Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Joe Mathai"'
Autor:
Gourav Datta, Souvik Kundu, Zihan Yin, Ravi Teja Lakkireddy, Joe Mathai, Ajey P. Jacob, Peter A. Beerel, Akhilesh R. Jaiswal
Publikováno v:
Scientific Reports, Vol 12, Iss 1, Pp 1-16 (2022)
Abstract The demand to process vast amounts of data generated from state-of-the-art high resolution cameras has motivated novel energy-efficient on-device AI solutions. Visual data in such cameras are usually captured in analog voltages by a sensor p
Externí odkaz:
https://doaj.org/article/eee7c4ebf07a4b1bac052f4567cc4578
Autor:
Gourav Datta, Souvik Kundu, Zihan Yin, Joe Mathai, Zeyu Liu, Zixu Wang, Mulin Tian, Shunlin Lu, Ravi Teja Lakkireddy, Andrew Schmidt, Wael Abd-Almageed, Ajey Jacob, Akhilesh Jaiswal, Peter Beerel
Publikováno v:
2022 IFIP/IEEE 30th International Conference on Very Large Scale Integration (VLSI-SoC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::11946eba08b2cb398c1519fe869c2002
https://doi.org/10.1109/vlsi-soc54400.2022.9939582
https://doi.org/10.1109/vlsi-soc54400.2022.9939582
Autor:
Gourav Datta, Zeyu Liu, Md Abdullah-Al Kaiser, Souvik Kundu, Joe Mathai, Zihan Yin, Ajey P. Jacob, Akhilesh R. Jaiswal, Peter A. Beerel
Due to the high activation sparsity and use of accumulates (AC) instead of expensive multiply-and-accumulates (MAC), neuromorphic spiking neural networks (SNNs) have emerged as a promising low-power alternative to traditional DNNs for several compute
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f7c92d8fd56c5b8164abf2b5fc7f254e
Advances in deep learning, combined with availability of large datasets, have led to impressive improvements in face presentation attack detection research. However, state-of-the-art face antispoofing systems are still vulnerable to novel types of at
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a7a985738fa167c1def4810933243205
http://arxiv.org/abs/2108.12081
http://arxiv.org/abs/2108.12081
Publikováno v:
CVPR
Face segmentation is the task of densely labeling pixels on the face according to their semantics. While current methods place an emphasis on developing sophisticated architectures, use conditional random fields for smoothness, or rather employ adver
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7e3beaf806d182b2b6192aa36068f21e
http://hdl.handle.net/11573/1458946
http://hdl.handle.net/11573/1458946
Autor:
Sébastien Marcel, Oswin G. Almeida, Mohamed E. Hussein, David Geissbühler, Leonidas Spinoulas, Guillaume Clivaz, Wael AbdAlmageed, Joe Mathai
In this work, we present a general framework for building a biometrics system capable of capturing multispectral data from a series of sensors synchronized with active illumination sources. The framework unifies the system design for different biomet
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b252b0a4b0d5d4900b351bc1b8dce119
Publikováno v:
ICB
Face occlusions, covering either the majority or discriminative parts of the face, can break facial perception and produce a drastic loss of information. Biometric systems such as recent deep face recognition models are not immune to obstructions or
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d041448b1cec18a0e3278666993b7de3
http://arxiv.org/abs/1906.02858
http://arxiv.org/abs/1906.02858
Publikováno v:
ASAR
Modern CRNN OCR models require a fixed line height for all images, and it is known that, up to a point, increasing this input resolution improves recognition performance. However, doing so by simply increasing the line height of input images without
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9cf3cdb0825014272680d191ed08ea39
https://doi.org/10.1109/asar.2018.8480182
https://doi.org/10.1109/asar.2018.8480182