The loss of spatial importance negatively affects the performance of hash learning and thus reduces its accuracy. To address this issue, we propose a new deep hashing method with weighted spatial information, which generates hash codes by using discrete spatial importance distribu- tion.
Feb 25, 2021 · We propose a new deep hashing method with weighted spatial information, which generates hash codes by using discrete spatial importance distribution.
Deep Hashing With Weighted Spatial Importance - IEEE Xplore
ieeexplore.ieee.org › abstract › document
Nov 18, 2020 · Specifically, the proposed DWSH first utilizes a spatial attention model to learn the importance of different spatial regions in the original ...
The experimental results of three widely used datasets show that the proposed deep weighted hashing method is superior to the state-of-the-art hashing method.
Discrete Spatial Importance-Based Deep Weighted Hashing. Yang Shi (Shandong ... weighted spatial information, which generates hash codes by using discrete spatial ...
Specifically, the proposed DWSH first utilizes a spatial attention model to learn the importance of different spatial regions in the original image, and then ...
Discrete Spatial Importance-Based Deep Weighted Hashing. Yang Shi (Shandong University), Xiushan Nie (Shandong Jianzhu University)*, Quan Zhou (Shandong ...
Papertalk is an open-source platform where scientists share video presentations about their newest scientific results - and watch, like + discuss them.
Supervised Discrete Hashing (SDH) [15] aims to directly optimize the binary hash codes using the discrete cyclic coordinate descend method.
Missing: Importance- | Show results with:Importance-
Apr 14, 2020 · In this paper, we propose a novel deep discrete hashing approach, namely Pairwise Correlation Discrete Hashing (PCDH), to utilize the pairwise ...