KAIST Develops AI That Reads Animal Behavior Like Language (IMAGE)
Caption
Discovery of a “compositional semantic structure” in animal behavior. When the model’s learned internal representation space was visualized using principal component analysis (PCA), different behaviors were geometrically organized along interpretable axes such as “mobility,” “vertical attention,” and “social engagement.” The relationships between behaviors were expressed as consistent vector transformations, much like the semantic relationships found in word embeddings. Notably, the same compositional structure emerged even when the model was trained only through self-supervised learning, using masked keypoint modeling without any behavior labels. This suggests that animal movement itself contains a language-like semantic structure.
Credit
KAIST
Usage Restrictions
No
License
Licensed content