Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Dalong Du"'
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::78736a0b9a002df93e5f0dc92a0246aa
https://doi.org/10.1109/cvpr52688.2022.00164
https://doi.org/10.1109/cvpr52688.2022.00164
Autor:
Zheng Zhu, Guan Huang, Jiankang Deng, Yun Ye, Junjie Huang, Xinze Chen, Jiagang Zhu, Tian Yang, Dalong Du, Jiwen Lu, Jie Zhou
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence.
Face benchmarks empower the research community to train and evaluate high-performance face recognition systems. In this paper, we contribute a new million-scale recognition benchmark, containing uncurated 4M identities/260M faces (WebFace260M) and cl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c2a1e5fe4b25224eceb50f4e17eedf78
https://pubmed.ncbi.nlm.nih.gov/35471873
https://pubmed.ncbi.nlm.nih.gov/35471873
Publikováno v:
CVPR
Face clustering is a promising method for annotating un-labeled face images. Recent supervised approaches have boosted the face clustering accuracy greatly, however their performance is still far from satisfactory. These methods can be roughly divide
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ae870281ea70dd872bea377faa21d9de
https://doi.org/10.1109/cvpr46437.2021.00897
https://doi.org/10.1109/cvpr46437.2021.00897
Autor:
Jiankang Deng, Zheng Zhu, Yun Ye, Jie Zhou, Jiwen Lu, Tian Yang, Xinze Chen, Guan Huang, Jiagang Zhu, Junjie Huang, Dalong Du
Publikováno v:
CVPR
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
In this paper, we contribute a new million-scale face benchmark containing noisy 4M identities/260M faces (WebFace260M) and cleaned 2M identities/42M faces (WebFace42M) training data, as well as an elaborately designed time-constrained evaluation pro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a08478d8115e07b86ee6bf8ae29437b1
http://arxiv.org/abs/2103.04098
http://arxiv.org/abs/2103.04098
Publikováno v:
CVPR
This paper studies panoptic segmentation, a recently proposed task which segments foreground (FG) objects at the instance level as well as background (BG) contents at the semantic level. Existing methods mostly dealt with these two problems separatel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fba69c7b89e88448e0cf18f3150b8dde
https://doi.org/10.1109/cvpr.2019.00719
https://doi.org/10.1109/cvpr.2019.00719
Publikováno v:
ICCV Workshops
Convolutional neural networks (CNN) based tracking approaches have shown favorable performance in recent benchmarks. Nonetheless, the chosen CNN features are always pre-trained in different task and individual components in tracking systems are learn
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aa493255750e4d2e0688864d05ba2306
http://arxiv.org/abs/1711.04661
http://arxiv.org/abs/1711.04661
Autor:
Ruxandra Tapu, Tianzhu Zhang, Jaeil Cho, Dalong Du, Philip H. S. Torr, Kris M. Kitani, Deepak Mishra, Wenbing Tao, Fahad Shahbaz Khan, Luka Čehovin Zajc, Boyu Chen, Jae-chan Jeong, Andrea Vedaldi, Dawei Du, Jianke Zhu, Bogdan Mocanu, Weiming Hu, Alvaro Garcia-Martin, Jingyu Liu, João F. Henriques, Yang Li, Kai Chen, Junliang Xing, Luca Bertinetto, Chang Huang, Jiri Matas, Nianhao Xie, Risheng Liu, Payman Moallem, Guan Huang, Chong Sun, Qiang Wang, Roman Pflugfelder, David Zhang, Yifan Xing, Titus Zaharia, Gustavo Fernandez, Erhan Gundogdu, Karel Lebeda, Lingxiao Yang, Francesco Battistone, Guilherme Sousa Bastos, Junfei Zhuang, Matej Kristan, Zhipeng Zhang, Changsheng Xu, Vincenzo Santopietro, Matthias Mueller, Ning Wang, Ke Gao, Gustav Häger, Andrej Muhič, Pedro Senna, Richard Bowden, Wengang Zhou, Zhiqun He, Ming-Hsuan Yang, Qifeng Yu, Alireza Memarmoghadam, Jin Gao, Ondrej Miksik, Lei Zhang, Zheng Zhu, Alfredo Petrosino, Ales Leonardis, Tomas Vojir, Yingruo Fan, Siwei Lyu, Houqiang Li, Pallavi Venugopal M, Gorthi R. K. Sai Subrahmanyam, Longyin Wen, Xiao Bian, José M. Martínez, Antoine Tran, Michael Felsberg, Wei Zou, Wenbo Li, Jana Noskova, Sunglok Choi, Isabela Drummond, Xianguo Yu, Alan Lukezic, Stuart Golodetz, Abdelrahman Eldesokey, Lijun Wang, Erik Velasco-Salido, Huchuan Lu, Antoine Manzanera, Simon Hadfield, Ji-Wan Kim, Qingming Huang, Mengdan Zhang, Rafael Martin-Nieto, Goutam Bhat, Jae-Yeong Lee, Martin Danelljan, A. Aydin Alatan, Kannappan Palaniappan, Jack Valmadre, Guna Seetharaman, Junyu Gao, Hongliang Zhang, Mahdieh Poostchi
Publikováno v:
ICCV Workshops
The Visual Object Tracking challenge VOT2017 is the fifth annual tracker benchmarking activity organized by the VOT initiative. Results of 51 trackers are presented; many are state-of-the-art published at major computer vision conferences or journals
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f678b27c8d8099f3da3923b28010438b
https://doi.org/10.1109/iccvw.2017.230
https://doi.org/10.1109/iccvw.2017.230
Autor:
Philip H. S. Torr, Shuai Zheng, Sadeep Jayasumana, Chang Huang, Dalong Du, Vibhav Vineet, Bernardino Romera-Paredes, Zhizhong Su
Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learning techniques for image recognition to tackle pixel-level labelling tas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::442f9cccdb42e35a7a7d1db82c2a142d
http://arxiv.org/abs/1502.03240
http://arxiv.org/abs/1502.03240