SIFT meets CNN: A decade survey of instance retrieval
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 …
Since 2003, image retrieval based on local descriptors (de facto SIFT) has been extensively …
Outlier detection: Methods, models, and classification
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 …
to the design of efficient outlier detection techniques while taking into consideration …
Open3D: A modern library for 3D data processing
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 …
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
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 …
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
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 …
navigable small world graphs with controllable hierarchy (Hierarchical NSW, HNSW). The …
Clusterfomer: clustering as a universal visual learner
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 …
paradigm with TransFormer. It comprises two novel designs: 1) recurrent cross-attention …
Big IoT data analytics: architecture, opportunities, and open research challenges
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 …
miniaturization of Internet of things (IoT) devices increases. However, such data are not …
Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning
Predicting interactions between proteins and other biomolecules solely based on structure
remains a challenge in biology. A high-level representation of protein structure, the …
remains a challenge in biology. A high-level representation of protein structure, the …
A survey on learning to hash
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 …
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
Incorporating smoothness constraints into feature matching is known to enable ultra-robust
matching. However, such formulations are both complex and slow, making them unsuitable …
matching. However, such formulations are both complex and slow, making them unsuitable …