pith. sign in

arxiv: 2605.16418 · v1 · pith:M6QSIAYXnew · submitted 2026-05-14 · 💻 cs.CV · cs.AI

Neural Visual Decoding via Cognitive guided Adaptive Blurring and Information Constrained Alignment

Fan Yin , Chuhang Zheng , Peiliang Gong , Donghai Guan , Qi Zhu This is my paper

Pith reviewed 2026-05-20 21:35 UTC · model grok-4.3

classification 💻 cs.CV cs.AI
keywords EEG visual decodingbrain-to-image retrievaladaptive blurringinformation bottleneckneural oscillationszero-shot retrievalcross-modal attentionsaliency guidance
0
0 comments X

The pith

Cognitive-guided adaptive blurring aligns EEG signals with images by reducing visual redundancy to match neural granularity.

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

EEG visual decoding faces a mismatch where detailed images clash with coarse and noisy brain signals. The paper introduces the CAIA framework to simulate human selective attention by blurring visuals adaptively based on center bias and saliency cues integrated through cross-modal attention. On the brain side it screens EEG oscillations using known neural frequency patterns and an information bottleneck to raise signal quality. This produces stronger alignment and higher Top-1 and Top-5 accuracy in zero-shot brain-to-image retrieval for both familiar and new subjects. The central idea is that deliberately lowering visual information density to fit neural limits yields more robust decoding than treating features as static.

Core claim

CAIA improves both subject-dependent and subject-independent average Top-1 and Top-5 accuracy in zero-shot brain-to-image retrieval, significantly outperforming prior methods, by using a cognitive-dynamics-based adaptive blurring mechanism that integrates center-biased and saliency-guided visual cues via cross-modal attention on the visual side and neural oscillation priors with an information bottleneck on the EEG side, together with a distribution-aware boundary calibration loss to correct alignment bias from outliers.

What carries the argument

The cognitive-dynamics-based adaptive blurring mechanism that dynamically integrates center-biased and saliency-guided visual cues via cross-modal attention, paired with cognitively-guided information-screening of EEG oscillations and an information bottleneck.

Load-bearing premise

Dynamically integrating center-biased and saliency-guided visual cues via cross-modal attention combined with neural oscillation priors and information bottleneck effectively reduces redundancy and enhances SNR to match neural granularity.

What would settle it

A controlled test on standard EEG-image datasets in which the adaptive blurring and oscillation-screening steps are removed and Top-1 accuracy shows no gain or drops below baseline levels.

Figures

Figures reproduced from arXiv: 2605.16418 by Chuhang Zheng, Donghai Guan, Fan Yin, Peiliang Gong, Qi Zhu.

Figure 1
Figure 1. Figure 1: Bidirectional modulation of visual and EEG information densities to bridge the modality gap. (a) Visual [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: CAIA model framework: (a) dual-path adaptive blurring mechanism. (b) information-bottleneck-guided [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: EEG-image similarity distribution. We regard samples whose similarity lies near the distri￾bution mean as “inliers,” while those deviating signifi￾cantly—often due to attention drift or high-noise trials—are treated as “outliers.” Such outliers typically reflect substan￾tial cross-modal information mismatch. Optimizing with a uniform contrastive loss risks overfitting to these aberrant samples and may harm… view at source ↗
Figure 4
Figure 4. Figure 4: Visualization of the cognitive-dynamics-based [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Visualization of EEG signals before and after information-guided frequency band screening in the time [PITH_FULL_IMAGE:figures/full_fig_p009_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: EEG-image similarity distribution before and after calibration using the distribution-aware loss. [PITH_FULL_IMAGE:figures/full_fig_p009_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Successful retrieval examples. 17 [PITH_FULL_IMAGE:figures/full_fig_p017_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Failed retrieval examples. (a) UMAP visualization of EEG latent vari￾ables. (b) Joint UMAP visualization of multi￾modal latent variables. (c) UMAP visualization of image latent variables [PITH_FULL_IMAGE:figures/full_fig_p018_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: UMAP dimensionality reduction visualization. (b) green represents correct matches, red represents incorrect [PITH_FULL_IMAGE:figures/full_fig_p018_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Frequency band selection weights in subject [PITH_FULL_IMAGE:figures/full_fig_p019_10.png] view at source ↗
Figure 12
Figure 12. Figure 12: Visualization of EEG signals before and after information-guided frequency band screening under [PITH_FULL_IMAGE:figures/full_fig_p019_12.png] view at source ↗
read the original abstract

