Decoding Natural Images from EEG for Object Recognition
Not on the map. Why?
Abstract (arXiv)
Electroencephalography (EEG) signals, known for convenient non-invasive acquisition but low signal-to-noise ratio, have recently gained substantial attention due to the potential to decode natural images. This paper presents a self-supervised framework to demonstrate the feasibility of learning image representations from EEG signals, particularly for object recognition. The framework utilizes image and EEG encoders to extract features from paired image stimuli and EEG responses. Contrastive learning aligns these two modalities by constraining their similarity. With the framework, we attain significantly above-chance results on a comprehensive EEG-image dataset, achieving a top-1 accuracy of 15.6% and a top-5 accuracy of 42.8% in challenging 200-way zero-shot tasks. Moreover, we perform extensive experiments to explore the biological plausibility by resolving the temporal, spatial, spectral, and semantic aspects of EEG signals. Besides, we introduce attention modules to capture spatial correlations, providing implicit evidence of the brain activity perceived from EEG data. These findings yield valuable insights for neural decoding and brain-computer interfaces in real-world scenarios. The code will be released on https://github.com/eeyhsong/NICE-EEG.
Key facts. Cited by 81 papers in the map (data through 14 Oct 2026). Builds on 26 of its 66 references that are in the map. First posted on arXiv 25 Aug 2023.
Builds on
26 of 66 references.
References · 26
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2017Graph Attention Networkscited by 8,923
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
- 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
- 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,070
- 2021How Attentive are Graph Attention Networks?cited by 835
- 2023EVA-CLIP: Improved Training Techniques for CLIP at Scalecited by 798
- 2016EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfacescited by 628
14 more
- 2022OmniVL:One Foundation Model for Image-Language and Video-Language Taskscited by 143
- 2015Generic decoding of seen and imagined objects using hierarchical visual featurescited by 120
- 2022Learnable latent embeddings for joint behavioral and neural analysiscited by 117
- 2022Mind Reader: Reconstructing complex images from brain activitiescited by 85
- 2016Deep Learning Human Mind for Automated Visual Classificationcited by 77
- 2022Decoding Visual Neural Representations by Multimodal Learning of Brain-Visual-Linguistic Featurescited by 63
- 2022SPD domain-specific batch normalization to crack interpretable unsupervised domain adaptation in EEGcited by 53
- 2018Decoding Brain Representations by Multimodal Learning of Neural Activity and Visual Featurescited by 52
- 2022MAtt: A Manifold Attention Network for EEG Decodingcited by 44
- 2021LGGNet: Learning from Local-Global-Graph Representations for Brain-Computer Interfacecited by 36
- 2021Reconstructing Perceptive Images from Brain Activity by Shape-Semantic GANcited by 32
- 2021NeuroGen: activation optimized image synthesis for discovery neurosciencecited by 22
- 2020Object classification from randomized EEG trialscited by 19
- 2022Multi-view Multi-label Fine-grained Emotion Decoding from Human Brain Activitycited by 3
Built on by
Citing papers per year: 2023: 1; 2024: 12; 2025: 25; 2026: 43.
81 papers.
