fMRI (Functional Magnetic Resonance Imaging)
A brain imaging technique that measures neural activity by detecting blood flow changes in different brain regions.
fMRI — functional magnetic resonance imaging — is a neuroimaging technique that measures brain activity by detecting changes in blood oxygenation levels (the BOLD signal). When a brain region is more active, it requires more oxygen, and fMRI detects this change in real time.
In neuroscience research, fMRI is used to map which brain regions are involved in specific cognitive and emotional processes — attention, memory, fear, reward anticipation, and more. 7T fMRI (7 Tesla field strength) provides particularly high-resolution brain imaging used in advanced research.
In the context of video analysis, fMRI data has been used to train AI models that can predict which brain regions will activate when a person watches specific video content — without requiring the viewer to actually be in an MRI scanner.
Meta AI Research used 7T fMRI data to train TRIBE v2, a model that predicts cortical responses to visual stimuli. VidCognition is built on this model, meaning it can predict — for any uploaded video — which brain regions will activate at each second of viewing.
Related Terms
TRIBE v2 (Temporal Response In Brain Encoding)
Meta AI's model that predicts fMRI cortical responses to video stimuli, used as the engine behind VidCognition.
Neural Encoding
The process by which the brain converts sensory input into neural activity patterns.
Visual Cortex
The brain regions (V1–V5) that process visual information from the eyes.
Brain Engagement Score
A composite score predicting the intensity of neural activation across key brain regions during video viewing.