SIFT meets CNN: A decade survey of instance retrieval

L Zheng, Y Yang, Q Tian - IEEE transactions on pattern …, 2017 - ieeexplore.ieee.org
In the early days, content-based image retrieval (CBIR) was studied with global features.
Since 2003, image retrieval based on local descriptors (de facto SIFT) has been extensively …

Recent developments of content-based image retrieval (CBIR)

X Li, J Yang, J Ma - Neurocomputing, 2021 - Elsevier
With the development of Internet technology and the popularity of digital devices, Content-
Based Image Retrieval (CBIR) has been quickly developed and applied in various fields …

Recent advance in content-based image retrieval: A literature survey

W Zhou, H Li, Q Tian - arxiv preprint arxiv:1706.06064, 2017 - arxiv.org
The explosive increase and ubiquitous accessibility of visual data on the Web have led to
the prosperity of research activity in image search or retrieval. With the ignorance of visual …

Query-adaptive late fusion for image search and person re-identification

L Zheng, S Wang, L Tian, F He… - Proceedings of the …, 2015 - openaccess.thecvf.com
Feature fusion has been proven effective [31, 32] in image search. Typically, it is assumed
that the to-be-fused heterogeneous features work well by themselves for the query …

[KİTAP][B] Computer Vision and Recognition Systems: Research Innovations and Trends

CL Chowdhary, GT Reddy, BD Parameshachari - 2022 - api.taylorfrancis.com
This cutting-edge volume, Computer Vision and Recognition Systems: Research
Innovations and Trends, focuses on how artificial intelligence can be used to give computers …

Packing and padding: Coupled multi-index for accurate image retrieval

L Zheng, S Wang, Z Liu, Q Tian - Proceedings of the IEEE …, 2014 - openaccess.thecvf.com
Abstract In Bag-of-Words (BoW) based image retrieval, the SIFT visual word has a low
discriminative power, so false positive matches occur prevalently. Apart from the information …

Sparse contextual activation for efficient visual re-ranking

S Bai, X Bai - IEEE Transactions on Image Processing, 2016 - ieeexplore.ieee.org
In this paper, we propose an extremely efficient algorithm for visual re-ranking. By
considering the original pairwise distance in the contextual space, we develop a feature …

Deep convolutional features for image retrieval

S Gkelios, A Sophokleous, S Plakias, Y Boutalis… - Expert Systems with …, 2021 - Elsevier
Nowadays, the use of Convolutional Neural Networks (CNNs) has led to tremendous
achievements in several computer vision challenges. CNN-based image retrieval methods …

Image classification and retrieval are one

L **e, R Hong, B Zhang, Q Tian - Proceedings of the 5th ACM on …, 2015 - dl.acm.org
In this paper, we demonstrate that the essentials of image classification and retrieval are the
same, since both tasks could be tackled by measuring the similarity between images. To this …

Coupled binary embedding for large-scale image retrieval

L Zheng, S Wang, Q Tian - IEEE transactions on image …, 2014 - ieeexplore.ieee.org
Visual matching is a crucial step in image retrieval based on the bag-of-words (BoW) model.
In the baseline method, two keypoints are considered as a matching pair if their SIFT …