5 papers · 1 filter
EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding
Geo Ahn, Jiwook Han, Youngrae Kim +2
Fine-tuning MLLMs for Video Temporal Grounding (VTG) often improves in-domain performance but degrades sharply under domain shift. In this work, we find that this failure is primar…
BizGenEval: A Systematic Benchmark for Commercial Visual Content Generation
Yan Li, Zezi Zeng, Ziwei Zhou +13
Recent advances in image generation models have expanded their applications beyond aesthetic imagery toward practical visual content creation. However, existing benchmarks mainly f…
Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition
Geo Ahn, Inwoong Lee, Taeoh Kim +3
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 fa…
PCEvE: Part Contribution Evaluation Based Model Explanation for Human Figure Drawing Assessment and Beyond
Jongseo Lee, Geo Ahn, Seong Tae Kim +1
For automatic human figure drawing (HFD) assessment tasks, such as diagnosing autism spectrum disorder (ASD) using HFD images, the clarity and explainability of a model decision ar…
DEVIAS: Learning Disentangled Video Representations of Action and Scene
Kyungho Bae, Geo Ahn, Youngrae Kim +1
Video recognition models often learn scene-biased action representation due to the spurious correlation between actions and scenes in the training data. Such models show poor perfo…