Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Yafu Xiao"'
Publikováno v:
Neurocomputing. 516:77-91
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f4173012e58fb8c4786b9fb4aa62c02e
https://doi.org/10.1016/j.neucom.2022.10.031
https://doi.org/10.1016/j.neucom.2022.10.031
Publikováno v:
Multimedia Tools and Applications. 79:25171-25188
Despite excellent performance shown by spatially regularized discriminative correlation filters (SRDCF) for visual tracking, some issues remain open that hinder further boosting their performance: first, SRDCF utilizes multiple training images to for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3ce5a80b24fb012d524038b99b3b296e
https://doi.org/10.1007/s11042-020-09028-9
https://doi.org/10.1007/s11042-020-09028-9
Publikováno v:
Multimedia Tools and Applications. 79:20521-20543
In recent years, many efficient and accurate algorithms have been proposed in the field of target tracking. The existing correlation filter(CF) based tracking expands the sample through cyclic shift and uses the position of the maximum response map a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a847c3c0fef38356e6facdbac65e9b2e
https://doi.org/10.1007/s11042-020-08839-0
https://doi.org/10.1007/s11042-020-08839-0
Face alignment in-the-wild still faces great challenges due to that i) partial occlusion blurs the inter-features spatial relations of faces and ii) traditional CNN makes the network more difficult to capture the spatial positional relations between
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ee455577baf0fbb2653b6c7a857abf3c
https://hdl.handle.net/10453/169110
https://hdl.handle.net/10453/169110
Object tracking is an essential and challenging sub-domain in the field of computer vision owing to its wide range of applications and complexities of real-life situations. It has been studied extensively over the last decade, leading to the proposal
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8f56459804f8ac17c80656404e4863b6
https://hdl.handle.net/10453/168116
https://hdl.handle.net/10453/168116
Publikováno v:
IJCNN
Recently, the Siamese Region Proposal Network (SiamRPN) has been widely explored in tracking and achieved remarkable performance. However, the existing SiamRPN-based method uses a predefined and highly dependent on prior knowledge anchor, which limit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c9307f9980ec2f6c2e520e9d672ea089
https://doi.org/10.1109/ijcnn52387.2021.9533985
https://doi.org/10.1109/ijcnn52387.2021.9533985
Publikováno v:
Neurocomputing. 358:119-140
With extensive applications, visual tracking has already become one of the most important research focuses in computer vision. Due to such interference as serious occlusion or severe illumination change and so on, the appearance model of the target t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::132ce6f1ac05e1c3b400378529d0851d
https://doi.org/10.1016/j.neucom.2019.05.017
https://doi.org/10.1016/j.neucom.2019.05.017
Publikováno v:
Frontiers of Computer Science. 14:417-429
Despite demonstrated success of SVM based trackers, their performance remains a boosting room if carefully considering the following factors: first, the tradeoff between sampling and budgeting samples affects tracking accuracy and efficiency much; se
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::96371fd19165f3126629661bc320e037
https://doi.org/10.1007/s11704-018-8116-1
https://doi.org/10.1007/s11704-018-8116-1
Publikováno v:
Neurocomputing. 329:227-236
The new cascaded shape regression architecture proposed in this paper is actually an algorithm by Component Adaptive Mechanism (CAM) to cope with unconstrained face alignment. CAM divides the process of face alignment into two parts: the updating pro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bde7611b1e8e2cf2e4edec9f382f74e0
https://doi.org/10.1016/j.neucom.2018.10.068
https://doi.org/10.1016/j.neucom.2018.10.068
Publikováno v:
IJCNN
Support correlation filter tracking method uses cyclic sampling to transform the calculation into frequency domain, which solves the problems of sampling and large computation of support vector machine. However, the current method can not exploit the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::16cae1e6fed34434bb8198c9fc3d5f99
https://doi.org/10.1109/ijcnn48605.2020.9207179
https://doi.org/10.1109/ijcnn48605.2020.9207179