AI看动作时总盯着物体，不看时间
AI识别「打开抽屉」这类动作时，常常作弊：它只看物体（抽屉）就猜动词（打开），根本没看动作过程。研究者发现，这是因为训练数据里动词和物体总成对出现，模型学会了偷懒。他们设计了两招：一是把没见过的组合当反面教材，逼模型别依赖物体；二是让模型必须按时间顺序理解动作。结果模型不再靠物体猜动词，真正学会了看动作。这不是你明天能用的技术，但它揭示了AI视觉的一个盲区——我们以为它在看过程，其实它在猜标签。
📄 原文摘要(英文)
Zero-Shot Compositional Action Recognition (ZS-CAR) requires recognizing novel verb-object combinations composed of previously observed primitives. In this work, we tackle a key failure mode: models predict verbs via object-driven shortcuts (i.e., relying on the labeled object class) rather than temporal evidence. We argue that sparse compositional supervision and verb-object learning asymmetry can promote object-driven shortcut learning. Our analysis with proposed diagnostic metrics shows that existing methods overfit to training co-occurrence patterns and underuse temporal verb cues, resulting in weak generalization to unseen compositions. To address object-driven shortcuts, we propose Robust COmpositional REpresentations (RCORE) with two components. Co-occurrence Prior Regularization (CPR) adds explicit supervision for unseen compositions and regularizes the model against frequent co-occurrence priors by treating them as hard negatives. Temporal Order Regularization for Composition (TORC) enforces temporal-order sensitivity to learn temporally grounded verb representations. Across Sth-com and EK100-com, RCORE reduces shortcut diagnostics and consequently improves compositional generalization.