| title | Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition |
|---|---|
| authors | Geo Ahn, Inwoong Lee, Taeoh Kim, Minho Shim, Dongyoon Wee, Jinwoo Choi |
| date | 2026-07-02 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2601.16211 |
| affiliation | NAVER |
| upvotes | 47 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | 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. |
cite
@misc{ahn2026why,
title={Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition},
author={Geo Ahn and Inwoong Lee and Taeoh Kim and Minho Shim and Dongyoon Wee and Jinwoo Choi},
year={2026},
eprint={2601.16211},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2601.16211}
}