作者位次 #4/6ACL 2026Findings· Findings of ACL
AICA -Bench: Holistically Examining the Capabilities of VLM s in Affective Image Content Analysis
Dong She · Xianrong Yao · Liqun Chen · Jinghe Yu · Yang Gao · Zhanpeng Jin
摘要
Vision-Language Models (VLMs) have demonstrated strong capabilities in perception, yet holistic Affective Image Content Analysis (AICA)—which integrates perception, reasoning, and generation into a unified framework—remains underexplored. To address this, we introduce AICA-Bench, a comprehensive...