EEG-based visual decoding aims to establish a mapping between neural signals and visual semantics. However, it remains constrained by the dual challenges of severe information granularity mismatch and the low signal-to-noise ratio (SNR) of EEG signals. Existing approaches typically treat static visual features, ignoring the dynamic selectivity of human vision and the frequency specificity of neural oscillations. To bridge this gap, we propose CAIA, a Cognitive-guided Adaptive blurring with Information-Constrained Alignment framework for Neural-Visual decoding. On the visual side, it simulates selective attention to adaptively reduce redundancy. Meanwhile, on the EEG side, it leverages neural oscillation priors and the information bottleneck mechanism to enhance SNR. Specifically, we devise a cognitive-dynamics-based adaptive blurring mechanism that dynamically integrates center-biased and saliency-guided visual cues via cross-modal attention. Furthermore, we introduce a distribution-aware boundary calibration loss to robustly rectify alignment bias caused by outlier samples. Moreover, a cognitively-guided information-screening method is proposed to select task-relevant EEG oscillations. Extensive experiments demonstrate that CAIA improves both subject-dependent and subject-independent average Top-1 and Top-5 accuracy in zero-shot brain-to-image retrieval, significantly outperforming prior methods. Our work validates that optimizing visual information density to match neural granularity offers a more interpretable and robust pathway for neural 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

0 major / 3 minor

Summary. The manuscript introduces CAIA, a Cognitive-guided Adaptive blurring with Information-Constrained Alignment framework for EEG-based neural visual decoding. It addresses information granularity mismatch and low SNR by using a cognitive-dynamics-based adaptive blurring mechanism that integrates center-biased and saliency-guided visual cues via cross-modal attention on the visual side, combined with neural oscillation priors and an information bottleneck on the EEG side. A distribution-aware boundary calibration loss is introduced to handle alignment bias from outliers, and a cognitively-guided information-screening method selects task-relevant EEG oscillations. The central claim, supported by experiments on standard datasets, is that CAIA yields significant gains in both subject-dependent and subject-independent zero-shot brain-to-image retrieval, with improved average Top-1 and Top-5 accuracy over prior methods.

Significance. If the reported performance improvements hold, the work provides a cognitively motivated and interpretable approach to aligning visual and neural signals by dynamically matching information density to neural granularity. The dual focus on adaptive visual redundancy reduction and EEG frequency-specific screening, evaluated under both within-subject and cross-subject zero-shot protocols, could advance robust brain-to-image retrieval and related BCI applications. The inclusion of implementation details and baseline comparisons is a positive aspect for reproducibility.

minor comments (3)
  1. [Abstract] Abstract: the claim of 'significantly outperforming prior methods' would be more informative if accompanied by the specific average Top-1/Top-5 accuracy deltas or effect sizes achieved on the primary datasets.
  2. [Method] Method section: the description of the cross-modal attention integration for adaptive blurring would benefit from an explicit equation or pseudocode for the dynamic cue weighting to improve clarity and reproducibility.
  3. [Experiments] Experiments: while standard datasets and protocols are referenced, adding a table of per-subject or per-run standard deviations alongside the reported averages would strengthen the presentation of the subject-independent results.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive assessment of our CAIA framework and the recommendation for minor revision. The recognition of our cognitively motivated approach to matching visual information density with neural granularity, along with the dual mechanisms for adaptive blurring and EEG oscillation screening, is appreciated. We will incorporate minor revisions to further strengthen the manuscript.

Circularity Check

0 steps flagged

Derivation chain is self-contained with no circular reductions

full rationale

The paper describes CAIA as a framework combining cognitive-dynamics-based adaptive blurring via cross-modal attention, distribution-aware boundary calibration loss, and cognitively-guided information-screening for EEG oscillations. The central performance claims rest on experimental results from within- and across-subject protocols on standard datasets, with direct comparisons to prior baselines. No load-bearing step reduces by construction to a fitted parameter renamed as prediction, a self-citation chain, or an ansatz smuggled via prior work; the methods are presented as independently implemented components whose effectiveness is evaluated empirically against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract provides no explicit free parameters, axioms, or invented entities; analysis is limited to high-level description of mechanisms.

