Publications

[Extracted from DiVA, the publication database at KTH.]

Lindeberg, T. (2021):
Scale selection.
Chapter in book [Details]
Lindeberg, T. (2021):
Normative theory of visual receptive fields.
Heliyon 7: e05897-1-e05897-20 [Details]
Jansson, Y.; Lindeberg, T. (2021):
Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scales.
Manuscript (preprint) [Details]
Lindeberg, T. (2021):
Scale-covariant and scale-invariant Gaussian derivative networks.
[Conference paper] SSVM 2021: 8th International Conference on Scale Space and Variational Methods in Computer Vision, May 16-20, 2021.; Scale Space and Variational Methods in Computer Vision 3-14 [Details]
Finnveden, L.; Jansson, Y.; Lindeberg, T. (2021):
Understanding when spatial transformer networks do not support invariance, and what to do about it.
[Conference paper] ICPR 2020: 25th International Conference on Pattern Recognition, Milan, Italy, January 10-15, 2021; ICPR 2020: International Conference on Pattern Recognition 3427-3434 [Details]
Jansson, Y.; Lindeberg, T. (2021):
Exploring the ability of CNNs to generalise to previously unseen scales over wide scale ranges.
[Conference paper] ICPR 2020: 25th International Conference on Pattern Recognition, Milan, Italy, January 10-15, 2021; ICPR 2020: International Conference on Pattern Recognition 1181-1188 [Details]
Finnveden, L.; Jansson, Y.; Lindeberg, T. (2020):
The problems with using STNs to align CNN feature maps.
[Conference paper] Northern Lights Deep Learning Workshop 2020, Tromsø, Norway, 20-21 Jan 2020; [Details]
Lindeberg, T. (2020):
Provably scale-covariant continuous hierarchical networks based on scale-normalized differential expressions coupled in cascade.
Journal of Mathematical Imaging and Vision 62: 120-148 [Details]
Jansson, Y.; Maydanskiy, M.; Finnveden, L.; Lindeberg, T. (2020):
Inability of spatial transformations of CNN feature maps to support invariant recognition.
Report [Details]
Jansson, Y.; Maydanskiy, M.; Finnveden, L.; Lindeberg, T. (2020):
Spatial transformations in convolutional networks and invariant recognition..
[Conference paper] DeepMath2020 Conference on the Mathematical Theory of Deep Neural Networks Nov 5 - Nov 6, 2020; [Details]
Jansson, Y.; Lindeberg, T. (2020):
Exploring the ability of CNNs to generalise to previously unseen scales over wide scale ranges.
Manuscript (preprint) [Details]
Jansson, Y.; Lindeberg, T. (2020):
MNIST Large Scale dataset.
Data set [Details]
Finnveden, L.; Jansson, Y.; Lindeberg, T. (2020):
Understanding when spatial transformer networks do not support invariance, and what to do about it.
Manuscript (preprint) [Details]
Lindeberg, T. (2020):
Scale-covariant and scale-invariant Gaussian derivative networks.
Report [Details]
Lindeberg, T. (2019):
Provably scale-covariant networks from oriented quasi quadrature measures in cascade.
[Conference paper] 7th International Conference on Scale Space and Variational Methods in Computer Vision, SSVM 2019; Hofgeismar; Germany; 30 June 2019 through 4 July 2019; Scale Space and Variational Methods in Computer Vision 328-340 [Details]
Lindeberg, T. (2018):
Spatio-temporal scale selection in video data.
Journal of Mathematical Imaging and Vision 60: 525-562 [Details]
Jansson, Y.; Lindeberg, T. (2018):
Dynamic texture recognition using time-causal and time-recursive spatio-temporal receptive fields.
Journal of Mathematical Imaging and Vision 60: 1369-1398 [Details]
Lindeberg, T. (2018):
Dense scale selection over space, time and space-time.
SIAM Journal on Imaging Sciences 11: 407-441 [Details]
Friberg, A.; Lindeberg, T.; Hellwagner, M.; Helgason, P.; Salomão, G.; Elovsson, A.; Lemaitre, G.; Ternström, S. (2018):
Prediction of three articulatory categories in vocal sound imitations using models for auditory receptive fields.
Journal of the Acoustical Society of America 144: 1467-1483 [Details]
Jansson, Y.; Lindeberg, T. (2017):
Dynamic texture recognition using time-causal and time-recursive spatio-temporal receptive fields.
Report [Details]
Lindeberg, T. (2017):
Discrete approximations of the affine Gaussian derivative model for visual receptive fields.
Report [Details]
Lindeberg, T. (2017):
Discrete approximations of affine Gaussian receptive fields.
Report [Details]
Jansson, Y.; Lindeberg, T. (2017):
Dynamic texture recognition using time-causal spatio-temporal scale-space filters.
[Conference paper] SSVM 2017: 6th International Conference on Scale Space and Variational Methods in Computer Vision, Kolding, Denmark, June 4-8, 2017; Scale Space and Variational Methods in Computer Vision 16-28 [Details]
Lindeberg, T. (2017):
Spatio-temporal scale selection in video data.
[Conference paper] SSVM 2017: 6th International Conference on Scale Space and Variational Methods in Computer Vision, Kolding, Denmark, June 4-8, 2017; Scale Space and Variational Methods in Computer Vision 3-15 [Details]
Lindeberg, T. (2017):
Temporal scale selection in time-causal scale space.
Journal of Mathematical Imaging and Vision 58: 57-101 [Details]
Lindeberg, T. (2017):
Normative theory of visual receptive fields.
