Zobrazeno 1 - 10
of 519
pro vyhledávání: '"Liang, Yanjie"'
Autor:
Zhang, Qiang, Wang, Weili, Zhang, Zhixuan, Liang, Yanjie, Sun, Feng, Wang, Zaiyi, Han, Guifang, Zhang, Weibin
Publikováno v:
In Ceramics International 1 October 2024 50(19) Part A:35695-35705
The explanation for deep neural networks has drawn extensive attention in the deep learning community over the past few years. In this work, we study the visual saliency, a.k.a. visual explanation, to interpret convolutional neural networks. Compared
Externí odkaz:
http://arxiv.org/abs/2110.05182
Autor:
Yang, Huanxin, Chen, Xiangxiang, Lu, Haolin, Sun, Wenda, Li, Yue, Zhang, Yuhai, Liang, Yanjie, Long, Guankui, Zhang, Libing, Li, Xiyan
Publikováno v:
In Chemical Engineering Journal 1 July 2024 491
Autor:
Qiu, Lupeng, Yang, Zizhong, Jia, Guhe, Liang, Yanjie, Du, Sicheng, Zhang, Jian, Liu, Minglu, Zhao, Xiao, Jiao, Shunchang
Publikováno v:
In Heliyon 30 June 2024 10(12)
Publikováno v:
In Materials Science & Engineering R June 2024 159
Autor:
Li, Qingzhu, Lai, Xinting, Liu, Zhenxing, Chai, Fei, Zhao, Feiping, Peng, Cong, Liang, Yanjie
Publikováno v:
In Hydrometallurgy February 2024 224
Publikováno v:
ACM MM Asia2019
In recent years, Convolutional Neural Network (CNN) based trackers have achieved state-of-the-art performance on multiple benchmark datasets. Most of these trackers train a binary classifier to distinguish the target from its background. However, the
Externí odkaz:
http://arxiv.org/abs/2011.04260
Recently, some correlation filter based trackers with detection proposals have achieved state-of-the-art tracking results. However, a large number of redundant proposals given by the proposal generator may degrade the performance and speed of these t
Externí odkaz:
http://arxiv.org/abs/2007.07018
Publikováno v:
Proceedings of the 27th ACM International Conference on Multimedia (MM '19). 2019, Nice, France. ACM, New York, NY, USA
Event cameras, which are asynchronous bio-inspired vision sensors, have shown great potential in a variety of situations, such as fast motion and low illumination scenes. However, most of the event-based object tracking methods are designed for scena
Externí odkaz:
http://arxiv.org/abs/2002.05583
Autor:
Zhang, Jiatai, Wang, Weili, Zhang, Zhixuan, Chen, Jianqi, Sun, Xiaoning, Sun, Guoxun, Liang, Yanjie, Han, Guifang, Zhang, Weibin
Publikováno v:
In Journal of Alloys and Compounds 5 December 2023 966