pith-pipeline@v0.9.0 · 5772 in / 1069 out tokens · 92196 ms · 2026-05-20T21:35:10.897767+00:00 · methodology

discussion (0)

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

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

56 extracted references · 56 canonical work pages

  1. [1]

    Progress, challenges and future of linguistic neural decoding with deep learning.Communications Biology, 8(1):1350, 2025

    Yu Wang, Heyang Liu, Yuhao Wang, Chuan Xuan, Yixuan Hou, Sheng Feng, Hongcheng Liu, Yusheng Liao, and Yanfeng Wang. Progress, challenges and future of linguistic neural decoding with deep learning.Communications Biology, 8(1):1350, 2025

    work page 2025

  2. [2]

    Wang, Paul G

    Eric Y . Wang, Paul G. Fahey, Zhuokun Ding, Stelios Papadopoulos, Kayla Ponder, Marissa A. Weis, Andersen Chang, Taliah Muhammad, Saumil Patel, Zhiwei Ding, Dat Tran, Jiakun Fu, Casey M. Schneider-Mizell, Nuno Maçarico da Costa, R. Clay Reid, Forrest Collman, Katrin Franke, Alexander S. Ecker, Jacob Reimer, Xaq Pitkow, Fabian H. Sinz, Andreas S. Tolias, a...

    work page 2025

  3. [3]

    Intracranial brain-computer interface spelling using localized visual motion response.NeuroImage, 258:119363, 2022

    Dingkun Liu, Xin Xu, Dongyang Li, Jie Li, Xinguang Yu, Zhipei Ling, and Bo Hong. Intracranial brain-computer interface spelling using localized visual motion response.NeuroImage, 258:119363, 2022

    work page 2022

  4. [4]

    Criaud, M

    M. Criaud, M. Wulff, A.A. Alegria, G.J. Barker, V . Giampietro, and K. Rubia. Increased left inferior fronto-striatal activation during error monitoring after fmri neurofeedback of right inferior frontal cortex in adolescents with attention deficit hyperactivity disorder.NeuroImage: Clinical, 27:102311, 2020

    work page 2020

  5. [5]

    Spatially selective activation of the visual cortex via intraneural stimulation of the optic nerve.Nature Biomedical Engineering, 4(2):181–194, February 2020

    Vivien Gaillet, Annarita Cutrone, Fiorenzo Artoni, Paola Vagni, Ariastity Mega Pratiwi, Sandra Alejandra Romero, Dario Lipucci Di Paola, Silvestro Micera, and Diego Ghezzi. Spatially selective activation of the visual cortex via intraneural stimulation of the optic nerve.Nature Biomedical Engineering, 4(2):181–194, February 2020

    work page 2020

  6. [6]

    Changde Du, Kaicheng Fu, Jinpeng Li, and Huiguang He. Decoding visual neural representations by multimodal learning of brain-visual-linguistic features.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(9):10760–10777, 2023

    work page 2023

  7. [7]

    Tao, and Zhitao Zhou

    Erda Zhou, Xiner Wang, Jizhi Liang, Yang Liu, Qinrong Yang, Xingchen Ran, Lei Xia, Xiang Zou, Changjiang Liu, Liuyang Sun, Lei Peng, Liang Chen, Ying Mao, Zehan Wu, Tiger H. Tao, and Zhitao Zhou. Chronically stable, high-resolution micro-electrocorticographic brain-computer interfaces for real-time motor decoding.Advanced Science, 12(45):e06663, December 2025

    work page 2025

  8. [8]

    High-resolution image reconstruction with latent diffusion models from human brain activity

    Yu Takagi and Shinji Nishimoto. High-resolution image reconstruction with latent diffusion models from human brain activity. In2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 14453–14463, 2023

    work page 2023

  9. [9]

    Brain decoding: toward real-time reconstruction of visual perception

    Yohann Benchetrit, Hubert Banville, and Jean-Remi King. Brain decoding: toward real-time reconstruction of visual perception. In B. Kim, Y . Yue, S. Chaudhuri, K. Fragkiadaki, M. Khan, and Y . Sun, editors,International Conference on Learning Representations, volume 2024, pages 7846–7858, 2024

    work page 2024

  10. [10]

    Contrast, attend and diffuse to decode high-resolution images from brain activities

