Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Alan Lukezic"'
Publikováno v:
Sensors, Vol 20, Iss 2, p 566 (2020)
Although recently developed trackers have shown excellent performance even when tracking fast moving and shape changing objects with variable scale and orientation, the trackers for the electro-optical targeting systems (EOTS) still suffer from abrup
Externí odkaz:
https://doaj.org/article/70abe692b4834f1fb27afd3bd8c31c68
Autor:
Philip H. S. Torr, Haitao Zhang, Bin Yan, Ziyi Cheng, Fahad Shahbaz Khan, Shoumeng Qiu, Bineng Zhong, Ondrej Drbohlav, Bo Liu, Ozgun Cirakman, Kristian Simonato, Danda Pani Paudel, Xin Chen, Xiangyuan Lan, Wei Lu, Martin Danelljan, Felix Järemo Lawin, Qing Guo, Luka Čehovin Zajc, Christoph Mayer, Xiao Ke, Wankou Yang, Yanyan Huang, Xiaoning Song, Dong Wang, Felix Juefei-Xu, Xue-Feng Zhu, Guangting Wang, Jingen Liu, Jani Käpylä, Ales Leonardis, Christian Micheloni, Paul Voigtlaender, Yu-Chen Chiu, Lijun Wang, Shengyong Chen, Linyuan Wang, Shaochuan Zhao, Ling Shao, Yong Wang, Li Liu, Xiaoyun Yang, Liangliang Wang, Rongrong Ji, Gustavo Fernandez, Bilge Gunsel, Xingping Dong, Fei Xie, Jun Yin, Zhangyong Tang, Michael Felsberg, Aravindh Rajiv, Andreas Robinson, Miao Cheng, Mohana Murali Dasari, Josef Kittler, Chang Liu, Wencheng Han, Zhongqun Zhang, Yuezhou Li, Bedirhan Uzun, Roman Pflugfelder, Jinyu Yang, Yu Ye, Goutam Bhat, Kangkai Zhang, Hui Li, Jiri Matas, Mohamed H. Abdelpakey, Zhen-Hua Feng, Hyung Jin Chang, Ming Zhen, Matteo Dunnhofer, Xianxian Li, Yingjie Jiang, Luc Van Gool, Matej Kristan, Xiang Xu, Bastian Leibe, Xinyu Zhang, Filiz Gurkan, Jun Ha Lee, Yunhong Wang, Niki Martinel, Shang-Jhih Jhang, Yin Jun, Jianhua Li, Chengwei Zhang, Cheng Jiang, Muhammad Rana, Jie Ma, Houwen Peng, Gustav Häger, Zhiyong Feng, Wanli Xue, Gangshan Wu, Joni-Kristian Kamarainen, Zhibin Zhang, Alireza Memarmoghadam, Qili Deng, Daniel K. Du, Shiming Ge, Mohamed Shehata, Zhihong Fu, Chunhui Zhang, Yuzhen Niu, Xiaojun Wu, Rama Krishna Sai Subrahmanyam Gorthi, Hasan Saribas, Yuzhang Gu, Kenan Dai, Furao Shen, Qingjie Liu, Byeong Hak Kim, Hakan Cevikalp, Llukman Cerkezi, Jianbing Shen, Chenyan Wu, Alan Lukezic, Jiawen Zhu, Ziang Ma, Xiaohan Zhang, Limin Wang, Radu Timofte, Chi-Yi Tsai, Song Yan, Jonathon Luiten, Huchuan Lu, Kaihua Zhang, Tianyang Xu, Yutao Cui, Xiaolin Zhang
The Visual Object Tracking challenge VOT2021 is the ninth annual tracker benchmarking activity organized by the VOT initiative. Results of 71 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::717763c198da14f9ea29d111bbb1d71f
https://ora.ox.ac.uk/objects/uuid:d4585a6f-2205-4f68-b34a-8b6a61758cc8
https://ora.ox.ac.uk/objects/uuid:d4585a6f-2205-4f68-b34a-8b6a61758cc8
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 44(12)
Template-based discriminative trackers are currently the dominant tracking paradigm due to their robustness, but are restricted to bounding box tracking and a limited range of transformation models, which reduces their localization accuracy. We propo
Publikováno v:
IEEE transactions on cybernetics. 51(12)
A long-term visual object tracking performance evaluation methodology and a benchmark are proposed. Performance measures are designed by following a long-term tracking definition to maximize the analysis probing strength. The new measures outperform
Publikováno v:
ICPR
The best RGBD trackers provide high accuracy but are slow to run. On the other hand, the best RGB trackers are fast but clearly inferior on the RGBD datasets. In this work, we propose a deep depth-aware long-term tracker that achieves state-of-the-ar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fe8c050e8eb94265737afd8a6c757821
https://trepo.tuni.fi/handle/10024/143123
https://trepo.tuni.fi/handle/10024/143123
Publikováno v:
Sensors (Basel, Switzerland)
Sensors
Volume 20
Issue 2
Sensors, vol. 20, no. 2, 566, 2020.
Sensors, Vol 20, Iss 2, p 566 (2020)
Sensors
Volume 20
Issue 2
Sensors, vol. 20, no. 2, 566, 2020.
Sensors, Vol 20, Iss 2, p 566 (2020)
Although recently developed trackers have shown excellent performance even when tracking fast moving and shape changing objects with variable scale and orientation, the trackers for the electro-optical targeting systems (EOTS) still suffer from abrup
Publikováno v:
IEEE Transactions on Cybernetics. 48:1849-1861
Deformable parts models show a great potential in tracking by principally addressing non-rigid object deformations and self occlusions, but according to recent benchmarks, they often lag behind the holistic approaches. The reason is that potentially
Autor:
Matej Kristan, Jani Käpylä, Jiri Matas, Alan Lukezic, Joni-Kristian Kamarainen, Ugur Kart, Ahmed Durmush
Publikováno v:
ICCV
A long-term visual object tracking performance evaluation methodology and a benchmark are proposed. Performance measures are designed by following a long-term tracking definition to maximize the analysis probing strength. The new measures outperform
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::895489297e61ed51eedd9c1d827ce663
http://arxiv.org/abs/1907.00618
http://arxiv.org/abs/1907.00618
Publikováno v:
CVPR
Standard RGB-D trackers treat the target as an inherently 2D structure, which makes modelling appearance changes related even to simple out-of-plane rotation highly challenging. We address this limitation by proposing a novel long-term RGB-D tracker
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::389248a1c2bec7c4d0b59f712d13e676
https://trepo.tuni.fi/handle/10024/129781
https://trepo.tuni.fi/handle/10024/129781
Publikováno v:
CVPR
Template-based discriminative trackers are currently the dominant tracking paradigm due to their robustness, but are restricted to bounding box tracking and a limited range of transformation models, which reduces their localization accuracy. We propo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3c96aedbb2e1b7fed4f31e910218a1db