Fetching the paper…
Reading the bibliography…
This paper presents an overview of the evolution of local features from handcrafted to deep-learning-based methods, followed by a discussion of several benchmarks and papers evaluating such local features.
Digital Picture Processing
Azriel Rosenfeld and Avinash Kak · 1982
Earlier work this paper cites.
Corner detection using the facet model
Oscar A. Zuniga and Robert M. Haralick · 1983
Earlier work this paper cites.
Recognition-by-components: A theory of human image understanding
Irving Biederman · 1987
Earlier work this paper cites.
A combined corner and edge detector
Chris Harris and Mike Stephens · 1988
Earlier work this paper cites.
Moment preserving corner detection
Song-Tyang Liu and Wen-Hsiang Tsai · 1990
Earlier work this paper cites.
Nonparametric local transforms for computing visual correspondence
Ramin Zabih and John Woodfill · 1994
Earlier work this paper cites.
Real-time corner detection algorithm for motion estimation
Han Wang and Michael Brady · 1995
Earlier work this paper cites.
A comparative study of texture measures with classification based on featured distributions
Timo Ojala, Matti Pietikäinen, and David Harwood · 1996
Earlier work this paper cites.
Edges are the independent components of natural scenes
Anthony Bell and Terrence Sejnowski · 1997
Earlier work this paper cites.
SUSAN — a new approach to low level image processing
Stephen M. Smith and J. Michael Brady · 1997
Earlier work this paper cites.
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner · 1998
Earlier work this paper cites.
Similarity search in high dimensions via hashing
Aristides Gionis, Piotr Indyk, and Rajeev Motwani · 1999
Earlier work this paper cites.
Robust wide-baseline stereo from maximally stable extremal regions
Jiří Matas, Ondřej Chum, Martin Urban, and Tomas Pajdla · 2002
Earlier work this paper cites.
A performance evaluation of local descriptors
Krystian Mikolajczyk and Cordelia Schmid · 2003
Earlier work this paper cites.
Evaluation of salient point techniques
Nicu Sebe, Qi Tian, Etienne Loupias, Michael S. Lew, and Thomas S. Huang · 2003
Earlier work this paper cites.
Fast pose estimation with parameter sensitive hashing
Gregory Shakhnarovich, Paul Viola, and Trevor Darrell · 2003
Earlier work this paper cites.
Video google: A text retrieval approach to object matching in videos
Josef Sivic, and Andrew Zisserman · 2003
Earlier work this paper cites.
Visual categorization with bags of keypoints
Gabriela Csurka, Christopher R. Dance, Lixin Fan, Jutta Willamowski, and Cédric Bray · 2004
Earlier work this paper cites.
An affine invariant salient region detector
Timor Kadir, Andrew Zisserman, and Michael Brady · 2004
Earlier work this paper cites.
PCA-SIFT: A more distinctive representation for local image descriptors
Yan Ke and Rahul Sukthankar · 2004
Earlier work this paper cites.
Distinctive image features from scale-invariant keypoints
David G. Lowe · 2004
Earlier work this paper cites.
Scale and affine invariant interest point detectors
Krystian Mikolajczyk and Cordelia Schmid · 2004
Earlier work this paper cites.
Multi-image matching using multi-scale oriented patches
Matthew Brown, Richard Szeliski, and Simon Winder · 2005
Earlier work this paper cites.
Coherent regions for concise and stable image description
Jason J. Corso and Gregory D. Hager · 2005
Earlier work this paper cites.
A comparison of affine region detectors
Krystian Mikolajczyk, Tinne Tuytelaars, Cordelia Schmid, Andrew Zisserman, Jiří Matas, Timor Schaffalitzky, Frederik Kadir, and Luc Van Gool · 2005
Earlier work this paper cites.
CSIFT: A SIFT descriptor with color invariant characteristics
Alaa E. Abdel-Hakim and Aly A. Farag · 2006
Earlier work this paper cites.
SURF: Speeded up robust features
Herbert Bay, Tinne Tuytelaars, and Luc Van Gool · 2006
Earlier work this paper cites.
Keypoint recognition using randomized trees
Vincent Lepetit and Pascal Fua · 2006
Earlier work this paper cites.
Machine learning for high-speed corner detection
Edward Rosten and Tom Drummond · 2006
Earlier work this paper cites.