Sort:
By area:
- 2024Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusioncited by 81
- 2025Bridging the Vision-Brain Gap with an Uncertainty-Aware Blur Priorcited by 29
- 2024CognitionCapturer: Decoding Visual Stimuli From Human EEG Signal With Multimodal Informationcited by 28
- 2024Neuro-3D: Towards 3D Visual Decoding from EEG Signalscited by 23
- 2024Visual Neural Decoding via Improved Visual-EEG Semantic Consistencycited by 21
- 2024Self-supervised Learning for Electroencephalogram: A Systematic Surveycited by 19
- 2024Neural-MCRL: Neural Multimodal Contrastive Representation Learning for EEG-based Visual Decodingcited by 14
- 2025NeuroBridge: Bio-Inspired Self-Supervised EEG-to-Image Decoding via Cognitive Priors and Bidirectional Semantic Alignmentcited by 14
- 2024Mind's Eye: Image Recognition by EEG via Multimodal Similarity-Keeping Contrastive Learningcited by 12
- 2025CineBrain: A Large-Scale Multi-Modal Brain Dataset During Naturalistic Audiovisual Narrative Processingcited by 11
- 2025Towards Robust Multimodal Physiological Foundation Models: Handling Arbitrary Missing Modalitiescited by 11
- 2024NECOMIMI: Neural-Cognitive Multimodal EEG-informed Image Generation with Diffusion Modelscited by 10
38 more
- 2025Human-Aligned Image Models Improve Visual Decoding from the Braincited by 7
- 2026Let EEG Models Learn EEGcited by 7
- 2024Dual-TSST: A Dual-Branch Temporal-Spectral-Spatial Transformer Model for EEG Decodingcited by 6
- 2025WaveMind: Towards a Conversational EEG Foundation Model Aligned to Textual and Visual Modalitiescited by 6
- 2025ViEEG: Hierarchical Visual Neural Representation for EEG Brain Decodingcited by 5
- 2026Aligning What EEG Can See: Structural Representations for Brain-Vision Matchingcited by 5
- 2026HyFI: Hyperbolic Feature Interpolation for Brain-Vision Alignmentcited by 5
- 2024Achieving More Human Brain-Like Vision via Human EEG Representational Alignmentcited by 4
- 2025Unlocking In-Context Learning for Natural Datasets Beyond Language Modellingcited by 4
- 2025EEG2TEXT-CN: An Exploratory Study of Open-Vocabulary Chinese Text-EEG Alignment via Large Language Model and Contrastive Learning on ChineseEEGcited by 4
- 2025Foundation Models for Cross-Domain EEG Analysis Application: A Surveycited by 4
- 2026Deep Models, Shallow Alignment: Uncovering the Granularity Mismatch in Neural Decodingcited by 4
- 2026Subject-Aware Multi-Granularity Alignment for Zero-Shot EEG-to-Image Retrievalcited by 4
- 2024AI for Biomedicine in the Era of Large Language Modelscited by 3
- 2025A Survey on Bridging EEG Signals and Generative AI: From Image and Text to Beyondcited by 3
- 2025Category-aware EEG image generation based on wavelet transform and contrast semantic losscited by 3
- 2025Transformer-based EEG Decoding: A Surveycited by 3
- 2025Spatial-Functional awareness Transformer-based graph archetype contrastive learning for Decoding Visual Neural Representations from EEGcited by 3
- 2026Learning Brain Representation with Hierarchical Visual Embeddingscited by 3
- 2026ZUNA: Flexible EEG Superresolution with Position-Aware Diffusion Autoencoderscited by 3
- 2026Autoregressive Visual Decoding from EEG Signalscited by 3
- 2026SATTC: Structure-Aware Label-Free Test-Time Calibration for Cross-Subject EEG-to-Image Retrievalcited by 3
- 2026What Are We Actually Decoding? Source Attribution for Non-Invasive Brain-to-Language Retrievalcited by 3
- 2025EgoBrain: Synergizing Minds and Eyes For Human Action Understandingcited by 2
- 2025From Pixels to Feelings: Aligning MLLMs with Human Cognitive Perception of Imagescited by 2
- 2026CognitionCapturerPro: Towards High-Fidelity Visual Decoding from EEG/MEG via Multi-modal Information and Asymmetric Alignmentcited by 2
