pith. sign in

arxiv: 2606.22182 · v1 · pith:RHPUGWEOnew · submitted 2026-06-20 · 💻 cs.CV · cs.AI

Dual-Stream EEG Decoding for 3D Visual Perception

Ninon Liz\'e Masclef , Taisija Demcenko , Antonella Catanzaro , Nataliya Kosmyna This is my paper

Pith reviewed 2026-06-26 12:07 UTC · model grok-4.3

classification 💻 cs.CV cs.AI
keywords EEG decoding3D visual perceptiondual-stream architectureobject identityspatial orientationcircular regressionneural 3D reconstruction
0
0 comments X

The pith

A dual-stream EEG decoder extracts both object identity and continuous 3D orientation to support neural 3D reconstruction.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper develops a brain-decoding model that splits processing into two pathways, one for identifying objects and one for tracking their rotation angle, directly from EEG recordings taken while people view rotating 3D shapes. This split mirrors the brain's separate routes for "what" and "where" information and feeds the decoded signals into a diffusion model that reconstructs the viewed shapes. The approach matters because it moves beyond static image classification to recover dynamic 3D structure from neural activity. Interpretability results show that ventral, dorsal, and motor channels contribute at different moments rather than in a fixed pattern. If the separation works, EEG can supply usable signals for both recognition and geometry without requiring a single combined decoder.

Core claim

A dual-pathway architecture mirroring ventral and dorsal streams implements separate decoding modules for object identity and spatial orientation during continuous rotations; circular regression predicts angle while an EEG-conditioned multiview diffusion model produces 3D reconstructions, and channel analyses reveal temporally structured contributions from ventral, dorsal, and motor-related signals instead of static ventral dominance.

What carries the argument

Dual-stream decoder with one identity pathway and one circular-regression orientation pathway, followed by EEG-conditioned multiview diffusion for reconstruction.

If this is right

  • EEG signals during object rotation contain separable information about both identity and continuous orientation.
  • Neural activity can condition a diffusion process to output 3D shape reconstructions without intermediate image generation.
  • Channel contributions to decoding shift across time rather than remaining fixed to one visual stream.
  • Motor-related channels participate alongside ventral and dorsal channels during the task.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same dual-stream separation could be tested on EEG data from static viewing to check whether rotation is required for the temporal structure to appear.
  • If the angle decoder generalizes across objects, it could support viewpoint-invariant 3D reconstruction pipelines.
  • The observed timing differences suggest experiments that disrupt specific time windows to test causal roles of each channel group.

Load-bearing premise

Splitting the model into separate ventral-like and dorsal-like streams produces independent, usable signals for both identity and continuous angle from the same EEG recordings.

What would settle it

A controlled comparison in which a single shared decoder matches or exceeds the dual-stream model's accuracy on both identity classification and angle regression on the identical EEG dataset would falsify the need for the split.

Figures

Figures reproduced from arXiv: 2606.22182 by Antonella Catanzaro, Nataliya Kosmyna, Ninon Liz\'e Masclef, Taisija Demcenko.

Figure 1
Figure 1. Figure 1: Proposed dual-stream architecture for 3D brain decoding from EEG. [PITH_FULL_IMAGE:figures/full_fig_p006_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Top bias scores of different channel subsets, with subjects sorted from best per [PITH_FULL_IMAGE:figures/full_fig_p008_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Multi-view test set reconstructions across 6 categories (ground truth: top, gener [PITH_FULL_IMAGE:figures/full_fig_p009_3.png] view at source ↗
read the original abstract

This paper explores a novel brain decoding model for 3D shape perception through a dual pathway architecture mirroring biological vision. Our bio-inspired approach implements separate decoding modules for object identity and spatial orientation, inspired by ventral and dorsal pathways, during continuous rotations. We employ circular regression for angle prediction and develop EEG-conditioned multiview diffusion for 3D reconstruction. Our approach successfully decodes both object identity and spatial orientation from EEG signals and enables 3D reconstruction from neural activity, with interpretability analyses revealing temporally structured involvement of ventral, dorsal, and motor-related channels rather than a static ventral dominance in supporting object and angle decoding.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The paper proposes a dual-stream EEG decoding architecture inspired by ventral and dorsal visual pathways to separately decode object identity and spatial orientation from EEG signals recorded during continuous 3D object rotations. It employs circular regression for angle prediction and an EEG-conditioned multiview diffusion model for 3D reconstruction from neural activity. The central claims are successful decoding of both identity and orientation, enabling 3D reconstruction, and interpretability results showing temporally structured involvement of ventral, dorsal, and motor channels rather than static ventral dominance.