Report [Details]
Ekeberg, Ö.; Fransén, E.; Hellgren Kotaleski, J.; Herman, P.; Kumar, A.; Lansner, A.; Lindeberg, T. (2016):
Computational Brain Science at CST, CSC, KTH.
Other [Details]
Lindeberg, T. (2016):
Time-causal and time-recursive spatio-temporal receptive fields.
Journal of Mathematical Imaging and Vision 55: 50-88 [Details]
Lindeberg, T. (2016):
Time-causal and time-recursive spatio-temporal receptive fields for computer vision and computational modelling of biological vision.
[Conference paper] International Workshop on Geometry, PDE’s and Lie Groups in Image Analysis, Eindhoven, The Netherlands, August 24-26, 2016.; International Workshop on Geometry, PDE’s and Lie Groups in Image Analysis, Eindhoven, The Netherlands, August 24-26, 2016. [Details]
Lindeberg, T. (2016):
Time-causal and time-recursive receptive fields for invariance and covariance under natural image transformations.
[Conference paper] First European Machine Vision Forum, Heidelberg, Germany, September 8-9, 2016.; [Details]
Lindeberg, T. (2015):
Time-causal and time-recursive spatio-temporal receptive fields.
Report [Details]
Lindeberg, T.; Friberg, A. (2015):
Scale-space theory for auditory signals.
[Conference paper] SSVM 2015: Fifth International Conference on Scale Space and Variational Methods in Computer Vision, Lège Cap Ferret, France, 31 May - 4 June, 2015; Scale Space and Variational Methods in Computer Vision 3-15 [Details]
Lindeberg, T. (2015):
Separable time-causal and time-recursive spatio-temporal receptive fields.
[Conference paper] SSVM 2015: Fifth International Conference on Scale Space and Variational Methods in Computer Vision, Lège Cap Ferret, France, 31 May - 4 June, 2015; Scale Space and Variational Methods in Computer Vision 90-102 [Details]
Lindeberg, T. (2015):
Image matching using generalized scale-space interest points.
Journal of Mathematical Imaging and Vision 52: 3-36 [Details]
Lindeberg, T.; Friberg, A. (2015):
Idealized computational models for auditory receptive fields.
PLOS ONE 10: [Details]
Lindeberg, T. (2014):
Scale selection.
Chapter in book [Details]
Lindeberg, T. (2013):
Invariance of visual operations at the level of receptive fields.
[Conference paper] CNS 2013: 22nd Annual Computational Neuroscience Meeting, July 13-18, Paris, France. BMC Neuroscience 14(Suppl 1); P242 [Details]
Lindeberg, T. (2013):
Generalized axiomatic scale-space theory.
Chapter in book [Details]
Lindeberg, T. (2013):
Image matching using generalized scale-space interest points.
[Conference paper] SSVM 2013: Fourth International Conference on Scale Space and Variational Methods in Computer Vision, June 2-6, 2013, Schloss Seggau, Graz region, Austria; Scale Space and Variational Methods in Computer Vision: 4th International Conference, SSVM 2013, Schloss Seggau, Leibnitz, Austria, , June 2-6, 2013, Proceedings 355-367 [Details]
Lindeberg, T. (2013):
Scale Selection Properties of Generalized Scale-Space Interest Point Detectors.
Journal of Mathematical Imaging and Vision 46: 177-210 [Details]
Lindeberg, T. (2013):
A framework for invariant visual operations based on receptive field responses.
[Conference paper] SSVM 2013: Fourth International Conference on Scale Space and Variational Methods in Computer Vision, June 2-6, Schloss Seggau, Graz region, Austria; SSVM 2013: Fourth International Conference on Scale Space and Variational Methods in Computer Vision, June 2-6, Schloss Seggau, Graz region, Austria [Details]
Lindeberg, T. (2013):
A computational theory of visual receptive fields.
Biological Cybernetics 107: 589-635 [Details]
Lindeberg, T. (2013):
Invariance of visual operations at the level of receptive fields.
PLOS ONE 8: e66990-1-e66990-33 [Details]
Lindeberg, T. (2012):
Scale invariant feature transform.
Other [Details]
Linde, O.; Lindeberg, T. (2012):
Composed Complex-Cue Histograms - An Investigation of the Information Content in Receptive Field Based Image Descriptors for Object Recognition.
Computer Vision and Image Understanding 116: 538-560 [Details]
Lindeberg, T. (2011):
Generalized Gaussian Scale-Space Axiomatics Comprising Linear Scale-Space, Affine Scale-Space and Spatio-Temporal Scale-Space.
Journal of Mathematical Imaging and Vision 40: 36-81 [Details]
Lindeberg, T. (2009):
Scale-Space.
Chapter in book [Details]
Laptev, I.; Caputo, B.; Schüldt, C.; Lindeberg, T. (2007):
Local velocity-adapted motion events for spatio-temporal recognition.
Computer Vision and Image Understanding 108: 207-229 [Details]
Laptev, I.; Lindeberg, T. (2006):
Local descriptors for spatio-temporal recognition.
[Conference paper] 1st International Workshop on Spatial Coherence for Visual Motion Analysis, SCVMA 2004; Prague; 15 May 2004 through 15 May 2004; Spatial Coherence For Visual Motion Analysis 91-103 [Details]
Laptev, I.; Lindeberg, T. (2004):
Velocity adaptation of space-time interest points.
[Conference paper] 17th International Conference on Pattern Recognition (ICPR) Location: British Machine Vis Assoc, Cambridge, ENGLAND Date: AUG 23-26, 2004; Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004 52-56 [Details]

More