AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Knowledge-Enhanced Image Captioning with Adaptive Graph-based Multimodal Alignment and LLM

Guoyi Li, Die Hu, Haozhe Li, Zhongjiang Yao, Wei Mi, Zongzhen Liu, Xiaodan Zhang, Honglei Lyu

AAAI 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Concept-guided image captioning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add knowledge graph prompts (ablation)AKGMA · UniKnowCap TestRecogAcc: 48.0% -> 77.1%Improved
add adaptive RL-based subgraph construction (AKGC) instead of random walk (ablation)AKGMA · UniKnowCap TestRecogAcc: 57.4% -> 77.1%Improved
use AKGC instead of static 1-hop/2-hop neighbor expansion (ablation)AKGMA · UniKnowCap TestCHAIR-S: 8.3/8.9 -> 7.3Improved
add VKPairs training of EKA (ablation)AKGMA · UniKnowCap TestRecogAcc: 72.8% -> 77.1%Improved
add SCKA and AKGC on top of EKA (ablation)AKGMA · UniKnowCap TestRecogAcc: 54.8% -> 77.1%Improved
add scene-context knowledge adapter (SCKA) (ablation)AKGMA · MSCOCO TestCIDEr: 145.1 -> 149.3Improved
add knowledge graph prompts (ablation)AKGMA · MSCOCO TestCIDEr: 138.2 -> 149.3Improved
increase context vector length LD from 4 to 8 (ablation)AKGMA · MSCOCO TestCIDEr: 149.3 -> 148.5Hurt
decrease context vector length LD from 4 to 2 (ablation)AKGMA · MSCOCO TestCIDEr: 149.3 -> 144.7Hurt
add VKPairs training (ablation)AKGMA · MSCOCO TestCIDEr: 143.7 -> 149.3Improved
AKGMA vs best baseline on knowledge recognition (KnowCap)AKGMA · KnowCap TestCIDEr: 93.4 vs OFAK-Replay 99.6Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy