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 …

Outlier detection: Methods, models, and classification

A Boukerche, L Zheng, O Alfandi - ACM Computing Surveys (CSUR), 2020 - dl.acm.org
Over the past decade, we have witnessed an enormous amount of research effort dedicated
to the design of efficient outlier detection techniques while taking into consideration …

Open3D: A modern library for 3D data processing

QY Zhou, J Park, V Koltun - arxiv preprint arxiv:1801.09847, 2018 - arxiv.org
Open3D is an open-source library that supports rapid development of software that deals
with 3D data. The Open3D frontend exposes a set of carefully selected data structures and …

D2-net: A trainable cnn for joint description and detection of local features

M Dusmanu, I Rocco, T Pajdla… - Proceedings of the …, 2019 - openaccess.thecvf.com
In this work we address the problem of finding reliable pixel-level correspondences under
difficult imaging conditions. We propose an approach where a single convolutional neural …

Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs

YA Malkov, DA Yashunin - IEEE transactions on pattern …, 2018 - ieeexplore.ieee.org
We present a new approach for the approximate K-nearest neighbor search based on
navigable small world graphs with controllable hierarchy (Hierarchical NSW, HNSW). The …

Clusterfomer: clustering as a universal visual learner

J Liang, Y Cui, Q Wang, T Geng… - Advances in neural …, 2023 - proceedings.neurips.cc
This paper presents ClusterFormer, a universal vision model that is based on the Clustering
paradigm with TransFormer. It comprises two novel designs: 1) recurrent cross-attention …

Big IoT data analytics: architecture, opportunities, and open research challenges

M Marjani, F Nasaruddin, A Gani, A Karim… - ieee …, 2017 - ieeexplore.ieee.org
Voluminous amounts of data have been produced, since the past decade as the
miniaturization of Internet of things (IoT) devices increases. However, such data are not …

Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning

P Gainza, F Sverrisson, F Monti, E Rodola, D Boscaini… - Nature …, 2020 - nature.com
Predicting interactions between proteins and other biomolecules solely based on structure
remains a challenge in biology. A high-level representation of protein structure, the …

A survey on learning to hash

J Wang, T Zhang, N Sebe… - IEEE transactions on …, 2017 - ieeexplore.ieee.org
Nearest neighbor search is a problem of finding the data points from the database such that
the distances from them to the query point are the smallest. Learning to hash is one of the …

GMS: Grid-based motion statistics for fast, ultra-robust feature correspondence

JW Bian, WY Lin, Y Matsushita… - Proceedings of the …, 2017 - openaccess.thecvf.com
Incorporating smoothness constraints into feature matching is known to enable ultra-robust
matching. However, such formulations are both complex and slow, making them unsuitable …