Gang Lv
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Gang Lv has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Yining Sun
Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China
4 shared publications - Fudong Nian
Hefei University
2 shared publications - Fudong Nian
School of Advanced Manufacturing Engineering, Hefei University, Hefei, China
2 shared publications - Zuchang Ma
Institute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, China
2 shared publications - Guang-Zhou Zhang
Hefei University
1 shared publication Hao Zhao
Hefei University
1 shared publication
Latest Publications
- 22 January 2024
- Published by Springer Nature in Multimedia Systems
- Vol. 30 (1) , 1-12
Video–text retrieval via multi-modal masked transformer and adaptive attribute-aware graph convolutional network
- 22 January 2024
- Published by Springer Nature in Multimedia Systems
- Vol. 30 (1) , 1-12
Video–text retrieval via multi-modal masked transformer and adaptive attribute-aware graph convolutional network
- 13 July 2023
- Published by Springer Nature
- p. 55-59
Wege zur Vertiefung der Integration von Wirtschaft und Hochschulbildung
- 13 July 2023
- Published by Springer Nature
- p. 55-59
Wege zur Vertiefung der Integration von Wirtschaft und Hochschulbildung
- 17 April 2023
- Published by Springer Nature in Multimedia Systems
- Vol. 29 (4) , 2073-2083
Hierarchical cross-modal contextual attention network for visual grounding
- 17 April 2023
- Published by Springer Nature in Multimedia Systems
- Vol. 29 (4) , 2073-2083
Hierarchical cross-modal contextual attention network for visual grounding
- 15 August 2022
- Published by Springer Nature
- p. 522-534
Stitching High Resolution Notebook Keyboard Surface Based on Halcon Calibration
- 15 August 2022
- Published by Springer Nature
- p. 522-534
Stitching High Resolution Notebook Keyboard Surface Based on Halcon Calibration
- Open Access
- 1 May 2022
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 2198 (1) , 012037
Analysis for the Process Planning of the Body Side Welding in Delmia
Welding, as an important process for body-in-white (BIW), it should be taken into consideration in the automobile industry where the spot welding is often used. In order to validate the welding process of the whole welding line, the simulation process for the body side which is an important part of the BIW is discussed in the software Delmia according to the layout in AutoCAD which has been designed before. And then the establishment of model, the welding process and the specific working procedures are considered and discussed in the design stage to guarantee that the simulation process in Delmia can be carried on to validate whether the designed process can meet the working requirements. Additionally, the welding operation by multi-robots in a work station is analysed to verify that the number of robots and their positions are acceptable and they can reach working positions. Finally, the planning of the cycle time is obtained and then we can conclude that the designed welding process is feasible to guide the work in site.
- 1 May 2022
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 2198 (1) , 012037
Open AccessAnalysis for the Process Planning of the Body Side Welding in Delmia
Welding, as an important process for body-in-white (BIW), it should be taken into consideration in the automobile industry where the spot welding is often used. In order to validate the welding process of the whole welding line, the simulation process for the body side which is an important part of the BIW is discussed in the software Delmia according to the layout in AutoCAD which has been designed before. And then the establishment of model, the welding process and the specific working procedures are considered and discussed in the design stage to guarantee that the simulation process in Delmia can be carried on to validate whether the designed process can meet the working requirements. Additionally, the welding operation by multi-robots in a work station is analysed to verify that the number of robots and their positions are acceptable and they can reach working positions. Finally, the planning of the cycle time is obtained and then we can conclude that the designed welding process is feasible to guide the work in site.
- 28 April 2022
- Published by Springer Nature
- p. 45-62
Innovation und Umsetzung der internationalen dualen Hochschulausbildung am Beispiel der Hefei University
- 28 April 2022
- Published by Springer Nature
- p. 45-62
Innovation und Umsetzung der internationalen dualen Hochschulausbildung am Beispiel der Hefei University
- Open Access
- 25 March 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (7) , 1053
Scale and Background Aware Asymmetric Bilateral Network for Unconstrained Image Crowd Counting
This paper attacks the two challenging problems of image-based crowd counting, that is, scale variation and complex background. To that end, we present a novel crowd counting method, called the Scale and Background aware Asymmetric Bilateral Network (SBAB-Net), which is able to handle scale variation and background noise in a unified framework. Specifically, the proposed SBAB-Net contains three main components, a pre-trained backbone convolutional neural network (CNN) as the feature extractor and two asymmetric branches to generate a density map. These two asymmetric branches have different structures and use features from different semantic layers. One branch is densely connected stacked dilated convolution (DCSDC) sub-network with different dilation rates, which relies on one deep feature layer and can handle scale variation. The other branch is parameter-free densely connected stacked pooling (DCSP) sub-network with various pooling kernels and strides, which relies on shallow feature and can fuse features with several receptive fields to reduce the impact of background noise. Two sub-networks are fused by the attention mechanism to generate the final density map. Extensive experimental results on three widely-used benchmark datasets have demonstrated the effectiveness and superiority of our proposed method: (1) We achieve competitive counting performance compared to state-of-the-art methods; (2) Compared with baseline, the MAE and MSE are decreased by at least and , respectively.- 25 March 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (7) , 1053
Open AccessScale and Background Aware Asymmetric Bilateral Network for Unconstrained Image Crowd Counting
This paper attacks the two challenging problems of image-based crowd counting, that is, scale variation and complex background. To that end, we present a novel crowd counting method, called the Scale and Background aware Asymmetric Bilateral Network (SBAB-Net), which is able to handle scale variation and background noise in a unified framework. Specifically, the proposed SBAB-Net contains three main components, a pre-trained backbone convolutional neural network (CNN) as the feature extractor and two asymmetric branches to generate a density map. These two asymmetric branches have different structures and use features from different semantic layers. One branch is densely connected stacked dilated convolution (DCSDC) sub-network with different dilation rates, which relies on one deep feature layer and can handle scale variation. The other branch is parameter-free densely connected stacked pooling (DCSP) sub-network with various pooling kernels and strides, which relies on shallow feature and can fuse features with several receptive fields to reduce the impact of background noise. Two sub-networks are fused by the attention mechanism to generate the final density map. Extensive experimental results on three widely-used benchmark datasets have demonstrated the effectiveness and superiority of our proposed method: (1) We achieve competitive counting performance compared to state-of-the-art methods; (2) Compared with baseline, the MAE and MSE are decreased by at least and , respectively.