- 2023SI-SD: Sleep Interpreter through awake-guided cross-subject Semantic Decodingcited by 1
- 2024Adaptive Modality Balanced Online Knowledge Distillation for Brain-Eye-Computer based Dim Object Detectioncited by 1
- 2025Bridging Brain with Foundation Models through Self-Supervised Learningcited by 1
- 20253D-Telepathy: Reconstructing 3D Objects from EEG Signalscited by 1
- 2025Image-to-Brain Signal Generation for Visual Prosthesis with CLIP Guided Multimodal Diffusion Modelscited by 1
- 2025DynaMind: Reconstructing Dynamic Visual Scenes from EEG by Aligning Temporal Dynamics and Multimodal Semantics to Guided Diffusioncited by 1
- 2025Decoding Visual Neural Representations by Multimodal with Dynamic Balancingcited by 1
- 2025Decoding Dynamic Visual Experience from Calcium Imaging via Cell-Pattern-Aware Pretrainingcited by 1
- 2025Unveiling Deep Semantic Uncertainty Perception for Language-Anchored Multi-modal Vision-Brain Alignmentcited by 1
- 2026ENIGMA: EEG-to-Image in 15 Minutes Using Less Than 1% of the Parameterscited by 1
- 2026Hierarchic-EEG2Text: Assessing EEG-To-Text Decoding across Hierarchical Abstraction Levelscited by 1
- 2026EEG2Vision: A Multimodal EEG-Based Framework for 2D Visual Reconstruction in Cognitive Neurosciencecited by 1
50 most cited of 81 All 81 (JSON)
- 2026Brain2Face: A Study on the Relation of EEG Signals and Spatio-temporal Head Avatars12 Oct 2026
- 2026Structured Visual Target Learning For Cross-Subject eeg-to-image retrieval29 Sep 2026
- 2026The Visual Target Matters: Learning across the Visual Hierarchy for Brain-to-Image Retrieval21 Sep 2026
- 2026Adaptive Cortically Constrained EEG-Vision Alignment for Zero-Shot Brain-to-Image Retrieval21 Sep 2026
- 2026RPA: Residual Patch-Token Adapter for Image Retrieval from EEG and MEG19 Sep 2026
- 2026Brain-to-Image Generation: Reconstructing Visual Stimuli from EEG using Generative Adversarial Networks13 Sep 2026
- 2026EEG-VID: Task-Guided Latent Predictive Pretraining for EEG Decoding and Assistive Target Selection1 Sep 2026
- 2026SCORE: Subject Coordinate Recovery for Label-Free Cross-Subject EEG-to-Image Retrieval19 Aug 2026
- 2026Beyond Trial Averaging: Anchoring Neural and Visual Representations for Few-Repetition Brain-to-Image Retrieval19 Aug 2026
- 2026NeuroPB: Scaling Neural Decoding with Pretrained Behavioral Representations5 Aug 2026
- 2026EEG-EditBench: Probing Visual Information in EEG-Image Retrieval Models with Controlled Image Edits30 Jul 2026
- 2026Visual Semantic Decoding of Electrocorticography from Video Stimuli using End-to-End Deep Learning21 Jul 2026
38 more
- 2026FSDBN: Foreground-Aware EEG-Visual Alignment via Dynamic Brain Networks20 Jul 2026
- 2026MindAU: EEG-Conditioned Facial Action Unit Editing via Dual-Stream Manifold Alignment1 Jul 2026
- 2026BrainJanus: A Unified Model for Understanding and Generation across Brain, Vision, and Language29 Jun 2026
- 2026What Does the Brain See? Multiview Neural Representations to Demystify the Brain-Visual Alignment24 Jun 2026
- 2026SUP-MCRL: Subject-aware Unified Pseudo-feature Coded Multimodal Contrastive Representation Learning for EEG Visual Decoding15 Jun 2026
- 2026Channel-Preserving Representation Alignment for EEG-to-Music Reconstruction2 Jun 2026
- 2026Mind-Omni: A Unified Multi-Task Framework for Brain-Vision-Language Modeling via Discrete Diffusion28 May 2026
- 2026What Are We Actually Decoding? Source Attribution for Non-Invasive Brain-to-Language Retrieval23 May 2026
- 2026MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding23 May 2026
- 2026STAMBRIDGE: Spectral-Temporal Amplitude-aware Mid-Feature Bridge for EEG Visual Decoding22 May 2026
- 2026Let EEG Models Learn EEG20 May 2026
- 2026Neuroscience-inspired Staged Representation Learning with Disentangled Coarse- and Fine-Grained Semantics for EEG Visual Decoding16 May 2026
