Unverified50% confidenceFactExact time
In the PixCC dataset, humans showed a strategy shift: from holistic semantic association to describing low-level visual attributes (such as color and texture), whereas MLLMs tended to adhere to semantic-level association.
1
Sources
50%
Confidence
Long-term
Relevance
10/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedExperiments reveal that the model's early layers are dominated by perceptual primitives, primarily processing low-level visual features such as color, shape, and texture.71% similarUnverifiedThe study uses two datasets: SilCC (which modulates naming difficulty through progressively complex abstract shape compositions) and PixCC (which increases recognition difficulty by adding random visual noise) to compare the associative creativity of humans and multimodal large models.67% similarUnverified人类视觉系统对空间比例、色彩和谐和排版结构的感知远超对文本逻辑细微差异的辨别能力67% similarUnverifiedThe more specific the prompt is written (subject of the scene, environment, camera movement, lighting atmosphere, emotional tone), the more likely the model is to generate footage that matches the brand's tone.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1079456API
curl https://kongchang.com/api/v1/knowledge/claims/1079456MCP
get_claim(id=1079456)