Task specific local region matching
Boris Babenko, Piotr Dollár, and Serge Belongie · 2007
Earlier work this paper cites.
Fisher kernels on visual vocabularies for image categorization
Florent Perronnin and Christopher R. Dance · 2007
Earlier work this paper cites.
Object retrieval with large vocabularies and fast spatial matching
James Philbin, Ondřej Chum, Michael Isard, Josef Sivic, and Andrew Zisserman · 2007
Earlier work this paper cites.
Local invariant feature detectors: A survey
Tinne Tuytelaars and Krystian Mikolajczyk · 2007
Earlier work this paper cites.
Learning local image descriptors
Matthew Winder, Simon or Brown · 2007
Earlier work this paper cites.
Registration of challenging image pairs: Initialization, estimation, and decision
Gehua Yang, Charles V. Stewart, Michal Sofka, and Chia-Ling Tsai · 2007
Earlier work this paper cites.
A deformable local image descriptor
Hong Cheng, Zicheng Liu, Nanning Zheng, and Jie Yang · 2008
Earlier work this paper cites.
Learned local descriptors for recognition and matching
Michael Jahrer, Michael Grabner, and Horst Bischof · 2008
Earlier work this paper cites.
Computing information retrieval performance measures efficiently in the presence of tied scores
Frank McSherry and Marc Najork · 2008
Earlier work this paper cites.
On benchmarking camera calibration and multi-view stereo for high resolution imagery
Christoph Strecha, Wolfgang von Hansen, Luc Van Gool, Pascal Fua, and Ulrich Thoennessen · 2008
Earlier work this paper cites.
Feature correspondence via graph matching: Models and global optimization
Lorenzo Torresani, Vladimir Kolmogorov, and Carsten Rother · 2008
Earlier work this paper cites.
Spectral hashing
Yair Weiss, Antonio Torralba, and Robert Fergus · 2008
Earlier work this paper cites.
Shape analysis using the auto diffusion function
Katarzyna Gebal, Jakob Andreas Bærentzen, Henrik Aanæs, and Rasmus Larsen · 2009
Earlier work this paper cites.
Kernelized locality-sensitive hashing for scalable image search
Brian Kulis and Kristen Grauman · 2009
Earlier work this paper cites.
Efficient representation of local geometry for large scale object retrieval
Michal Perd’och, Ondřej Chum, and Jiří Matas · 2009
Earlier work this paper cites.
Training for task specific keypoint detection
Christoph Strecha, Albrecht Lindner, Karim Ali, and Pascal Fua · 2009
Earlier work this paper cites.
A concise and provably informative multi-scale signature based on heat diffusion
Jian Sun, Maks Ovsjanikov, and Leonidas Guibas · 2009
Earlier work this paper cites.
Distance metric learning for large margin nearest neighbor classification
Kilian Q. Weinberger and Lawrence K. Saul · 2009
Earlier work this paper cites.
Discriminative learning of local image descriptors
Matthew Brown, Gang Hua, and Simon Winder · 2010
Earlier work this paper cites.
Brief: Binary robust independent elementary features
Michael Calonder, Vincent Lepetit, Christoph Strecha, and Pascal Fua · 2010
Cited alongside, same era.
Accurate, dense, and robust multiview stereopsis
Yasutaka Furukawa and Jean Ponce · 2010
Cited alongside, same era.
K-nearest neighbor search: Fast GPU-based implementations and application to high-dimensional feature matching
Vincent Garcia, Éric Debreuve, Frank Nielsen, and Michel Barlaud · 2010
Cited alongside, same era.
Aggregating local descriptors into a compact image representation
Hervé Jégou, Matthijs Douze, Cordelia Schmid, and Patrick Pérez · 2010
Cited alongside, same era.
Descriptor learning for efficient retrieval
James Philbin, Michael Isard, Josef Sivic, and Andrew Zisserman · 2010
Cited alongside, same era.
Simultaneous pose, correspondence and non-rigid shape
Jordi Sanchez-Riera, Jonas Östlund, Pascal Fua, and Francesc Moreno-Noguer · 2010
Local multi-grouped binary descriptor with ring-based pooling configuration and optimization
Yongqiang Gao, Weilin Huang, and Yu Qiao · 2015
Later among the works it cites.
