Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Qishuo Lu"'
Publikováno v:
IET Computer Vision, Vol 13, Iss 6, Pp 562-568 (2019)
The receptive field size of a convolutional filter in a deep convolutional network is a crucial issue for object detection task, as the output must response to a suitable size of area in the image to capture proper information. Receptive field size o
Externí odkaz:
https://doaj.org/article/b45c454e0ce3456a999f34f3fb40e8f7
Publikováno v:
IEEE Access, Vol 6, Pp 12587-12597 (2018)
Video-based person reidentification (re-id) is a challenging problem due to much discrepancy between different videos by person pose, illumination, viewpoint change, background clutter, and occlusion within each camera and across different cameras. H
Externí odkaz:
https://doaj.org/article/78d074aa1df54c8a904d7692d09e9d3a
Publikováno v:
IEEE Access, Vol 5, Pp 24023-24031 (2017)
We propose an object detection system that depends on position-sensitive grid feature maps. State-of-the-art object detection networks rely on convolutional neural networks pre-trained on a large auxiliary data set (e.g., ILSVRC 2012) designed for an
Externí odkaz:
https://doaj.org/article/7ca3e812a0bd4509805bd1cc96d0bdbb
Autor:
Zhuqing Jiang, Qishuo Lu, Aidong Men, Shang-Hua Gao, Zhengxin Zeng, Qiulin Zhang, Jia'nan Han
Publikováno v:
IJCAI
Many effective solutions have been proposed to reduce the redundancy of models for inference acceleration. Nevertheless, common approaches mostly focus on eliminating less important filters or constructing efficient operations, while ignoring the pat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::87ab6b30bdd81fa8effb4f0decca24ec
http://arxiv.org/abs/2006.12085
http://arxiv.org/abs/2006.12085
Publikováno v:
IEEE Access, Vol 6, Pp 12587-12597 (2018)
Video-based person reidentification (re-id) is a challenging problem due to much discrepancy between different videos by person pose, illumination, viewpoint change, background clutter, and occlusion within each camera and across different cameras. H
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c9153093fe57acdc1bbcfbd319d7b228
https://doi.org/10.1109/access.2018.2803789
https://doi.org/10.1109/access.2018.2803789
Publikováno v:
IEEE Access, Vol 5, Pp 24023-24031 (2017)
We propose an object detection system that depends on position-sensitive grid feature maps. State-of-the-art object detection networks rely on convolutional neural networks pre-trained on a large auxiliary data set (e.g., ILSVRC 2012) designed for an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6bec1daeb3c0dc20877dd9823eeeefb9
https://doi.org/10.1109/access.2017.2770178
https://doi.org/10.1109/access.2017.2770178
Publikováno v:
Wireless Networks. 24:295-307
We present a fuzzy satellite routing strategy (FSRS) for NGEO satellite IP networks to meet multi-class QoS demands. A set of fuzzy rules is established to map the congestion degrees and the linguistic variables. For every queue in a satellite, an ou
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::386132563e548d2362ad8d308ba0b0f3
https://doi.org/10.1007/s11276-016-1326-8
https://doi.org/10.1007/s11276-016-1326-8