Significance. If the quantitative results and ablations support the claims, the work would advance EEG-based 3D perception decoding by providing a bio-inspired separable architecture and a new reconstruction pipeline, with potential implications for BCI and understanding stream-specific temporal dynamics in visual processing.

major comments (1)
  1. [Abstract] Abstract: The central claim of successful decoding and reconstruction is asserted without any reported metrics, baselines, error bars, participant numbers, or method implementation details, rendering the claim unevaluable from the supplied text and preventing assessment of whether the dual-stream design delivers separable signals.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their comments. We address the concern about the abstract below and will revise accordingly to improve evaluability.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The central claim of successful decoding and reconstruction is asserted without any reported metrics, baselines, error bars, participant numbers, or method implementation details, rendering the claim unevaluable from the supplied text and preventing assessment of whether the dual-stream design delivers separable signals.

    Authors: We agree that the provided abstract does not contain quantitative metrics, baselines, error bars, participant numbers or implementation details, which limits immediate evaluation of the claims from the abstract alone. The full manuscript reports these details in the results and methods sections, including identity decoding accuracy, circular regression angular errors, reconstruction metrics, participant count, and ablations demonstrating separable ventral/dorsal contributions. We will revise the abstract to incorporate the key quantitative results and participant information from the paper to make the central claims directly evaluable while preserving brevity. revision: yes

Circularity Check

0 steps flagged

No circularity in derivation chain

full rationale

The supplied abstract and description contain no equations, derivations, or analytical steps that could reduce to self-definition, fitted inputs renamed as predictions, or self-citation load-bearing claims. The work describes an empirical bio-inspired neural architecture for EEG decoding and 3D reconstruction; central claims rest on experimental results rather than any closed mathematical chain. No load-bearing premise is justified solely by prior self-citation or ansatz smuggling. This is the expected outcome for an applied ML paper lacking formal derivations.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review supplies no information on free parameters, background axioms, or new postulated entities.

pith-pipeline@v0.9.1-grok · 5640 in / 1033 out tokens · 30752 ms · 2026-06-26T12:07:15.201103+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

292 extracted references · 246 canonical work pages · 14 internal anchors

  1. [1]

    Lizé Masclef, Ninon and Demcenko, Taisija and Catanzaro, Antonella and Kosmyna, Nataliya , year =. Dual-. Proceedings of

  2. [2]

    Onoo, Shunsuke and Nagano, Yoshihiro and Kamitani, Yukiyasu , year =. Readout. doi:10.48550/ARXIV.2510.12228 , abstract =

    work page doi:10.48550/arxiv.2510.12228

  3. [3]

    International Association for the Study of Dreams 40th Annual Dream Conference , author =

    Reconstructing the. International Association for the Study of Dreams 40th Annual Dream Conference , author =

  4. [4]

    Brain-Computer Interfaces , author =

    Riemannian geometry for. Brain-Computer Interfaces , author =. 2017 , pages =. doi:10.1080/2326263X.2017.1297192 , language =

    work page doi:10.1080/2326263x.2017.1297192 2017

  5. [5]

    Kneeland, Reese and Torrico, Cesar and Chen, Tong and Ojeda, Jordyn Antonio and Khanna, Shubh and Xu, Jonathan and Scotti, Paul Steven and Naselaris, Thomas , month = oct, year =

  6. [6]

    Journal of Cognitive Neuroscience , author =

    Using. Journal of Cognitive Neuroscience , author =. 2022 , pages =. doi:10.1162/jocn_a_01845 , abstract =

    work page doi:10.1162/jocn_a_01845 2022

  7. [7]