MatchNet: Unifying feature and metric learning for patch-based matching
Xufeng Han, Thomas Leung, Yangqing Jia, Rahul Sukthankar, and Alexander C. Berg · 2015
Later among the works it cites.
Decoupled deep neural network for semi-supervised semantic segmentation
Seunghoon Hong, Hyeonwoo Noh, and Bohyung Han · 2015
Later among the works it cites.
Spatial transformer networks
Max Jaderberg, Karen Simonyan, Andrew Zisserman, et al · 2015
Later among the works it cites.
Deep learning
Yann LeCun, Yoshua Bengio, and Geoffrey Hinton · 2015
Later among the works it cites.
LATCH: learned arrangements of three patch codes
Gil Levi and Tal Hassner · 2015
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited alongside, same era.
Daisy: An efficient dense descriptor applied to wide-baseline stereo
Engin Tola, Vincent Lepetit, and Pascal Fua · 2010
Cited alongside, same era.
Dual averaging methods for regularized stochastic learning and online optimization
Liu Xiao · 2010
Cited alongside, same era.
Iterative quantization: A procrustean approach to learning binary codes
Yunchao Gong and Svetlana Lazebnik · 2011
Cited alongside, same era.
BRISK: Binary robust invariant scalable keypoints
Stefan Leutenegger, Margarita Chli, and Roland Y. Siegwart · 2011
Cited alongside, same era.
Computer Vision Using Binary Patterns , volume 40
Matti Pietikäinen, Abdenour Hadid, Guoying Zhao, and Timo Ahonen · 2011
Cited alongside, same era.
ORB: An efficient alternative to SIFT or SURF
Ethan Rublee, Vincent Rabaud, Kurt Konolige, and Gary Bradski · 2011
Cited alongside, same era.
Bilinear CNN models for fine-grained visual recognition
Tsung-Yu Lin, Aruni RoyChowdhury, and Subhransu Maji · 2015
Later among the works it cites.
Learning compact binary face descriptor for face recognition
Jiwen Lu, Xiuzhuang Liong, Venice Erin Zhou, and Jie Zhou · 2015
Later among the works it cites.
WxBS: Wide baseline stereo generalizations
Dmytro Mishkin, Jiří Matas, Michal Perdoch, and Karel Lenc · 2015
Later among the works it cites.
Object scene flow for autonomous vehicles
Menze Moritz and Geiger Andreas · 2015
Later among the works it cites.
Local convolutional features with unsupervised training for image retrieval
Mattis Paulin, Matthijs Douze, Zaid Harchaoui, Julien Mairal, Florent Perronin, and Cordelia Schmid · 2015
Later among the works it cites.
Deep learning in neural networks: An overview
Jürgen Schmidhuber · 2015
Later among the works it cites.
Going deeper with convolutions
Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich · 2015
Later among the works it cites.
Learning image descriptors with boosting
Tomasz Trzcinski, Mario Christoudias, and Vincent Lepetit · 2015
Later among the works it cites.
TILDE: A temporally invariant learned detector
Yannick Verdie, Kwang Moo Yi, Pascal Fua, and Vincent LePetit · 2015
Later among the works it cites.
Show, attend and tell: Neural image caption generation with visual attention
Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio · 2015
Later among the works it cites.
Learning to compare image patches via convolutional neural networks
Sergey Zagoruyko and Nikos Komodakis · 2015
Later among the works it cites.
Universal correspondence network
Christopher B. Choy, JunYoung Gwak, Silvio Savarese, and Manmohan Chandraker · 2016
Later among the works it cites.
Deep learning
Ian Goodfellow, Yoshua Bengio, Aaron Courville, and Yoshua Bengio · 2016
Later among the works it cites.
Deep residual learning for image recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun · 2016
Later among the works it cites.
The HCI benchmark suite: Stereo and flow ground truth with uncertainties for urban autonomous driving
Daniel Kondermann, Rahul Nair, Katrin Honauer, Karsten Krispin, Jonas Andrulis, Alexander Brock, Güssefeld Burkhard, Mohsen Rahimimoghaddam, Sabine Hofmann, Claus Brenner, and B. Jähne · 2016
Later among the works it cites.