    Jingyuan Sun, Mingxiao Li, Zijiao Chen, Yunhao Zhang, Shaonan Wang, and Marie-Francine Moens. Contrast, attend and diffuse to decode high-resolution images from brain activities. In A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine, editors,Advances in Neural Information Processing Systems, volume 36, pages 12332–12348. Curran Associates...

    work page 2023

  11. [11]

    A magnetoencephalography dataset for motor and cognitive imagery-based brain-computer interface.Scientific Data, 8(1):120, April 2021

    Dheeraj Rathee, Haider Raza, Sujit Roy, and Girijesh Prasad. A magnetoencephalography dataset for motor and cognitive imagery-based brain-computer interface.Scientific Data, 8(1):120, April 2021

    work page 2021

  12. [12]

    Eeg-based strategies to detect motor imagery for control and rehabilitation

    Kai Keng Ang and Cuntai Guan. Eeg-based strategies to detect motor imagery for control and rehabilitation. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25(4):392–401, 2017

    work page 2017

  13. [13]

    Fanelli, and Massimo Filippi

    Anna Bellini, Davide Gusmeo Curti, Marco Cursi, Giordano Cecchetti, Federica Agosta, Giovanna F. Fanelli, and Massimo Filippi. Predictors of seizure detection and EEG clinical impact in an italian tertiary emergency department.Journal of Neurology, 271(8):5137–5145, August 2024

    work page 2024

  14. [14]

    Robinson, Martin N

    Tijl Grootswagers, Ivy Zhou, Amanda K. Robinson, Martin N. Hebart, and Thomas A. Carlson. Human eeg recordings for 1,854 concepts presented in rapid serial visual presentation streams.Scientific Data, 9(1):3, January 2022

    work page 2022

  15. [15]

    Brainvis: Exploring the bridge between brain and visual signals via image reconstruction

    Honghao Fu, Hao Wang, Jing Jih Chin, and Zhiqi Shen. Brainvis: Exploring the bridge between brain and visual signals via image reconstruction. InICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5, 2025

    work page 2025

  16. [16]

    Decoding natural images from eeg for object recognition, 2024

    Yonghao Song, Bingchuan Liu, Xiang Li, Nanlin Shi, Yijun Wang, and Xiaorong Gao. Decoding natural images from eeg for object recognition, 2024

    work page 2024

  17. [17]

    Visual decoding and reconstruction via eeg embeddings with guided diffusion

    Dongyang Li, Chen Wei, Shiying Li, Jiachen Zou, and Quanying Liu. Visual decoding and reconstruction via eeg embeddings with guided diffusion. In A. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, and C. Zhang, editors,Advances in Neural Information Processing Systems, volume 37, pages 102822–102864. Curran Associates, Inc., 2024. 10

    work page 2024

  18. [18]

    Unveiling deep semantic uncertainty perception for language-anchored multi-modal vision-brain alignment, 2025

    Zehui Feng, Chenqi Zhang, Mingru Wang, Minuo Wei, Shiwei Cheng, Cuntai Guan, and Ting Han. Unveiling deep semantic uncertainty perception for language-anchored multi-modal vision-brain alignment, 2025

    work page 2025

  19. [19]

    Bridging the vision-brain gap with an uncertainty-aware blur prior

    Haitao Wu, Qing Li, Changqing Zhang, Zhen He, and Xiaomin Ying. Bridging the vision-brain gap with an uncertainty-aware blur prior. In2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 2246–2257, 2025

    work page 2025

  20. [20]

    C. A. Curcio, K. R. Sloan, R. E. Kalina, and A. E. Hendrickson. Human photoreceptor topography.The Journal of Comparative Neurology, 292(4):497–523, February 1990

    work page 1990

  21. [21]

    Stimulus center bias persists irrespective of its position on the display

    Rotem Mairon and Ohad Ben-Shahar. Stimulus center bias persists irrespective of its position on the display. Journal of Eye Movement Research, 18(6):77, December 2025

    work page 2025

  22. [22]

    Computational modelling of visual attention.Nature Reviews Neuroscience, 2(3):194–203, March 2001

    Laurent Itti and Christof Koch. Computational modelling of visual attention.Nature Reviews Neuroscience, 2(3):194–203, March 2001

    work page 2001

  23. [23]

    Revisited visual saliency detection with deep learning: A review of recent advancements.ACM Comput

