EUVIMEDEUVIMED entdecken
Crossref

Enhancing Neural Encoding of Natural Scenes through Hierarchical Integration of Saliency and Semantic Context

Sizhuo Wang iD, Fan Qin iD, Quan Pan iD, Chang Liu iD, Hongjia Zhu iD, Wenbo Li iD, Hongmei Yan iD, Wei Huang iD

International Journal of Neural Systems · 2027-04 · 37 (04)

DOI: 10.1142/s0129065727500201 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Neural Systems, online erschienen am 29.08.2026. Verfasst von Sizhuo Wang und 7 weiteren Autor:innen. Beteiligte Einrichtung: The Clinical Hospital of Chengdu Brain Science Institute, China-Cuba Belt and Road Joint Laboratory on Neurotechnology and Brain-Apparatus Communicat…. Hauptthemen laut MEDLINE: Semantics, Brain Mapping, Visual Cortex, Models, Neurological. Die Arbeit nennt 57 Literaturangaben. Gefördert von: the National Natural Science Foundation of China, the Fundamental Research Funds for the Central Universities, the Sichuan Science and Technology Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Understanding how the human brain encodes complex natural scenes remains a central problem in computational neuroscience and artificial intelligence. Existing visual encoding models often rely on a single dominant feature representation and may insufficiently characterize how saliency-guided spatial information and high-level semantic context jointly contribute to cortical response prediction. To address this issue, this study proposes a saliency-guided multimodal visual encoding model, termed SMG-MVEM, to predict voxel-wise cortical responses to natural scene stimuli. The model integrates image features, saliency cues, and text-derived semantic representations through a hierarchical fusion architecture, followed by a Transformer-based brain mapper. Experiments on the Natural Scenes Dataset (NSD) show that SMG-MVEM improves prediction performance over representative neural encoding baselines and internal control variants, with the average PCC increasing from [Formula: see text] for the best-performing baseline to [Formula: see text]. Regional analyses further show that saliency contributed more strongly to early visual areas, whereas semantic features provided greater benefits in higher-order regions. Representational analyses also suggest that the model-predicted responses preserved aspects of hierarchical and category-related organization across the visual cortex. These findings indicate that structured integration of saliency and semantic context can improve cortical response prediction and provide interpretable representational patterns for natural vision.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SemanticsBrain MappingVisual CortexModels, NeurologicalPattern Recognition, VisualHumansMagnetic Resonance ImagingAdultMale

Stichwörter der Autor:innen

Visual neural encodingfunctional magnetic resonance imaging (fMRI)multimodal learningsaliency-guided modeling

Autor:innen und Institutionen

  • The Clinical Hospital of Chengdu Brain Science Institute, China-Cuba Belt and Road Joint Laboratory on Neurotechnology and Brain-Apparatus Communication, Brain-Computer Interface and Brain-Inspired Intelligence Key Labo…
  • BGI Research, Beijing 102206, China.

ORCID-Profile: Sizhuo Wang, Fan Qin, Quan Pan, Chang Liu, Hongjia Zhu, Wenbo Li, Hongmei Yan, Wei Huang

Förderung

  • the National Natural Science Foundation of China
  • the Fundamental Research Funds for the Central Universities
  • the Sichuan Science and Technology Program
  • the Science and Technology Department of Sichuan Province

Zitieren

APA

Wang, S., Qin, F., Pan, Q., Liu, C., Zhu, H., Li, W., Yan, H., & Huang, W. (2027). Enhancing Neural Encoding of Natural Scenes through Hierarchical Integration of Saliency and Semantic Context. International Journal of Neural Systems, 37(04). https://doi.org/10.1142/s0129065727500201

Vancouver

Wang S, Qin F, Pan Q, Liu C, Zhu H, Li W, et al. Enhancing Neural Encoding of Natural Scenes through Hierarchical Integration of Saliency and Semantic Context. International Journal of Neural Systems. 2027;37(04). doi:10.1142/s0129065727500201

BibTeX
@article{Wang2027,
  author = {Wang, Sizhuo and Qin, Fan and Pan, Quan and Liu, Chang and Zhu, Hongjia and Li, Wenbo and Yan, Hongmei and Huang, Wei},
  title = {Enhancing Neural Encoding of Natural Scenes through Hierarchical Integration of Saliency and Semantic Context},
  journal = {International Journal of Neural Systems},
  year = {2027},
  volume = {37},
  number = {04},
  doi = {10.1142/s0129065727500201}
}
Kostenlos starten →