Results 41 to 50 of about 10,164 (194)

Ranking-based Deep Cross-modal Hashing

, 2019
Cross-modal hashing has been receiving increasing interests for its low storage cost and fast query speed in multi-modal data retrievals. However, most existing hashing methods are based on hand-crafted or raw level features of objects, which may not be ...
Domeniconi, Carlotta, Guo, Maozu, Liu, Xuanwu, Ren, Yazhou, Wang, Jun, Yu, Guoxian   +5 more
core   +1 more source

KNN Algorithm of Enhanced Clustering Based on Density Canopy and Deep Feature

Jisuanji kexue yu tansuo, 2021
As the most widely used supervised classification algorithm, K nearest neighbor (KNN) algorithm is often inefficient in the processing of large-scale and multidimensional data.
SHEN Xueli, QIN Xinyu
doaj   +1 more source

Deep Policy Hashing Network with Listwise Supervision [PDF]

Proceedings of the 2019 on International Conference on Multimedia Retrieval, 2019
Deep-networks-based hashing has become a leading approach for large-scale image retrieval, which learns a similarity-preserving network to map similar images to nearby hash codes. The pairwise and triplet losses are two widely used similarity preserving manners for deep hashing.
Wang, Shaoying, Lai, Haijiang, Yang, Yifan, Yin, Jian   +3 more
openaire   +2 more sources

Variational Deep Semantic Hashing for Text Documents

, 2017
As the amount of textual data has been rapidly increasing over the past decade, efficient similarity search methods have become a crucial component of large-scale information retrieval systems.
Erin Liong V., Germain M., Gionis A., Glorot X., Goodfellow I., Goodfellow I., Kingma D., Kingma D. P., Kingma D. P., Kulis B., Larochelle H., Liu W., Liu W., Miao Y., Ng A. Y., Rezende D. J., Wang J., Weiss Y., Xia R., Xu J.   +19 more
core   +1 more source

Weakly Supervised Deep Image Hashing Through Tag Embeddings

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Many approaches to semantic image hashing have been formulated as supervised learning problems that utilize images and label information to learn the binary hash codes. However, large-scale labeled image data is expensive to obtain, thus imposing a restriction on the usage of such algorithms.
Gattupalli, Vijetha, Zhuo, Yaoxin, Li, Baoxin   +2 more
openaire   +2 more sources

Deep supervised hashing network with integrated regularisation [PDF]

IET Image Processing, 2019
Hashing has been widely deployed to approximate nearest neighbour search for large‐scale multimedia retrieval tasks due to storage and retrieval efficiency. State‐of‐the‐art supervised hashing methods for image retrieval construct deep structures to simultaneously learn image representation and generate good hash codes, and the key step among them is ...
Jianxin Liao, Baoran Li, Di Yang, Jingyu Wang, Qi Qi, Jing Wang   +5 more
openaire   +1 more source

Supervised Hashing with End-to-End Binary Deep Neural Network

, 2018
Image hashing is a popular technique applied to large scale content-based visual retrieval due to its compact and efficient binary codes. Our work proposes a new end-to-end deep network architecture for supervised hashing which directly learns binary ...
Cheung, Ngai-Man, Do, Thanh-Toan, Tan, Dang-Khoa Le   +2 more
core   +1 more source

Instance-Aware Hashing for Multi-Label Image Retrieval

, 2016
Similarity-preserving hashing is a commonly used method for nearest neighbour search in large-scale image retrieval. For image retrieval, deep-networks-based hashing methods are appealing since they can simultaneously learn effective image ...
Lai, Hanjiang, Shu, Xiangbo, Wei, Yunchao, Yan, Pan, Yan, Shuicheng   +4 more
core   +1 more source

Neural Fields for Highly Accelerated 2D Cine Phase Contrast MRI

Advanced Science, EarlyView.
ABSTRACT 2D cine phase contrast (CPC) MRI provides quantitative information on blood velocity and flow within the human vasculature. However, data acquisition is time‐consuming, motivating the reconstruction of the velocity field from undersampled measurements to reduce scan times. In this work, neural fields are proposed as a continuous spatiotemporal
Pablo Arratia, Martin J. Graves, Mary McLean, Carolin Pirkl, Carola‐Bibiane Schönlieb, Timo Schirmer, Florian Wiesinger, Matthias J. Ehrhardt   +7 more
wiley   +1 more source

Asymmetric Deep Semantic Quantization for Image Retrieval

IEEE Access, 2019
Due to its fast retrieval and storage efficiency capabilities, hashing has been widely used in nearest neighbor retrieval tasks. By using deep learning-based techniques, hashing can outperform non-learning-based hashing technique in many applications ...
Zhan Yang, Osolo Ian Raymond, Wuqing Sun, Jun Long   +3 more
doaj   +1 more source