    Sandeep Chand Kumain, Maheep Singh, and Lalit Kumar Awasthi. Revisited visual saliency detection with deep learning: A review of recent advancements.ACM Comput. Surv., 58(6), December 2025

    work page 2025

  24. [24]

    Human gaze holding and its disorders.Annals of Otology and Neurotology, 02:33–40, 03 2019

    Aasef Shaikh. Human gaze holding and its disorders.Annals of Otology and Neurotology, 02:33–40, 03 2019

    work page 2019

  25. [25]

    Interpretable cross-modal alignment network for eeg visual decoding with algorithm unrolling.IEEE Transactions on Neural Networks and Learning Systems, 36(11):19894–19908, 2025

    Daowen Xiong, Liangliang Hu, Jiahao Jin, Yikang Ding, Congming Tan, Jing Zhang, and Yin Tian. Interpretable cross-modal alignment network for eeg visual decoding with algorithm unrolling.IEEE Transactions on Neural Networks and Learning Systems, 36(11):19894–19908, 2025

    work page 2025

  26. [26]

    Roberts, and Avgis Hadjipapas

    Eric Lowet, Peter De Weerd, Mark J. Roberts, and Avgis Hadjipapas. Tuning neural synchronization: The role of variable oscillation frequencies in neural circuits.Frontiers in Systems Neuroscience, V olume 16 - 2022, 2022

    work page 2022

  27. [27]

    The information bottleneck method.Proceedings of the 37th Allerton Conference on Communication, Control and Computation, 49, 07 2001

    Naftali Tishby, Fernando Pereira, and William Bialek. The information bottleneck method.Proceedings of the 37th Allerton Conference on Communication, Control and Computation, 49, 07 2001

    work page 2001

  28. [28]

    Deep cnn model based on serial-parallel structure optimization for four-class motor imagery eeg classification.Biomedical Signal Processing and Control, 72:103338, 2022

    Xuefei Zhao, Dong Liu, Li Ma, Quan Liu, Kun Chen, Shane Xie, and Qingsong Ai. Deep cnn model based on serial-parallel structure optimization for four-class motor imagery eeg classification.Biomedical Signal Processing and Control, 72:103338, 2022

    work page 2022

  29. [29]

    Brain emotion perception inspired eeg emotion recognition with deep reinforcement learning.IEEE Transactions on Neural Networks and Learning Systems, 35(9):12979–12992, 2024

    Dongdong Li, Li Xie, Zhe Wang, and Hai Yang. Brain emotion perception inspired eeg emotion recognition with deep reinforcement learning.IEEE Transactions on Neural Networks and Learning Systems, 35(9):12979–12992, 2024

    work page 2024

  30. [30]

    Vicchietti, Fernando M

    Mário L. Vicchietti, Fernando M. Ramos, Luiz E. Betting, and Andriana S. L. O. Campanharo. Computational methods of EEG signals analysis for Alzheimer’s disease classification.Scientific Reports, 13(1):8184, 2023

    work page 2023

  31. [31]

    Alleviating the semantic gap for generalized fmri-to-image reconstruction

    Tao Fang, Qian Zheng, and Gang Pan. Alleviating the semantic gap for generalized fmri-to-image reconstruction. InProceedings of the 37th International Conference on Neural Information Processing Systems, NIPS ’23, Red Hook, NY , USA, 2023. Curran Associates Inc

    work page 2023

  32. [32]

    Minddiffuser: Controlled image reconstruction from human brain activity with semantic and structural diffusion

    Yizhuo Lu, Changde Du, Qiongyi Zhou, Dianpeng Wang, and Huiguang He. Minddiffuser: Controlled image reconstruction from human brain activity with semantic and structural diffusion. InProceedings of the 31st ACM International Conference on Multimedia, MM ’23, page 5899–5908, New York, NY , USA, 2023. Association for Computing Machinery

    work page 2023

  33. [33]

    Self- supervised natural image reconstruction and large-scale semantic classification from brain activity.NeuroImage, 254:119121, 2022

    Guy Gaziv, Roman Beliy, Niv Granot, Assaf Hoogi, Francesca Strappini, Tal Golan, and Michal Irani. Self- supervised natural image reconstruction and large-scale semantic classification from brain activity.NeuroImage, 254:119121, 2022

    work page 2022

  34. [34]

