Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Hamed Kiani Galoogahi"'
Autor:
Houqiang Li, Huchuan Lu, Siwen Wang, Rafael Martin-Nieto, Efstratios Gavves, Feng Li, Manqiang Che, Erhan Gundogdu, Priya Mariam Raju, Xiaofan Zhang, Roman Pflugfelder, Yan Lu, Xinmei Tian, Martin Danelljan, Deepak Mishra, Guilherme Sousa Bastos, Honggang Zhang, Heng Fan, Mohamed H. Abdelpakey, Zhen-Hua Feng, Wang Wei, Andrej Muhič, Wengang Zhou, Deming Chen, Haojie Zhao, Sihang Wu, Richard M. Everson, Junfei Zhuang, Qin Zhou, Myunggu Kang, Abel Gonzalez-Garcia, Pablo Vicente-Moñivar, Richard Bowden, Horst Possegger, Yicai Yang, Andrea Vedaldi, Jaime Spencer Martin, Jongwon Choi, Yunhua Zhang, Yiannis Demiris, Seokeon Choi, Alireza Memarmoghadam, Wangmeng Zuo, Changzhen Xiong, Yuxuan Sun, Daijin Kim, Yuhong Li, Qing Guo, Tang Ming, Arnold W. M. Smeulders, Hamed Kiani Galoogahi, Zhihui Wang, Asanka G. Perera, Fahad Shahbaz Khan, George De Ath, Shuangping Huang, Qian Ruihe, Philip H. S. Torr, Haojie Li, Zhiqun He, João F. Henriques, Namhoon Lee, Chong Sun, Jorge Rodríguez Herranz, Vincenzo Santopietro, Lijun Wang, Qiang Wang, Gustavo Fernandez, Shuai Bai, Weiming Hu, Ondrej Miksik, Dongyoon Wee, Xiaohe Wu, Goutam Bhat, Yifan Jiao, A. Aydin Alatan, Alfredo Petrosino, Ran Tao, Tianyang Xu, Sergio Vivas, Cheng Tian, Yee Wei Law, Wei Feng, José M. Martínez, Luca Bertinetto, Runling Wang, Liu Si, Tianzhu Zhang, Tomas Vojir, Mario Edoardo Maresca, Lichao Zhang, Changick Kim, Luka Čehovin Zajc, Lingxiao Yang, Yan Li, Javaan Chahl, Simon Hadfield, Chong Luo, Jiří Matas, Ales Leonardis, Jack Valmadre, Pedro Senna, Josef Kittler, Klemen Grm, Cong Hao, Haibin Ling, Isabela Drummond, Zheng Zhang, Fan Yang, Joakim Johnander, Tobias Fischer, Gorthi R. K. Sai Subrahmanyam, Jinyoung Sung, Jin-Young Choi, Bo Li, Hui Zhi, Álvaro Iglesias-Arias, Joost van de Weijer, Hyung Jin Chang, Jinqing Qi, Michael Felsberg, Francesco Battistone, Sangdoo Yun, Wei Zou, Huiyun Li, Boyu Chen, Zheng Zhu, Jing Li, Abdelrahman Eldesokey, Litu Rout, Matej Kristan, Mohamed Shehata, Fei Zhao, Changsheng Xu, Alan Lukežič, Yi Wu, Wenjun Zeng, Lutao Chu, Vitomir Struc, Stuart Golodetz, Alvaro Garcia-Martin, Dong Wang, Junyu Gao, Hankyeol Lee, Hyemin Lee, Ning Wang, Wei Wu, Anfeng He, Xiaojun Wu, Rama Krishna Sai Subrahmanyam Gorthi, Payman Moallem, Peixia Li, Jinqiao Wang, Erik Velasco-Salido, Ming-Hsuan Yang
Publikováno v:
European Conference on Computer Vision
Lecture Notes in Computer Science ISBN: 9783030110086
ECCV Workshops (1)
Lecture Notes in Computer Science ISBN: 9783030110086
ECCV Workshops (1)
The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative. Results of over eighty trackers are presented; many are state-of-the-art trackers published at major computer vision confe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a449874fbb7a60c1bc50564cd356140f
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-161343
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-161343
Publikováno v:
ICRA
In this paper we present a new approach for efficient regression based object tracking which we refer to as Deep- LK. Our approach is closely related to the Generic Object Tracking Using Regression Networks (GOTURN) framework of Held et al. We make t
Publikováno v:
ICCV
Correlation Filters (CFs) have recently demonstrated excellent performance in terms of rapidly tracking objects under challenging photometric and geometric variations. The strength of the approach comes from its ability to efficiently learn - on the
Publikováno v:
ICCV
An emerging problem in computer vision is the reconstruction of 3D shape and pose of an object from a single image. Hitherto, the problem has been addressed through the application of canonical deep learning methods to regress from the image directly
Publikováno v:
ICCV
In this paper, we propose the first higher frame rate video dataset (called Need for Speed - NfS) and benchmark for visual object tracking. The dataset consists of 100 videos (380K frames) captured with now commonly available higher frame rate (240 F
Publikováno v:
Group and Crowd Behavior for Computer Vision
Crowd scene analysis has recently attracted intense attention from the vision community due to its crucial role for a wide range of surveillance applications such as crowd flow segmentation, detecting and tracking people in crowds, and analyzing thei
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::969ed346d3130674e6a51589ec4e226e
https://doi.org/10.1016/b978-0-12-809276-7.00013-8
https://doi.org/10.1016/b978-0-12-809276-7.00013-8
Autor:
Terence Sim, Hamed Kiani Galoogahi
Publikováno v:
WACV
The application of correlation filters for the task of facial landmark detection has been studied by many vision works. Their success, however, is limited by the presence of large pose variations, expression and occlusion in face images. Moreover, ex
Publikováno v:
WACV
The rise of wearable devices has led to many new ways of re-identifying an individual. Unlike static cameras, where the views are often restricted or zoomed out and occlusions are common scenarios, first-person-views (FPVs) or ego-centric views see p
Publikováno v:
Toward Robotic Socially Believable Behaving Systems-Volume II ISBN: 9783319310527
Toward Robotic Socially Believable Behaving Systems (II)
Toward Robotic Socially Believable Behaving Systems (II)
This Chapter presents a framework for the the task of abnormality detection in crowded scenes based on the analysis of trajectories, build up upon a novel video descriptor, called Histogram of Oriented Tracklets. Unlike standard approaches that emplo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c07e8994fd063f2c5ded1cce9fafe337
https://doi.org/10.1007/978-3-319-31053-4_11
https://doi.org/10.1007/978-3-319-31053-4_11
Publikováno v:
CVPR
Correlation filters take advantage of specific properties in the Fourier domain allowing them to be estimated efficiently: O(NDlogD) in the frequency domain, versus O(D^3 + ND^2) spatially where D is signal length, and N is the number of signals. Rec