Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Syed Sameed Husain"'
Autor:
Syed Sameed Husain, Eng-Jon Ong, Dmitry Minskiy, Mikel Bober-Irizar, Amaia Irizar, Miroslaw Bober
Publikováno v:
Communications Biology, Vol 6, Iss 1, Pp 1-14 (2023)
Abstract Unravelling protein distributions within individual cells is vital to understanding their function and state and indispensable to developing new treatments. Here we present the Hybrid subCellular Protein Localiser (HCPL), which learns from w
Externí odkaz:
https://doaj.org/article/6b31d30808374001bc42a3ec7e80045b
Publikováno v:
Multimedia Tools and Applications. 81:20425-20441
Autor:
Syed Sameed Husain, Eng-Jon Ong, Dmitry Minskiy, Mikel Bober-Irizar, Amaia Irizar, Miroslaw Bober
Unravelling protein distributions within individual cells is vital to understanding their function and state and indispensable to developing new treatments. Here we present the Hybrid subCellular Protein Localiser (HCPL), which learns from weakly lab
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a858ded851ccffd864f200e89523da56
http://arxiv.org/abs/2205.09841
http://arxiv.org/abs/2205.09841
Publikováno v:
Signal, Image and Video Processing. 13:439-445
Widespread high dynamic range (HDR) video distribution via transmission and broadcast is imminent in the near future. However, the rate control (RC) algorithms in video coding standards, like high-efficiency video coding (HEVC), are optimized and des
Autor:
Miroslaw Bober, Syed Sameed Husain
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 39:1783-1796
Visual search and image retrieval underpin numerous applications, however the task is still challenging predominantly due to the variability of object appearance and ever increasing size of the databases, often exceeding billions of images. Prior art
Autor:
Syed Sameed Husain, Miroslaw Bober
Publikováno v:
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society.
This paper addresses the problem of very large-scale image retrieval, focusing on improving its accuracy and robustness. We target enhanced robustness of search to factors such as variations in illumination, object appearance and scale, partial occlu
Autor:
Qiuqiang Kong, Miroslaw Bober, Cemre Zor, Christian Kroos, Syed Sameed Husain, Muhammad Awais, Josef Kittler
Publikováno v:
ICASSP
In this paper, we address the problem of bird audio detection and propose a new convolutional neural network architecture together with a divergence based information channel weighing strategy in order to achieve improved state-of-the-art performance
We propose a novel CNN architecture called ACTNET for robust instance image retrieval from large-scale datasets. Our key innovation is a learnable activation layer designed to improve the signal-to-noise ratio of deep convolutional feature maps. Furt
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ea7b6a3b6ac3cd8cea52989dc2af562c
This work addresses the problem of accurate semantic labelling of short videos. To this end, a multitude of different deep nets, ranging from traditional recurrent neural networks (LSTM, GRU), temporal agnostic networks (FV,VLAD,BoW), fully connected
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0283704e0a05c5d1817d0e7924a94e93
Autor:
Syed Sameed Husain, Miroslaw Bober
Publikováno v:
ICME Workshops
This paper addresses the problem of aggregating local binary descriptors for large scale image retrieval in mobile scenarios. Binary descriptors are becoming increasingly popular, especially in mobile applications, as they deliver high matching speed
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b194d5e749d2e839fb42f68cd694e965
https://surrey.eprints-hosting.org/811329/
https://surrey.eprints-hosting.org/811329/