    From voxels to pixels and back: Self-supervision in natural-image reconstruction from fmri

    Roman Beliy, Guy Gaziv, Assaf Hoogi, Francesca Strappini, Tal Golan, and Michal Irani. From voxels to pixels and back: Self-supervision in natural-image reconstruction from fmri. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett, editors,Advances in Neural Information Processing Systems, volume 32. Curran Associates, Inc., 2019

    work page 2019

  35. [35]

    Deep learning applications in fmri – a review work

    Jiangxue Li and Peize Zhao. Deep learning applications in fmri – a review work. InProceedings of the 2023 13th International Conference on Bioscience, Biochemistry and Bioinformatics, ICBBB ’23, page 75–80, New York, NY , USA, 2023. Association for Computing Machinery

    work page 2023

  36. [36]

    On the interpretation of weight vectors of linear models in multivariate neuroimaging.NeuroImage, 87:96–110, 2014

    Stefan Haufe, Frank Meinecke, Kai Görgen, Sven Dähne, John-Dylan Haynes, Benjamin Blankertz, and Felix Bießmann. On the interpretation of weight vectors of linear models in multivariate neuroimaging.NeuroImage, 87:96–110, 2014

    work page 2014

  37. [37]

    Lawhern, Amelia J

    Vernon J. Lawhern, Amelia J. Solon, Nicholas R. Waytowich, Stephen M. Gordon, Chou P. Hung, and Brent J. Lance. EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces.Journal of Neural Engineering, 15(5):056013, 2018. 11

    work page 2018

  38. [38]

    Eeg conformer: Convolutional transformer for eeg decoding and visualization.IEEE Transactions on Neural Systems and Rehabilitation Engineering, 31:710–719, 2023

    Yonghao Song, Qingqing Zheng, Bingchuan Liu, and Xiaorong Gao. Eeg conformer: Convolutional transformer for eeg decoding and visualization.IEEE Transactions on Neural Systems and Rehabilitation Engineering, 31:710–719, 2023

    work page 2023

  39. [39]

    Dreamdiffusion: Generating high-quality images from brain eeg signals, 2023

    Yunpeng Bai, Xintao Wang, Yan pei Cao, Yixiao Ge, Chun Yuan, and Ying Shan. Dreamdiffusion: Generating high-quality images from brain eeg signals, 2023

    work page 2023

  40. [40]

    Brainflora: Uncovering brain concept representation via multimodal neural embeddings, 2025

    Dongyang Li, Haoyang Qin, Mingyang Wu, Chen Wei, and Quanying Liu. Brainflora: Uncovering brain concept representation via multimodal neural embeddings, 2025

    work page 2025

  41. [41]

    Cognitioncapturer: Decoding visual stimuli from human eeg signal with multimodal information, 2024

    Kaifan Zhang, Lihuo He, Xin Jiang, Wen Lu, Di Wang, and Xinbo Gao. Cognitioncapturer: Decoding visual stimuli from human eeg signal with multimodal information, 2024

    work page 2024

  42. [42]

    A simple framework for contrastive learning of visual representations, 02 2020

    Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. A simple framework for contrastive learning of visual representations, 02 2020

    work page 2020

  43. [43]

    SimCSE: Simple contrastive learning of sentence embeddings

    Tianyu Gao, Xingcheng Yao, and Danqi Chen. SimCSE: Simple contrastive learning of sentence embeddings. In Marie-Francine Moens, Xuanjing Huang, Lucia Specia, and Scott Wen-tau Yih, editors,Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6894–6910, Online and Punta Cana, Dominican Republic, November 2021. Assoc...

    work page 2021

  44. [44]

    Learning transferable visual models from natural language supervision, 02 2021

    Alec Radford, Jong Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. Learning transferable visual models from natural language supervision, 02 2021

    work page 2021

  45. [45]

    Visual neural decoding via improved visual-eeg semantic consistency.ArXiv, 2024

    Hongzhou Chen, Lianghua He, Yihang Liu, and Longzhen Yang. Visual neural decoding via improved visual-eeg semantic consistency.ArXiv, 2024

    work page 2024

  46. [46]

    Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, and Xiaoli Li. Self- supervised learning for label- efficient sleep stage classification: A comprehensive evaluation.IEEE Transactions on Neural Systems and Rehabilitation Engineering, 31:1333–1342, 2023

    work page 2023

  47. [47]

