Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Hossein Ghanei-Yakhdan"'
Publikováno v:
Multimedia Tools and Applications. 80:22027-22076
Due to the automatic feature extraction procedure via multi-layer nonlinear transformations, the deep learning-based visual trackers have recently achieved a great success in challenging scenarios for visual tracking purposes. Although many of those
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a010c69ce20da20944c556f859562582
https://doi.org/10.1007/s11042-020-10382-x
https://doi.org/10.1007/s11042-020-10382-x
Publikováno v:
The Visual Computer. 38:849-869
Sparsity-based trackers describe a candidate region by solving the $${l}_{1}$$ minimization problem. This process is done for many candidates generated in a particle filter framework. This results in a high computational cost, and thus it can preclud
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::91c2bdc7014cba5f21cbdec0e8ff24af
https://doi.org/10.1007/s00371-020-02055-5
https://doi.org/10.1007/s00371-020-02055-5
Publikováno v:
Multimedia Tools and Applications. 80:12335-12365
Video compression makes the encoded video stream more vulnerable to the channel errors so that, the quality of the received video is exposed to severe degradation when the compressed video is transmitted over the error-prone environments. Therefore,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a89e36bba54bfa90181c6e3857134122
https://doi.org/10.1007/s11042-020-10290-0
https://doi.org/10.1007/s11042-020-10290-0
Publikováno v:
Neural Computing and Applications. 33:8319-8334
In recent years, visual tracking methods that are based on discriminative correlation filters (DCFs) have been very promising. However, most of these methods suffer from a lack of robust scale estimation skills. Although a wide range of recent DCF-ba
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8406485bfe13eaffc4b331f03d4cab2a
https://doi.org/10.1007/s00521-020-05586-z
https://doi.org/10.1007/s00521-020-05586-z
Publikováno v:
The Visual Computer. 36:701-715
In this paper, a tracker scheme is proposed that not only can face object tracking challenges but also can estimate object positions over occluded frames. In the proposed scheme, kernelized correlation filter (KCF) is considered as our basic tracker
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::057f6bdc65dcad9d760908c181d26d68
https://doi.org/10.1007/s00371-019-01652-3
https://doi.org/10.1007/s00371-019-01652-3
Autor:
Shohreh Kasaei, Javad Khaghani, Seyed Mojtaba Marvasti-Zadeh, Hossein Ghanei-Yakhdan, Li Cheng
Publikováno v:
Computer Vision – ACCV 2020 ISBN: 9783030695316
ACCV (2)
ACCV (2)
We consider the problem of tracking an unknown small target from aerial videos of medium to high altitudes. This is a challenging problem, which is even more pronounced in unavoidable scenarios of drastic camera motion and high density. To address th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f15edd188afb01f4499b0232dd3e8f06
https://doi.org/10.1007/978-3-030-69532-3_36
https://doi.org/10.1007/978-3-030-69532-3_36
Autor:
Shohreh Kasaei, Hossein Ghanei-Yakhdan, Seyed Mojtaba Marvasti-Zadeh, Kamal Nasrollahi, Thomas B. Moeslund
Publikováno v:
Zadeh, S M M, Ghanei-Yakhdan, H, Kasaei, S, Nasrollahi, K & Moeslund, T B 2022, ' Effective Fusion of Deep Multitasking Representations for Robust Visual Tracking ', Visual Computer, vol. 38, no. 12, pp. 4397-4417 . https://doi.org/10.1007/s00371-021-02304-1
Visual object tracking remains an active research field in computer vision due to persisting challenges with various problem-specific factors in real-world scenes. Many existing tracking methods based on discriminative correlation filters (DCFs) empl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::23f57574245b0209fdee423c2f8a593d
Autor:
Shohreh Kasaei, Shaochuan Zhao, Zhen-Hua Feng, Shuhao Chen, Xiaojun Wu, Rama Krishna Sai Subrahmanyam Gorthi, Jianlong Fu, Gustavo Fernandez, Wei Lu, Roman Pflugfelder, Haibin Ling, Yuzhang Gu, Kenan Dai, Hui Li, Martin Danelljan, Felix Järemo Lawin, Jiaqian Yu, Xiaoyun Yang, Yingming Wang, Jinyu Yang, Yuncon Yao, Gian Luca Foresti, Bedirhan Uzun, Xue-Feng Zhu, Heng Fan, Haoran Bai, Houqiang Li, Alexander G. Hauptmann, Thomas B. Schön, Guangqi Chen, Mohana Murali Dasari, Ziang Ma, Pengyu Zhang, Joni-Kristian Kamarainen, Dong Wang, Yunsung Lee, Fei Wang, Fredrik K. Gustafsson, Bin Yan, Ondrej Drbohlav, Song Yan, Fei Xie, Linyuan Wang, Michael Felsberg, Alan Lukežič, Christian Micheloni, Wengang Zhou, Yingjie Jiang, Kaicheng Yu, Chen Qian, Yu Ye, Haojie Zhao, Seyed Mojtaba Marvasti-Zadeh, Huchuan Lu, Bing Li, Jingtao Xu, Jesús Bescós, Matej Kristan, Tianyang Xu, Yushan Zhang, Hasan Saribas, Linbo He, Xiaolin Zhang, Kaiwen Liu, Jun Yin, Lijun Wang, Hakan Cevikalp, Alireza Memarmoghadam, Seokeon Choi, Alvaro Garcia-Martin, Awet Haileslassie Gebrehiwot, Zezhou Wang, Junhyun Lee, Ning Wang, Luca Bertinetto, Hari Chandana Kuchibhotla, Javad Khaghani, Anton Varfolomieiev, Luc Van Gool, Jiří Matas, Josef Kittler, Kang Yang, Xi Qiu, Philip H. S. Torr, Haitao Zhang, Xiao Ke, Ales Leonardis, Weiming Hu, Radu Timofte, Chi-Yi Tsai, Shoumeng Qiu, Zhipeng Zhang, Hossein Ghanei-Yakhdan, Houwen Peng, Luka Čehovin Zajc, Qiang Wang, Andreas Robinson, Matteo Dunnhofer, Yiwei Chen, Zhirong Wu, Jianhua Li, Miao Cheng, Yuezhou Li, Goutam Bhat, Zhijun Mai, Zhangyong Tang, Li Zhang, Li Cheng
Publikováno v:
Computer Vision – ECCV 2020 Workshops ISBN: 9783030682378
ECCV Workshops (5)
ECCV Workshops (5)
The Visual Object Tracking challenge VOT2020 is the eighth annual tracker benchmarking activity organized by the VOT initiative. Results of 58 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::722c41ae8bc63845cb1731bcc91fd851
http://hdl.handle.net/11390/1205562
http://hdl.handle.net/11390/1205562
Visual target tracking is one of the most sought-after yet challenging research topics in computer vision. Given the ill-posed nature of the problem and its popularity in a broad range of real-world scenarios, a number of large-scale benchmark datase
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::676ad2910573652ed46e2eea11fb6d19
Publikováno v:
Volume: 24, Issue: 6 5195-5209
Turkish Journal of Electrical Engineering and Computer Science
Turkish Journal of Electrical Engineering and Computer Science
Nowadays some systems such as multimedia systems try to present a high quality of digital videos every day. Because of the possible errors in communication channels, compressed video data would be damaged in the sending process. Error concealment is
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5f16167a128ff1c062b35bdedb778e72
https://doi.org/10.3906/elk-1409-88
https://doi.org/10.3906/elk-1409-88