Learning local image descriptors with deep siamese and triplet convolutional networks by minimizing global loss functions
Vijay Kumar B. G., Gustavo Carneiro, and Ian Reid · 2016
Later among the works it cites.
Learning covariant feature detectors
Karel Lenc and Andrea Vedaldi · 2016
Later among the works it cites.
Learning compact binary descriptors with unsupervised deep neural networks
Kevin Lin, Jiwen Lu, Chu-Song Chen, and Jie Zhou · 2016
Later among the works it cites.
Yu A. Malkov and D. A. Yashunin · 2016
Later among the works it cites.
Structure-from-motion revisited
Johannes L. Schönberger and Jan-Michael Frahm · 2016
Later among the works it cites.
Learning deep embeddings with histogram loss
Evgenia Ustinova and Victor Lempitsky · 2016
Later among the works it cites.
Exploring local and overall ordinal information for robust feature description
Zhenhua Wang, Bin Fan, Gang Wang, and Fuchao Wu · 2016
Later among the works it cites.
Stereo matching by training a convolutional neural network to compare image patches
Jure Zbontar and Yann LeCun · 2016
Later among the works it cites.
HPatches: A benchmark and evaluation of handcrafted and learned local descriptors
Vassileios Balntas, Karel Lenc, Andrea Vedaldi, and Krystian Mikolajczyk · 2017
Later among the works it cites.
SIFTing through scales
Tal Hassner, Shay Filosof, Viki Mayzels, and Lihi Zelnik-Manor · 2017
Later among the works it cites.
Densely connected convolutional networks
Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q. Weinberger · 2017
Later among the works it cites.
Ground truth accuracy and performance of the matching pipeline
Josef Maier, Martin Humenberger, Oliver Zendel, and Markus Vincze · 2017
Later among the works it cites.
Working hard to know your neighbor’s margins: Local descriptor learning loss
Anastasiya Mishchuk, Dmytro Mishkin, Filip Radenović, and Jiří Matas · 2017
Later among the works it cites.
Large-scale image retrieval with attentive deep local features
Hyeonwoo Noh, André Araujo, Jack Sim, Tobias Weyand, and Bohyung Han · 2017
Later among the works it cites.
Quad-networks: unsupervised learning to rank for interest point detection
Nikolay Savinov, Akihito Seki, Lubor Ladicky, Torsten Sattler, and Marc Pollefeys · 2017
Later among the works it cites.
Comparative evaluation of hand-crafted and learned local features
Johannes L. Schönberger, Hans Hardmeier, Torsten Sattler, and Marc Pollefeys · 2017
Later among the works it cites.
A dataset for benchmarking image-based localization
Xun Sun, Yuanfan Xie, Pei Luo, and Liang Wang · 2017
Later among the works it cites.
L2-Net: Deep learning of discriminative patch descriptor in euclidean space
Yurun Tian, Bin Fan, and Fuchao Wu · 2017
Later among the works it cites.
DeepCD: Learning deep complementary descriptors for patch representations
Tsun-Yi Yang, Jo-Han Hsu, Yen-Yu Lin, and Yung-Yu Chuang · 2017
Later among the works it cites.
Learning discriminative and transformation covariant local feature detectors
Xu Zang, Felix X. Yu, Svebor Karaman, and Shih-Fu Chang · 2017
Later among the works it cites.
Learning spread-out local feature descriptors
Xu Zhang, Felix X. Yu, Sanjiv Kumar, and Shih-Fu Chang · 2017
Later among the works it cites.
Binary online learned descriptors
Vassileios Balntas, Lilian Tang, and Krystian Mikolajczyk · 2018
Closest in time.
SuperPoint: Self-supervised interest point detection and description
Daniel DeTone, Tomasz Malisiewicz, and Andrew Rabinovich · 2018
Closest in time.
Large scale evaluation of local image feature detectors on homography datasets
Karel Lenc and Andrea Vedaldi · 2018
Closest in time.
Simultaneous local binary feature learning and encoding for homogeneous and heterogeneous face recognition
Jiwen Lu, Venice Erin Liong, and Jie Zhou · 2018
Closest in time.
Kernelized subspace pooling for deep local descriptors
Xing Wei, Yue Zhang, Yihong Gong, and Nanning Zheng · 2018
Closest in time.