<p>(A) Human identification accuracy scores for the vision and mental imagery trials of th

Human identification accuracy scores for the vision and mental imagery trials of the NSD-Imagery benchmark. The dataset, authored by Reese Kneeland, is a 5.5 KB Excel file last updated on May 22, 2026. Scores are provided for each method and stimulus type, with best values bolded and second best underlined.

Use Cases

• Benchmarking computational models of vision against human performance based on the provided accuracy scores.
• Comparing the efficacy of different methods for stimulus identification based on the scores by method and stimulus type.
• Analyzing the gap between human visual perception and mental imagery performance based on the trial results.

Strengths

• Provides human benchmark scores with statistical significance (all p < 0.001).
• Includes a clear chance-level baseline for comparison (chance = 50%).
• Distinguishes between best and second-best performing methods through formatting (bolded and underlined values).

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small (5.5 KB), indicating limited scope.

Provenance

Source

figshare, authored by Reese Kneeland.

Collection Method

Likely contains experimental results from the NSD-Imagery benchmark.

Time Range

null

Freshness

Last updated 2026-05-22 17:43:54; freshness should be verified.

Geography

null