    The Journal of Neuroscience , author =

    Dorsal–. The Journal of Neuroscience , author =. 2009 , pages =. doi:10.1523/JNEUROSCI.4978-08.2009 , abstract =

    work page doi:10.1523/jneurosci.4978-08.2009 2009

  8. [8]

    Cerebral Cortex Communications , author =

    Temporal asymmetries and interactions between dorsal and ventral visual pathways during object recognition , volume =. Cerebral Cortex Communications , author =. 2023 , pages =. doi:10.1093/texcom/tgad003 , abstract =

    work page doi:10.1093/texcom/tgad003 2023

  9. [9]

    and Aoki, Shuntaro C

    Wang, Haibao and Ho, Jun Kai and Cheng, Fan L. and Aoki, Shuntaro C. and Muraki, Yusuke and Tanaka, Misato and Park, Jong-Yun and Kamitani, Yukiyasu , month = jul, year =. Inter-individual and inter-site neural code conversion without shared stimuli , volume =. Nature Computational Science , publisher =. doi:10.1038/s43588-025-00826-5 , abstract =

    work page doi:10.1038/s43588-025-00826-5

  10. [10]

    NeuroImage , author =

    Inter-individual deep image reconstruction via hierarchical neural code conversion , volume =. NeuroImage , author =. 2023 , keywords =. doi:10.1016/j.neuroimage.2023.120007 , abstract =

    work page doi:10.1016/j.neuroimage.2023.120007 2023

  11. [11]

    NeuroImage , author =

    Inter-subject neural code converter for visual image representation , volume =. NeuroImage , author =. 2015 , keywords =. doi:10.1016/j.neuroimage.2015.03.059 , abstract =

    work page doi:10.1016/j.neuroimage.2015.03.059 2015

  12. [12]

    Constraints on an external reality under the simulation hypothesis , abstract =

  13. [13]

    Meaning is perspectival and associated with physical action , language =

  14. [14]

    Cognitive and Behavioral Neurology , author =

    Consciousness as a. Cognitive and Behavioral Neurology , author =. 2022 , pages =. doi:10.1097/WNN.0000000000000319 , abstract =

    work page doi:10.1097/wnn.0000000000000319 2022

  15. [15]

    Advancing

    Schreiner, Leonhard and Sieghartsleitner, Sebastian and La Rosa, Matteo and Tanackovic, Slobodan and Pretl, Harald and Colamarino, Emma and Guger, Christoph , month = oct, year =. Advancing. 2024. doi:10.1109/MetroXRAINE62247.2024.10796840 , abstract =

    work page doi:10.1109/metroxraine62247.2024.10796840 2024

  16. [16]

    Epoché Magazine , author =

    Gilbert. Epoché Magazine , author =

  17. [17]

    Journal of Mathematical Neuroscience , author =

    Rendering neuronal state equations compatible with the principle of stationary action , volume =. Journal of Mathematical Neuroscience , author =. 2021 , pages =. doi:10.1186/s13408-021-00108-0 , abstract =

    work page doi:10.1186/s13408-021-00108-0 2021

  18. [18]

    Theoretical Computer Science , author =

    The principle of least cognitive action , volume =. Theoretical Computer Science , author =. 2016 , keywords =. doi:10.1016/j.tcs.2015.06.042 , abstract =

    work page doi:10.1016/j.tcs.2015.06.042 2016

  19. [19]

    , month = mar, year =

    Khona, Mikail and Fiete, Ila R. , month = mar, year =. Attractor and integrator networks in the brain , url =. doi:10.48550/arXiv.2112.03978 , abstract =

    work page doi:10.48550/arxiv.2112.03978

  20. [21]

    Decoding of image properties from single-trial visual evoked potentials recorded by ultra-high-density

