Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Wenchi Ma"'
Publikováno v:
IEEE Access, Vol 8, Pp 129300-129309 (2020)
In the majority of object detection frameworks, the confidence of instance classification is used as the quality criterion of predicted bounding boxes, like the confidence-based ranking in non-maximum suppression (NMS). However, the quality of boundi
Externí odkaz:
https://doaj.org/article/ca0fcc35f194412bb191856a93518ee6
Publikováno v:
ICPR
Crowd counting in still images is a challenging problem in practice due to huge crowd-density variations, large perspective changes, severe occlusion, and variable lighting conditions. The state-of-the-art patch rescaling module (PRM) based approache
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ffb41f243ceab5286d9cb26baa3f39a8
https://doi.org/10.1109/icpr48806.2021.9412406
https://doi.org/10.1109/icpr48806.2021.9412406
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030873547
ICIG (1)
ICIG (1)
Most deep learning models are data-driven and the excellent performance is highly dependent on the abundant and diverse datasets. However, it is very hard to obtain and label the datasets of some specific scenes or applications. If we train the detec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ed066caf689e58052e92134b3bf13bc2
https://doi.org/10.1007/978-3-030-87355-4_15
https://doi.org/10.1007/978-3-030-87355-4_15
The paper proposes a semantic clustering based deduction learning by mimicking the learning and thinking process of human brains. Human beings can make judgments based on experience and cognition, and as a result, no one would recognize an unknown an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::240b718e11b9ec4d0ef44e8b963b32a6
Publikováno v:
ICTAI
Layer-wise learning, as an alternative to global back-propagation, is easy to interpret, analyze, and it is memory efficient. Recent studies demonstrate that layer-wise learning can achieve state-of-the-art performance in image classification on vari
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c45c4cb8f039621f3e26e3619ce04061
https://doi.org/10.1109/ictai50040.2020.00046
https://doi.org/10.1109/ictai50040.2020.00046
Publikováno v:
IEEE Access, Vol 8, Pp 129300-129309 (2020)
In the majority of object detection frameworks, the confidence of instance classification is used as the quality criterion of predicted bounding boxes, like the confidence-based ranking in non-maximum suppression (NMS). However, the quality of boundi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cd3f4259f270c938152f857c873c9964
http://arxiv.org/abs/2007.06233
http://arxiv.org/abs/2007.06233
This chapter presents a brief overview of the recent developments in object detection using convolutional neural networks (CNNs) and describes several classical CNN-based detectors. It also presents some performance comparison results of different mo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2d67d1c4980de74ca7248bb8eef50a84
https://doi.org/10.1201/9781351003827-2
https://doi.org/10.1201/9781351003827-2
Publikováno v:
WACV
In this paper, we investigate the empirical impact of orthogonality regularization (OR) in deep learning, either solo or collaboratively. Recent works on OR showed some promising results on the accuracy. In our ablation study, however, we do not obse
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1ffda2c2678246d5878ab011b6319666
http://arxiv.org/abs/2001.01275
http://arxiv.org/abs/2001.01275
In this paper, we address the problem of weakly supervised object localization (WSL), which trains a detection network on the dataset with only image-level annotations. The proposed approach is built on the observation that the proposal set from the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bbe89b3e7dd5fd596a166df0aea87a5b
http://arxiv.org/abs/1910.02101
http://arxiv.org/abs/1910.02101
Autor:
Chenfeng Liu, Jingkai Zhou, Dongdong Li, Panagiotis Giannakeris, Nitin Bansal, Yunchao Wei, Chase Brown, Bo Ke, Han Deng, Zhipeng Deng, Lin Cheng, Lianjie Wang, Qingming Huang, Zexin Wang, Qinqin Nie, Guanghui Wang, Wenrui He, Xintao Lian, Shubo Wei, Lars Sommer, Jian Cheng, Lei Zhang, Wei Li, Xiaoyu Liu, Haipeng Zhang, Emmanouil Michail, Ioannis Kompatsiaris, Zhaoyue Xia, Yuanwei Wu, Qinghua Hu, Liyu Lu, Haoran Wang, Haibin Ling, Kaiwen Duan, Qiuchen Sun, Siwei Wang, Hongyu Xu, Qishang Cheng, Yong Wang, Hao Liu, Xiao Bian, Nehal Mamgain, Lin Ma, Shengjin Wang, Yue Fan, K J Joseph, Minyu Huang, Honggang Qi, Robert Laganiere, Honghui Shi, Yali Li, Chen Qian, Lu Ding, Juanping Zhao, Xiufang Li, Zichen Song, Ke Wang, Heqian Qiu, Oliver Acatay, Zhen Cui, Wei Zhang, Stefanos Vrochidis, Arne Schumann, Xinbin Luo, Usman Sajid, Yifan Zhang, Sujuan Wang, Ying Li, Qijie Zhao, Feng Ni, Tiaojio Lee, Zhenwei He, Weikun Wu, Yongtao Wang, Fan Zhang, Yangliu Kuai, Qiong Liu, Wenzhe Yang, Hao Cheng, Vineeth N Balasubramanian, Yuqin Zhang, Jianqiang Wang, Jianxiu Yang, Zhiyao Guo, Dawei Du, Li Yang, Chengzheng Li, Xiaoyu Chen, Longyin Wen, Hongliang Li, Sheng Jiang, Yi Luo, Naveen Kumar Vedurupaka, Karthik Suresh, Zhangyang Wang, Qian Wang, Pengfei Zhu, Yiling Liu, Wenya Ma, Hu Lin, Wenchi Ma, Feng Zhu, Konstantinos Avgerinakis, Xin Sun, Haotian Wu
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030110208
ECCV Workshops (5)
ECCV Workshops (5)
Object detection is a hot topic with various applications in computer vision, e.g., image understanding, autonomous driving, and video surveillance. Much of the progresses have been driven by the availability of object detection benchmark datasets, i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::237443796468ab57b6319eb33efab2e4
https://doi.org/10.1007/978-3-030-11021-5_27
https://doi.org/10.1007/978-3-030-11021-5_27