    Robust contrastive learning against noisy views

    Ching-Yao Chuang, R Devon Hjelm, Xin Wang, Vibhav Vineet, Neel Joshi, Antonio Torralba, Stefanie Jegelka, and Yale Song. Robust contrastive learning against noisy views. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 16670–16681, June 2022

    work page 2022

  48. [48]

    Evidential deep learning to quantify classification uncertainty

    Murat Sensoy, Lance Kaplan, and Melih Kandemir. Evidential deep learning to quantify classification uncertainty. In S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett, editors,Advances in Neural Information Processing Systems, volume 31. Curran Associates, Inc., 2018

    work page 2018

  49. [49]

    Things-data, a multimodal collection of large-scale datasets for investigating object representations in human brain and behavior.eLife, 12:e82580, feb 2023

    Martin N Hebart, Oliver Contier, Lina Teichmann, Adam H Rockter, Charles Y Zheng, Alexis Kidder, Anna Corriveau, Maryam Vaziri-Pashkam, and Chris I Baker. Things-data, a multimodal collection of large-scale datasets for investigating object representations in human brain and behavior.eLife, 12:e82580, feb 2023

    work page 2023

  50. [50]

    Mb2c: Multimodal bidirectional cycle consistency for learning robust visual neural representations

    Yayun Wei, Lei Cao, Hao Li, and Yilin Dong. Mb2c: Multimodal bidirectional cycle consistency for learning robust visual neural representations. InProceedings of the 32nd ACM International Conference on Multimedia, MM ’24, page 8992–9000, New York, NY , USA, 2024. Association for Computing Machinery

    work page 2024

  51. [51]

    Neural-mcrl: Neural multimodal contrastive representation learning for eeg-based visual decoding

    Yueyang Li, Zijian Kang, Shengyu Gong, Wenhao Dong, Weiming Zeng, Hongjie Yan, Wai Ting Siok, and Nizhuan Wang. Neural-mcrl: Neural multimodal contrastive representation learning for eeg-based visual decoding. In2025 IEEE International Conference on Multimedia and Expo (ICME), pages 1–6, 2025

    work page 2025

  52. [52]

    Beta-band oscillations—signalling the status quo?Current Opinion in Neurobiology, 20(2):156–165, 2010

    Andreas K Engel and Pascal Fries. Beta-band oscillations—signalling the status quo?Current Opinion in Neurobiology, 20(2):156–165, 2010. Cognitive neuroscience

    work page 2010

  53. [53]

    Visual areas exert feedforward and feedback influences through distinct frequency channels.Neuron, 85(2):390–401, 2015

    André Moraes Bastos, Julien Vezoli, Conrado Arturo Bosman, Jan-Mathijs Schoffelen, Robert Oostenveld, Jarrod Robert Dowdall, Peter De Weerd, Henry Kennedy, and Pascal Fries. Visual areas exert feedforward and feedback influences through distinct frequency channels.Neuron, 85(2):390–401, 2015

    work page 2015

  54. [54]

    Xuan-Hao Liu, Yan-Kai Liu, Tianyi Zhou, Bao-Liang Lu, and Wei-Long Zheng. Mindcross: Fast new subject adaptation with limited data for cross-subject video reconstruction from brain signals.Proceedings of the AAAI Conference on Artificial Intelligence, 40(21):17589–17597, Mar. 2026

    work page 2026

  55. [55]

    Infinimind: A learning-optimized large-scale brain-computer interface

    Yeongwoo Jang, Daye Jung, Seunghyun Song, Hunjun Lee, and Jangwoo Kim. Infinimind: A learning-optimized large-scale brain-computer interface. InProceedings of the 52nd Annual International Symposium on Computer Architecture, ISCA ’25, page 1969–1985, New York, NY , USA, 2025. Association for Computing Machinery

    work page 1969

  56. [56]

    beyond-image

    Yuta Sasatake and Kojiro Matsushita. P300 erp system utilizing wireless visual stimulus presentation devices. Sensors (Basel, Switzerland), 25(12):10, 2025. 12 6 A. Supplementary Material 6.1 Details of the Datasets Things-EEG[ 14] is a large-scale neuroimaging resource designed to facilitate zero-shot visual object recognition from neural signals. The da...

    work page 2025