    Sieghartsleitner, Sebastian and Schreiner, Leonhard and Grünwald, Johannes and Jordan, Michael and Spataro, Rossella and Scharinger, Josef and Guger, Christoph , month = sep, year =. Decoding of image properties from single-trial visual evoked potentials recorded by ultra-high-density. Scientific Reports , publisher =. doi:10.1038/s41598-025-18275-5 , abstract =

    work page doi:10.1038/s41598-025-18275-5

  21. [22]

    Neuroscience & Biobehavioral Reviews , author =

    Sleep and dreaming in the light of reactive and predictive homeostasis , volume =. Neuroscience & Biobehavioral Reviews , author =. 2023 , keywords =. doi:10.1016/j.neubiorev.2023.105104 , abstract =

    work page doi:10.1016/j.neubiorev.2023.105104 2023

  22. [23]

    Holmes, Jeremy and Nolte, Tobias , month = mar, year =. “. Frontiers in Psychology , publisher =. doi:10.3389/fpsyg.2019.00592 , abstract =

    work page doi:10.3389/fpsyg.2019.00592 2019

  23. [24]

    Psychoanalytic psychotherapies and the free energy principle , volume =

    Rabeyron, Thomas , month = aug, year =. Psychoanalytic psychotherapies and the free energy principle , volume =. Frontiers in Human Neuroscience , publisher =. doi:10.3389/fnhum.2022.929940 , abstract =

    work page doi:10.3389/fnhum.2022.929940 2022

  24. [25]

    Frontiers in Psychology , author =

    Free. Frontiers in Psychology , author =. 2016 , pages =. doi:10.3389/fpsyg.2016.00922 , abstract =

    work page doi:10.3389/fpsyg.2016.00922 2016

  25. [26]

    , month = jun, year =

    Jha, Rishi and Zhang, Collin and Shmatikov, Vitaly and Morris, John X. , month = jun, year =. Harnessing the. doi:10.48550/arXiv.2505.12540 , abstract =

    work page doi:10.48550/arxiv.2505.12540

  26. [27]

    Huh, Minyoung and Cheung, Brian and Wang, Tongzhou and Isola, Phillip , month = jul, year =. The. doi:10.48550/arXiv.2405.07987 , abstract =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2405.07987

  27. [28]

    and Jirsa, Viktor K

    Pillai, Ajay S. and Jirsa, Viktor K. , month = jun, year =. Symmetry. Neuron , publisher =. doi:10.1016/j.neuron.2017.05.013 , language =

    work page doi:10.1016/j.neuron.2017.05.013 2017

  28. [29]

    Annual review of neuroscience , author =

    Computation. Annual review of neuroscience , author =. 2020 , pages =. doi:10.1146/annurev-neuro-092619-094115 , abstract =

    work page doi:10.1146/annurev-neuro-092619-094115 2020

  29. [30]

    Is perception discrete or continuous? , volume =

    VanRullen, Rufin and Koch, Christof , month = may, year =. Is perception discrete or continuous? , volume =. Trends in Cognitive Sciences , publisher =. doi:10.1016/S1364-6613(03)00095-0 , language =

    work page doi:10.1016/s1364-6613(03)00095-0

  30. [31]

    Physical Review E , author =

    Thermodynamics of feedback controlled systems , volume =. Physical Review E , author =. 2009 , note =. doi:10.1103/PhysRevE.79.041118 , abstract =

    work page doi:10.1103/physreve.79.041118 2009

  31. [32]

    Memory and entropy , url =

    Rovelli, Carlo , month = mar, year =. Memory and entropy , url =. doi:10.48550/arXiv.2003.06687 , abstract =

    work page doi:10.48550/arxiv.2003.06687 2003

  32. [33]

    Optimal transport for machine learning -

  33. [34]

    Computational

    Peyré, Gabriel and Cuturi, Marco , month = mar, year =. Computational. doi:10.48550/arXiv.1803.00567 , abstract =

    work page doi:10.48550/arxiv.1803.00567

  34. [35]

    Topics in optimal transportation , isbn =

    Villani, Cédric , year =. Topics in optimal transportation , isbn =

  35. [36]

    An invitation to optimal transport,

    Figalli, Alessio and Glaudo, Federico , year =. An invitation to optimal transport,

  36. [37]

