2 papers
q-bio.NC2026
Behavioral Geometric Supervision Aligns Video Foundation Models with Human Social Perception
Kathy Garcia, Leyla Isik
Current video foundation models, including the strongest self-supervised models such as V-JEPA2, fail to capture how humans organize social information in dynamic scenes. For examp…
cs.CV2026
Simple 3D Pose Features Support Human and Machine Social Scene Understanding
Wenshuo Qin, Leyla Isik
Humans effortlessly recognize social interactions from visual input, yet the underlying computations remain unknown, and social interaction recognition challenges even the most adv…