- 2026Multi-Level Bidirectional Biomimetic Learning for EEG-Based Visual Decoding6 May 2026
- 2026SIMON: Saliency-aware Integrative Multi-view Object-centric Neural Decoding1 May 2026
- 2026ViBE: Visual-to-M/EEG Brain Encoding via Spatio-Temporal VAE and Distribution-Aligned Projection29 Apr 2026
- 2026Brain-Inspired Capture: Evidence-Driven Neuromimetic Perceptual Simulation for Visual Decoding20 Apr 2026
- 2026Subject-Aware Multi-Granularity Alignment for Zero-Shot EEG-to-Image Retrieval20 Apr 2026
- 2026EEG2Vision: A Multimodal EEG-Based Framework for 2D Visual Reconstruction in Cognitive Neuroscience9 Apr 2026
- 2026HyFI: Hyperbolic Feature Interpolation for Brain-Vision Alignment24 Mar 2026
- 2026SATTC: Structure-Aware Label-Free Test-Time Calibration for Cross-Subject EEG-to-Image Retrieval21 Mar 2026
- 2026Toward High-Fidelity Visual Reconstruction: From EEG-Based Conditioned Generation to Joint-Modal Guided Rebuilding20 Mar 2026
- 2026CognitionCapturerPro: Towards High-Fidelity Visual Decoding from EEG/MEG via Multi-modal Information and Asymmetric Alignment13 Mar 2026
- 2026Aligning What EEG Can See: Structural Representations for Brain-Vision Matching7 Mar 2026
- 2026Autoregressive Visual Decoding from EEG Signals26 Feb 2026
- 2026Hierarchic-EEG2Text: Assessing EEG-To-Text Decoding across Hierarchical Abstraction Levels24 Feb 2026
- 2026MindPilot: Closed-loop Visual Stimulation Optimization for Brain Modulation with EEG-guided Diffusion11 Feb 2026
- 2026ENIGMA: EEG-to-Image in 15 Minutes Using Less Than 1% of the Parameters10 Feb 2026
- 2026ZUNA: Flexible EEG Superresolution with Position-Aware Diffusion Autoencoders9 Feb 2026
- 2026Learning Brain Representation with Hierarchical Visual Embeddings7 Feb 2026
- 2026Deep Models, Shallow Alignment: Uncovering the Granularity Mismatch in Neural Decoding29 Jan 2026
- 2026Contrastive and Multi-Task Learning on Noisy Brain Signals with Nonlinear Dynamical Signatures13 Jan 2026
- 2025TF-MCL: Time-frequency Fusion and Multi-domain Cross-Loss for Self-supervised Depression Detection14 Dec 2025
- 2025From Pixels to Feelings: Aligning MLLMs with Human Cognitive Perception of Images27 Nov 2025
- 2025NeuroBridge: Bio-Inspired Self-Supervised EEG-to-Image Decoding via Cognitive Priors and Bidirectional Semantic Alignment10 Nov 2025
- 2025Unveiling Deep Semantic Uncertainty Perception for Language-Anchored Multi-modal Vision-Brain Alignment6 Nov 2025
- 2025Decoding Dynamic Visual Experience from Calcium Imaging via Cell-Pattern-Aware Pretraining21 Oct 2025
- 2025Spatial-Functional awareness Transformer-based graph archetype contrastive learning for Decoding Visual Neural Representations from EEG29 Sep 2025
- 2025WaveMind: Towards a Conversational EEG Foundation Model Aligned to Textual and Visual Modalities26 Sep 2025
50 newest of 81 All 81 (JSON)
- 2024Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusioncited by 81
- 2024NECOMIMI: Neural-Cognitive Multimodal EEG-informed Image Generation with Diffusion Modelscited by 10
- 2025A Survey on Bridging EEG Signals and Generative AI: From Image and Text to Beyondcited by 3
- 2026ZUNA: Flexible EEG Superresolution with Position-Aware Diffusion Autoencoderscited by 3
- 2025Image-to-Brain Signal Generation for Visual Prosthesis with CLIP Guided Multimodal Diffusion Modelscited by 1
- 2025DynaMind: Reconstructing Dynamic Visual Scenes from EEG by Aligning Temporal Dynamics and Multimodal Semantics to Guided Diffusioncited by 1
- 2026MindPilot: Closed-loop Visual Stimulation Optimization for Brain Modulation with EEG-guided Diffusioncited by 0
- 2026MindPilot: Closed-loop Visual Stimulation Optimization for Brain Modulation with EEG-guided Diffusion11 Feb 2026