    IEEE Trans

    Recent. IEEE Trans. Pattern Anal. Mach. Intell. , author =. 2025 , pages =. doi:10.1109/TPAMI.2024.3489030 , abstract =

    work page doi:10.1109/tpami.2024.3489030 2025

  37. [38]

    Advances in optimal transport and applications to neuroscience , abstract =

  38. [39]

    IEEE transactions on bio-medical engineering , author =

    Transfer. IEEE transactions on bio-medical engineering , author =. 2022 , keywords =. doi:10.1109/TBME.2021.3105912 , abstract =

    work page doi:10.1109/tbme.2021.3105912 2022

  39. [40]

    LoRA: Low-Rank Adaptation of Large Language Models

    Hu, Edward J. and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Wang, Lu and Chen, Weizhu , month = oct, year =. doi:10.48550/arXiv.2106.09685 , abstract =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2106.09685

  40. [41]

    MVDream: Multi-view Diffusion for 3D Generation

    Shi, Yichun and Wang, Peng and Ye, Jianglong and Long, Mai and Li, Kejie and Yang, Xiao , month = apr, year =. doi:10.48550/arXiv.2308.16512 , abstract =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2308.16512

  41. [42]

    , month = may, year =

    Luck, Steven J. , month = may, year =. An

  42. [43]

    Practical Bayesian Optimization of Machine Learning Algorithms

    Snoek, Jasper and Larochelle, Hugo and Adams, Ryan P. , month = aug, year =. Practical. doi:10.48550/arXiv.1206.2944 , abstract =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1206.2944

  43. [44]

    Scientific Reports , publisher =

    Zhao, Wei and Jiang, Xiaolu and Zhang, Baocan and Xiao, Shixiao and Weng, Sujun , month = aug, year =. Scientific Reports , publisher =. doi:10.1038/s41598-024-71118-7 , abstract =

    work page doi:10.1038/s41598-024-71118-7

  44. [46]

    Journal of Neurophysiology , author =

    Integration of. Journal of Neurophysiology , author =. 2001 , pages =. doi:10.1152/jn.2001.86.6.2856 , abstract =

    work page doi:10.1152/jn.2001.86.6.2856 2001

  45. [47]

    Evidence of a predictive coding hierarchy in the human brain listening to speech , volume =

    Caucheteux, Charlotte and Gramfort, Alexandre and King, Jean-Rémi , month = mar, year =. Evidence of a predictive coding hierarchy in the human brain listening to speech , volume =. Nature Human Behaviour , publisher =. doi:10.1038/s41562-022-01516-2 , abstract =

    work page doi:10.1038/s41562-022-01516-2

  46. [48]

    DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation

    Park, Jeong Joon and Florence, Peter and Straub, Julian and Newcombe, Richard and Lovegrove, Steven , month = jan, year =. doi:10.48550/arXiv.1901.05103 , abstract =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1901.05103 1901

  47. [49]

    IEEE Transactions on Neural Networks and Learning Systems , author =

    Spatio-. IEEE Transactions on Neural Networks and Learning Systems , author =. 2021 , keywords =. doi:10.1109/TNNLS.2020.3048385 , abstract =

    work page doi:10.1109/tnnls.2020.3048385 2021

  48. [50]

    ResearchGate , month = aug, year =

    (. ResearchGate , month = aug, year =. doi:10.1016/j.cad.2011.04.008 , abstract =

    work page doi:10.1016/j.cad.2011.04.008 2011

  49. [51]

    Experimental Brain Research , author =

    Source locations of pattern-specific components of human visual evoked potentials. Experimental Brain Research , author =. 1972 , keywords =. doi:10.1007/BF00233371 , language =

    work page doi:10.1007/bf00233371 1972

  50. [52]

    Nature Reviews

    A new neural framework for visuospatial processing , volume =. Nature Reviews. Neuroscience , author =. 2011 , keywords =. doi:10.1038/nrn3008 , abstract =

    work page doi:10.1038/nrn3008 2011

  51. [53]

