NeuroAlign: Dynamic Dual-Stream Alignment of Perception and Cognition for Zero-Shot Brain-Image Retrieval
Open Access
- 15 June 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 108-117
Abstract
No abstract availableFunding Information
- Strategic Priority Research Program of the Chinese Academy of Sciences (XDB0930000)
- Guangdong Provincial Key Laboratory of Multimodality Non-Invasive Brain-Computer Interfaces (2024B1212010010)
This publication has 43 references indexed in Scilit:
- Self-supervised cross-modal visual retrieval from brain activitiesPattern Recognition, 2023
- DM-RE2I: A framework based on diffusion model for the reconstruction from EEG to imageBiomedical Signal Processing and Control, 2023
- A large and rich EEG dataset for modeling human visual object recognitionNeuroImage, 2022
- SLIP: Self-supervision Meets Language-Image Pre-training2022
- Self-supervised Natural Image Reconstruction and Large-scale Semantic Classification from Brain ActivityNeuroImage, 2022
- The representational dynamics of visual objects in rapid serial visual processing streamsNeuroImage, 2019
- The anterior temporal cortex is a primary semantic source of top-down influences on object recognitionCortex, 2016
- Untangling invariant object recognitionTrends in Cognitive Sciences, 2007
- A possible mechanism of zero-crossing detection using the concept of the extended classical receptive field of retinal ganglion cellsBiological Cybernetics, 2005
- A saliency-based search mechanism for overt and covert shifts of visual attentionVision Research, 2000