图像意义随上下文变化，该研究提出分级框架提升语义检索效果
Same Image, Different Meanings: Toward Retrieval of Context-Dependent Meanings
- 构建从具体到抽象的四级语义框架（L1-L4），区分图像中稳定与可变的语义成分
- 抽象语义依赖叙事上下文，尤其在图像端注入背景信息时检索效果显著提升
- 最抽象层级仍难精准检索，揭示上下文依赖图像理解是待解难题
同一幅雨中两人场景，在重逢故事中传递希望与温暖，在告别故事中则暗示悲伤与终结。本文探究图像意义的上下文依赖性及其对检索的影响。核心发现：语义抽象程度决定上下文敏感性——具体元素（物体、动作）跨情境保持稳定，而抽象元素（氛围、意图）随上下文变化。为此提出L1-L4语义分级框架，从不依赖上下文（L1）到高度依赖（L4）。通过合成故事上下文与查询进行受控评估，发现具体查询无需上下文即可检索，而抽象层级检索效果随叙事嵌入显著提升；尤其在图像端注入上下文时表现更优。然而，最抽象层级即使完全注入上下文仍难以准确检索，凸显上下文依赖图像检索仍是重要开放问题。本研究为构建能处理叙事语境中图像意义变化的检索系统奠定基础。
原文摘要 · Abstract (English)
A scene of two people in the rain can convey hope and warmth in a reunion story or sorrow and finality in a farewell story. We investigate this context-dependent nature of image meaning and its implications for retrieval. Our key observation is that context dependency correlates with semantic abstraction: concrete elements (objects, actions) remain stable across contexts, while abstract elements (atmosphere, intent) shift with context. We operationalize this as the L1--L4 framework, organizing image semantics from context-independent (L1) to maximally context-dependent (L4). Using synthetic story contexts and queries for controlled evaluation, we examine how injecting narrative context into embeddings affects retrieval across abstraction levels. Concrete queries are retrievable without context, while abstract levels increasingly depend on narrative grounding. Where context is injected also matters, with image-side enrichment proving particularly effective. The most abstract level, however, remains challenging even with full context, highlighting context-dependent image retrieval as an important open problem. Our framework and findings lay groundwork toward retrieval systems that handle the context-dependent meanings images acquire in narrative settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。