    Nature Neuroscience , author =

    Patches of face-selective cortex in the macaque frontal lobe , volume =. Nature Neuroscience , author =. 2008 , keywords =. doi:10.1038/nn.2158 , abstract =

    work page doi:10.1038/nn.2158 2008

  52. [54]

    General \

    Weiler, Maurice and Cesa, Gabriele , month = apr, year =. General \. doi:10.48550/arXiv.1911.08251 , abstract =

    work page doi:10.48550/arxiv.1911.08251 1911

  53. [55]

    Group Equivariant Convolutional Networks

    Cohen, Taco S. and Welling, Max , month = jun, year =. Group. doi:10.48550/arXiv.1602.07576 , abstract =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1602.07576

  54. [56]

    Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds

    Thomas, Nathaniel and Smidt, Tess and Kearnes, Steven and Yang, Lusann and Li, Li and Kohlhoff, Kai and Riley, Patrick , month = may, year =. Tensor field networks:. doi:10.48550/arXiv.1802.08219 , abstract =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1802.08219

  55. [57]

    and Tancik, Matthew and Barron, Jonathan T

    Mildenhall, Ben and Srinivasan, Pratul P. and Tancik, Matthew and Barron, Jonathan T. and Ramamoorthi, Ravi and Ng, Ren , month = aug, year =. doi:10.48550/arXiv.2003.08934 , abstract =

    work page doi:10.48550/arxiv.2003.08934 2003

  56. [58]

    Inductive Representation Learning on Large Graphs

    Hamilton, William L. and Ying, Rex and Leskovec, Jure , month = sep, year =. Inductive. doi:10.48550/arXiv.1706.02216 , abstract =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1706.02216

  57. [59]

    Semi-Supervised Classification with Graph Convolutional Networks

    Kipf, Thomas N. and Welling, Max , month = feb, year =. Semi-. doi:10.48550/arXiv.1609.02907 , abstract =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1609.02907

  58. [60]

    Zhao, Hengshuang and Jiang, Li and Jia, Jiaya and Torr, Philip and Koltun, Vladlen , month = sep, year =. Point. doi:10.48550/arXiv.2012.09164 , abstract =

    work page doi:10.48550/arxiv.2012.09164 2012

  59. [61]

    Maturana, Daniel and Scherer, Sebastian , month = sep, year =. 2015. doi:10.1109/IROS.2015.7353481 , abstract =

    work page doi:10.1109/iros.2015.7353481 2015

  60. [62]

    Experimental Brain Research , author =

    Flow of activation from. Experimental Brain Research , author =. 2002 , keywords =. doi:10.1007/s00221-001-0906-7 , abstract =

    work page doi:10.1007/s00221-001-0906-7 2002

  61. [64]

    doi:10.48550/arXiv.2410.20981 , abstract =

    Xiang, Xin and Zhou, Wenhui and Dai, Guojun , month = nov, year =. doi:10.48550/arXiv.2410.20981 , abstract =

    work page doi:10.48550/arxiv.2410.20981

  62. [65]

    Biological Cybernetics , author =

    Neocognitron:. Biological Cybernetics , author =. 1980 , pages =. doi:10.1007/BF00344251 , abstract =

    work page doi:10.1007/bf00344251 1980

  63. [66]

    The Journal of Physiology , author =

    Receptive fields, binocular interaction and functional architecture in the cat's visual cortex , volume =. The Journal of Physiology , author =. 1962 , keywords =. doi:10.1113/jphysiol.1962.sp006837 , language =

    work page doi:10.1113/jphysiol.1962.sp006837 1962

  64. [67]

    arXiv.org , author =

  65. [68]

    Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence , volume =

    Cichy, Radoslaw Martin and Khosla, Aditya and Pantazis, Dimitrios and Torralba, Antonio and Oliva, Aude , month = jun, year =. Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence , volume =. Scientific Reports , publisher =. doi:10.1038/srep27755 , abstract =

    work page doi:10.1038/srep27755

  66. [69]

    Hinton, Geoffrey and Sabour, Sara and Frosst, Nicholas , year =

  67. [70]

