Springer Science and Business Media LLC

Công bố khoa học tiêu biểu

* Dữ liệu chỉ mang tính chất tham khảo

Sắp xếp:  
A robust infrared and visible image fusion framework via multi-receptive-field attention and color visual perception
Springer Science and Business Media LLC - Tập 53 - Trang 8114-8132 - 2022
Zhaisheng Ding, Haiyan Li, Dongming Zhou, Yanyu Liu, Ruichao Hou
In this paper, a robust infrared and visible image fusion scheme that joins a dual-branch multi-receptive-field neural network and a color vision transfer algorithm is designed to aggregate infrared and visible video sequences. The proposed method enables the fused image to effectively recognize thermal objects, contain rich texture information and ensure visual perception quality. The fusion netw...... hiện toàn bộ
Bi-attention network for bi-directional salient object detection
Springer Science and Business Media LLC - Tập 53 - Trang 21500-21516 - 2023
Cheng Xu, Hui Wang, Xianhui Liu, Weidong Zhao
Saliency detection models based on neural networks have achieved outstanding results, but there are still problems such as low accuracy of object boundaries and redundant parameters. To alleviate these problems, we make full use of position and contour information from the down-sampling layers, and optimize the detection result layer by layer. First, this paper designs an attention-based adaptive ...... hiện toàn bộ
Computation and memory optimized spectral domain convolutional neural network for throughput and energy-efficient inference
Springer Science and Business Media LLC - Tập 53 - Trang 4499-4523 - 2022
Shahriyar Masud Rizvi, Ab Al-Hadi Ab Rahman, Usman Ullah Sheikh, Kazi Ahmed Asif Fuad, Hafiz Muhammad Faisal Shehzad
Conventional convolutional neural networks (CNNs) present a high computational workload and memory access cost (CMC). Spectral domain CNNs (SpCNNs) offer a computationally efficient approach to compute CNN training and inference. This paper investigates CMC of SpCNNs and its contributing components analytically and then proposes a methodology to optimize CMC, under three strategies, to enhance inf...... hiện toàn bộ
Mạng lưới phân cụm hình ảnh theo không gian con sâu với tự biểu diễn và tự giám sát Dịch bởi AI
Springer Science and Business Media LLC - Tập 53 - Trang 4859-4873 - 2022
Chao Chen, Hu Lu, Hui Wei, Xia Geng
Các thuật toán phân cụm không gian con cho bộ dữ liệu hình ảnh áp dụng ma trận hệ số tự biểu diễn để xác định mối liên hệ giữa các mẫu và sau đó thực hiện phân cụm. Tuy nhiên, các thuật toán như vậy được đề xuất trong những năm gần đây không sử dụng nhãn phân cụm trong không gian con để hướng dẫn mạng sâu và không tạo ra một khung trích xuất đặc trưng và phân cụm có thể huấn luyện theo kiểu đầu-đế...... hiện toàn bộ
#Phân cụm không gian con #mô hình tự giám sát #mạng sâu #trích xuất đặc trưng #tối ưu hóa lặp luân phiên
A visualized fire detection method based on convolutional neural network beyond anchor
Springer Science and Business Media LLC - - 2022
Yuming Li, Wei Zhang, Yanyan Liu, Yao Jin
Bayesian model averaging for river flow prediction
Springer Science and Business Media LLC - Tập 49 - Trang 103-111 - 2018
Paul J. Darwen
This paper explores the practical benefits of Bayesian model averaging, for a problem with limited data, namely future flow of five intermittent rivers. This problem is a useful proxy for many others, as the limited amount of data only allows tuning of small, simple models. Bayesian model averaging is theoretically a good way to cope with these difficulties, but it has not been widely used on this...... hiện toàn bộ
Editorial
Springer Science and Business Media LLC - - 2006
Chris J. Hinde
Learning rich feature representation and aggregation for accurate visual tracking
Springer Science and Business Media LLC - Tập 53 - Trang 28114-28132 - 2023
Yijin Yang, Xiaodong Gu
Visual tracking is a key component of computer vision and has a wide range of practical applications. Recently, the tracking-by-segmentation framework has been widely applied in visual tracking due to its astonishing performance on accuracy. It attempts to learn from the framework of video object segmentation to realize accurate tracking. Although segmentation-based trackers are effective for targ...... hiện toàn bộ
A novel gated dual convolutional neural network model with autoregressive method and attention mechanism for probabilistic load forecasting
Springer Science and Business Media LLC - Tập 53 - Trang 20256-20271 - 2023
Yilei Qiu, Shunzhen Wang, Shuai Zhang, Jiyuan Xu
Accurate load forecasting is prime in the electric power industry, while the complexity and variability of the load data make it a challenging problem. Therefore, the probabilistic load forecasting is used to provide a prediction interval for the power system. However, the input scale insensitive problem has rarely been addressed in existing works when exploring the multi-load zones data, resultin...... hiện toàn bộ
OSAF-Net: A one-stage anchor-free detector for small-target crop pest detection
Springer Science and Business Media LLC - Tập 53 - Trang 24895-24907 - 2023
Rujing Wang, Shifeng Dong, Lin Jiao, Jianming Du, Ziliang Huang, Shijian Zheng, Chenrui Kang
Multi-class crop pest detection in massive images is a practically challenging problem. Recently, convolutional neural networks (CNN) based approaches have shown promise in detecting crop pests, but there are still significant obstacles to overcome. Two primary challenges include the highly similar physical appearance of some categories, making it difficult to distinguish the specific categories m...... hiện toàn bộ
Tổng số: 3,988   
  • 1
  • 2
  • 3
  • 4
  • 5
  • 6
  • 10