layer. The multimodal encoders learn separate
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ce61937462ce0ed61156a191dae3cb98
https://doi.org/10.1109/icip40778.2020.9191317
https://doi.org/10.1109/icip40778.2020.9191317
Publikováno v:
CVPR
Recent developments in image classification and natural language processing, coupled with the rapid growth in social media usage, have enabled fundamental advances in detecting breaking events around the world in real-time. Emergency response is one
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::99231d3b419ea3b473830634f1296de4
http://arxiv.org/abs/2004.04917
http://arxiv.org/abs/2004.04917
Autor:
Vishal M. Patel, Mahdi Abavisani
Publikováno v:
Information Fusion. 39:168-177
In this paper, we propose multimodal extensions of the recently introduced sparse subspace clustering (SSC) and low-rank representation (LRR) based subspace clustering algorithms for clustering data lying in a union of subspaces. Given multimodal dat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8cc54a67a2ef65757bde149a8081f6c6
https://doi.org/10.1016/j.inffus.2017.05.002
https://doi.org/10.1016/j.inffus.2017.05.002
Publikováno v:
CVPR
We present an efficient approach for leveraging the knowledge from multiple modalities in training unimodal 3D convolutional neural networks (3D-CNNs) for the task of dynamic hand gesture recognition. Instead of explicitly combining multimodal inform
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c9b7b271a1cc71d5b5e8a106846c5678
https://doi.org/10.1109/cvpr.2019.00126
https://doi.org/10.1109/cvpr.2019.00126
Autor:
Vishal M. Patel, Mahdi Abavisani
Publikováno v:
ISBA
We propose a novel method for clustering a collection of data that comes from several domains. Since members of the same class might look very different across different domains and because in a clustering problem we have no side information such as
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dee5aa7bd4af97b492dad0ce8ce85a2c
https://doi.org/10.1109/isba.2018.8311478
https://doi.org/10.1109/isba.2018.8311478
Autor:
Vishal M. Patel, Mahdi Abavisani
We present convolutional neural network (CNN) based approaches for unsupervised multimodal subspace clustering. The proposed framework consists of three main stages - multimodal encoder, self-expressive layer, and multimodal decoder. The encoder take
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4325214e50254a2df4b5f73b5e712beb
Publikováno v:
ICPR
In unsupervised image-to-image translation, the goal is to learn the mapping between an input image and an output image using a set of unpaired training images. In this paper, we propose an extension of the unsupervised image-to-image translation pro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fa5bb4fb8930bdfdc7c4f96bc5b5dcbf
Autor:
Shaban Mehrvarz, Mahdi Abavisani, Saieed Derakhshani, Seyed Mohsen Towliat, Hassan Ali Mohebbi
Publikováno v:
Iranian Red Crescent Medical Journal
Background The tendency towards sphincter preserving for low rectal cancers with low anterior resection, has led to the technique of straight coloanal anastomosis (SCAA) or colonic J-pouch anal anastomosis (CPAA). Objectives The aim of our study was
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a975e36bbb2adc09aa750779f6b0a86e
https://doi.org/10.5812/ircmj.3804
https://doi.org/10.5812/ircmj.3804