- 2026ZUNA: Flexible EEG Superresolution with Position-Aware Diffusion Autoencoders9 Feb 2026
- 2025DynaMind: Reconstructing Dynamic Visual Scenes from EEG by Aligning Temporal Dynamics and Multimodal Semantics to Guided Diffusion1 Sep 2025
- 2025Image-to-Brain Signal Generation for Visual Prosthesis with CLIP Guided Multimodal Diffusion Models31 Aug 2025
- 2025A Survey on Bridging EEG Signals and Generative AI: From Image and Text to Beyond17 Feb 2025
- 2024NECOMIMI: Neural-Cognitive Multimodal EEG-informed Image Generation with Diffusion Models1 Oct 2024
- 2024Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion12 Mar 2024
- 2025WaveMind: Towards a Conversational EEG Foundation Model Aligned to Textual and Visual Modalitiescited by 6
- 2025From Pixels to Feelings: Aligning MLLMs with Human Cognitive Perception of Imagescited by 2
- 2026Mind-Omni: A Unified Multi-Task Framework for Brain-Vision-Language Modeling via Discrete Diffusioncited by 0
- 2026Mind-Omni: A Unified Multi-Task Framework for Brain-Vision-Language Modeling via Discrete Diffusion28 May 2026
- 2025From Pixels to Feelings: Aligning MLLMs with Human Cognitive Perception of Images27 Nov 2025
- 2025WaveMind: Towards a Conversational EEG Foundation Model Aligned to Textual and Visual Modalities26 Sep 2025
- 2025Bridging the Vision-Brain Gap with an Uncertainty-Aware Blur Priorcited by 29
- 2024CognitionCapturer: Decoding Visual Stimuli From Human EEG Signal With Multimodal Informationcited by 28
- 2024Neuro-3D: Towards 3D Visual Decoding from EEG Signalscited by 23
- 2024Visual Neural Decoding via Improved Visual-EEG Semantic Consistencycited by 21
- 2024Self-supervised Learning for Electroencephalogram: A Systematic Surveycited by 19
- 2024Neural-MCRL: Neural Multimodal Contrastive Representation Learning for EEG-based Visual Decodingcited by 14
- 2025NeuroBridge: Bio-Inspired Self-Supervised EEG-to-Image Decoding via Cognitive Priors and Bidirectional Semantic Alignmentcited by 14
- 2024Mind's Eye: Image Recognition by EEG via Multimodal Similarity-Keeping Contrastive Learningcited by 12
- 2025CineBrain: A Large-Scale Multi-Modal Brain Dataset During Naturalistic Audiovisual Narrative Processingcited by 11
- 2025Towards Robust Multimodal Physiological Foundation Models: Handling Arbitrary Missing Modalitiescited by 11
- 2025Human-Aligned Image Models Improve Visual Decoding from the Braincited by 7
- 2026Let EEG Models Learn EEGcited by 7
12 most cited of 71 All 71 (JSON)
- 2026Brain2Face: A Study on the Relation of EEG Signals and Spatio-temporal Head Avatars12 Oct 2026
- 2026Structured Visual Target Learning For Cross-Subject eeg-to-image retrieval29 Sep 2026
- 2026The Visual Target Matters: Learning across the Visual Hierarchy for Brain-to-Image Retrieval21 Sep 2026
- 2026Adaptive Cortically Constrained EEG-Vision Alignment for Zero-Shot Brain-to-Image Retrieval21 Sep 2026
- 2026RPA: Residual Patch-Token Adapter for Image Retrieval from EEG and MEG19 Sep 2026
- 2026Brain-to-Image Generation: Reconstructing Visual Stimuli from EEG using Generative Adversarial Networks13 Sep 2026
- 2026EEG-VID: Task-Guided Latent Predictive Pretraining for EEG Decoding and Assistive Target Selection1 Sep 2026
- 2026SCORE: Subject Coordinate Recovery for Label-Free Cross-Subject EEG-to-Image Retrieval19 Aug 2026
- 2026Beyond Trial Averaging: Anchoring Neural and Visual Representations for Few-Repetition Brain-to-Image Retrieval19 Aug 2026
- 2026NeuroPB: Scaling Neural Decoding with Pretrained Behavioral Representations5 Aug 2026
- 2026EEG-EditBench: Probing Visual Information in EEG-Image Retrieval Models with Controlled Image Edits30 Jul 2026
- 2026Visual Semantic Decoding of Electrocorticography from Video Stimuli using End-to-End Deep Learning21 Jul 2026
12 newest of 71 All 71 (JSON)