    IEEE Signal Processing Magazine , author =

    Geometric deep learning: going beyond. IEEE Signal Processing Magazine , author =. 2017 , note =. doi:10.1109/MSP.2017.2693418 , abstract =

    work page doi:10.1109/msp.2017.2693418 2017

  68. [71]

    and Vasco, Miguel and Taleb, Farzaneh and Björkman, Mårten and Kragic, Danica , month = jun, year =

    Rajabi, Nona and Ribeiro, Antônio H. and Vasco, Miguel and Taleb, Farzaneh and Björkman, Mårten and Kragic, Danica , month = jun, year =. Human-. doi:10.48550/arXiv.2502.03081 , abstract =

    work page doi:10.48550/arxiv.2502.03081

  69. [73]

    Proceedings of the National Academy of Sciences of the United States of America , author =

    Performance-optimized hierarchical models predict neural responses in higher visual cortex , volume =. Proceedings of the National Academy of Sciences of the United States of America , author =. 2014 , keywords =. doi:10.1073/pnas.1403112111 , abstract =

    work page doi:10.1073/pnas.1403112111 2014

  70. [74]

    PLoS computational biology , author =

    Deep supervised, but not unsupervised, models may explain. PLoS computational biology , author =. 2014 , keywords =. doi:10.1371/journal.pcbi.1003915 , abstract =

    work page doi:10.1371/journal.pcbi.1003915 2014

  71. [75]

    Güçlü, Umut and Gerven, Marcel A. J. van , month = jul, year =. Deep. Journal of Neuroscience , publisher =. doi:10.1523/JNEUROSCI.5023-14.2015 , abstract =

    work page doi:10.1523/jneurosci.5023-14.2015 2015

  72. [77]

    ResearchGate , month = mar, year =

    Evaluation of. ResearchGate , month = mar, year =. doi:10.2466/03.04.22.PMS.113.4.188-200 , abstract =

    work page doi:10.2466/03.04.22.pms.113.4.188-200

  73. [78]

    The Journal of Physiology , author =

    Changes in pattern-evoked responses in man associated with the vertical and horizontal meridians of the visual field , volume =. The Journal of Physiology , author =. 1970 , pages =. doi:10.1113/jphysiol.1970.sp009134 , abstract =

    work page doi:10.1113/jphysiol.1970.sp009134 1970

  74. [79]

    Event-related brain potentials during selective attention to depth and form in global stereopsis , volume =

    Kasai, Tetsuko and Morotomi, Takashi , year =. Event-related brain potentials during selective attention to depth and form in global stereopsis , volume =. Vision Research , publisher =. doi:10.1016/S0042-6989(01)00067-0 , abstract =

    work page doi:10.1016/s0042-6989(01)00067-0

  75. [80]

    and Rosch, E

    Palmer, S. and Rosch, E. and Chase, P. , year =. Canonical

  76. [81]

    Canonical perspective and the perception of objects. , url =

  77. [82]

    Op de and Torfs, Katrien and Wagemans, Johan , month = oct, year =

    Beeck, Hans P. Op de and Torfs, Katrien and Wagemans, Johan , month = oct, year =. Perceived. Journal of Neuroscience , publisher =. doi:10.1523/JNEUROSCI.2511-08.2008 , abstract =

    work page doi:10.1523/jneurosci.2511-08.2008 2008

  78. [83]

    , year =

    Torralba, Antonio and Isola, Phillip and Freeman, William T. , year =. Foundations of computer vision , isbn =

  79. [84]

    Li, Dongyang and Wei, Chen and Li, Shiying and Zou, Jiachen and Qin, Haoyang and Liu, Quanying , month = oct, year =. Visual. doi:10.48550/arXiv.2403.07721 , abstract =

    work page doi:10.48550/arxiv.2403.07721

  80. [85]

    Trends in Neurosciences , author =

    Separate visual pathways for perception and action , volume =. Trends in Neurosciences , author =. 1992 , keywords =. doi:10.1016/0166-2236(92)90344-8 , abstract =

    work page doi:10.1016/0166-2236(92)90344-8 1992

Showing first 80 references.