Aligning Video Models with Human Social Judgments via Behavior-Guided Fine-Tuning

Abstract: Humans intuitively perceive complex social signals in visual scenes, yet it remains unclear whether state-of-the-art AI models encode the same similarity structure. We study (Q1) whether modern video and LLMs capture human-perceived similarity in social videos, and (Q2) how to instill this structure into models using human behavioral data. To address this, we introduce a new benchmark of over 49,000 odd-one-out similarity judgments on 250 three-second video clips of social interactions, and discover a modality gap: despite the task being visual, caption-based language embeddings align better with human similarity than any pretrained video model. We close this gap by fine-tuning a TimeSformer video model on these human judgments with our novel hybrid triplet-RSA objective using low-rank adaptation (LoRA), aligning pairwise distances to human similarity. This fine-tuning protocol yields significantly improved alignment with human perceptions on held-out videos in terms of both explained variance and odd-one-out triplet accuracy. Variance partitioning shows that the fine-tuned video model increases shared variance with language embeddings and explains additional unique variance not captured by the LLM. Finally, we test transfer via linear probes and find that human-similarity fine-tuning strengthens the encoding of social-affective attributes (intimacy, valence, dominance, communication) relative to the pretrained baseline. Overall, our findings highlight a gap in pretrained video models' social recognition and demonstrate that behavior-guided fine-tuning shapes video representations toward human social perception.