automated metrics 1benchmark 1instruction following 1spatio-temporal reasoning 1video generation evaluation 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CV2026
VGIF-Score: Interpretable and Diagnostic Evaluation of Spatio-Temporal Instruction Following in Video Generation
Songyu Xu, Xin Wang, Qiang Chen +6
The paper introduces VGIF-Score, an automated and interpretable framework that evaluates how well video generation models follow long, compositional instructions by parsing prompts…
cs.CV2026
DetailVerifyBench: A Benchmark for Dense Hallucination Localization in Long Image Captions
Xinran Wang, Yuxuan Zhang, Xiao Zhang +7
Accurately detecting and localizing hallucinations is a critical task for ensuring high reliability of image captions. In the era of Multimodal Large Language Models (MLLMs), capti…