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 …

Source-free unsupervised domain adaptation: Current research and future directions

N Zhang, J Lu, K Li, Z Fang, G Zhang - Neurocomputing, 2024 - Elsevier
In the field of Transfer Learning, Source-Free Unsupervised Domain Adaptation (SFUDA)
emerges as a practical and novel task that enables a pre-trained model to adapt to a new …

Fine-tuning CNN image retrieval with no human annotation

F Radenović, G Tolias, O Chum - IEEE transactions on pattern …, 2018 - ieeexplore.ieee.org
Image descriptors based on activations of Convolutional Neural Networks (CNNs) have
become dominant in image retrieval due to their discriminative power, compactness of …

Generalizing a person retrieval model hetero-and homogeneously

Z Zhong, L Zheng, S Li, Y Yang - Proceedings of the …, 2018 - openaccess.thecvf.com
Person re-identification (re-ID) poses unique challenges for unsupervised domain
adaptation (UDA) in that classes in the source and target sets (domains) are entirely different …

Re-ranking person re-identification with k-reciprocal encoding

Z Zhong, L Zheng, D Cao, S Li - Proceedings of the IEEE …, 2017 - openaccess.thecvf.com
When considering person re-identification (re-ID) as a retrieval process, re-ranking is a
critical step to improve its accuracy. Yet in the re-ID community, limited effort has been …

Pedestrian alignment network for large-scale person re-identification

Z Zheng, L Zheng, Y Yang - … on Circuits and Systems for Video …, 2018 - ieeexplore.ieee.org
Person re-identification (re-ID) is mostly viewed as an image retrieval problem. This task
aims to search a query person in a large image pool. In practice, person re-ID usually adopts …

Deep image retrieval: Learning global representations for image search

A Gordo, J Almazán, J Revaud, D Larlus - Computer Vision–ECCV 2016 …, 2016 - Springer
We propose a novel approach for instance-level image retrieval. It produces a global and
compact fixed-length representation for each image by aggregating many region-wise …

Particular object retrieval with integral max-pooling of CNN activations

G Tolias, R Sicre, H Jégou - arxiv preprint arxiv:1511.05879, 2015 - arxiv.org
Recently, image representation built upon Convolutional Neural Network (CNN) has been
shown to provide effective descriptors for image search, outperforming pre-CNN features as …