AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Enhancing Meme Emotion Understanding with Multi-Level Modality Enhancement and Dual-Stage Modal Fusion

Yi Shi, Wenlong Meng, Zhenyuan Guo, Chengkun Wei, Wenzhi Chen

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal sentiment analysis · 1 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
replace dual-stage fusion with simple concatenation (ablation)MemoDetector · MET-MEMEMacro-F1 (%): 43.57 -> 45.33Improved
add Text Meaning enhancement step (ablation)MemoDetector · MOODMacro-F1 (%): 80.54 -> 82.65Improved
add Image Description step (ablation)MemoDetector · MET-MEMEMacro-F1 (%): 44.29 -> 45.33Improved
add Combined Implicit Meaning step (ablation)MemoDetector · MET-MEMEMacro-F1 (%): 44.32 -> 45.33Improved
add Context Analysis step (ablation)MemoDetector · MOODMacro-F1 (%): 80.75 -> 82.65Improved
use four-step enhancement instead of direct single-step enhancement (ablation)MemoDetector · MET-MEME and MOODAccuracy, Precision, Recall, F1Improved
use bidirectional cross-attention in second fusion stage instead of add, concat or cross-attention (ablation)MemoDetector · MET-MEME and MOODAccuracy, Macro-F1Improved
add chain-of-thought prompting to MLLM direct classificationQwen2.5-VL-7B · MET-MEMEMacro-F1 (%): 32.30 -> 36.59Improved
add chain-of-thought prompting to MLLM direct classificationQwen2.5-VL-32B · MET-MEMEMacro-F1 (%): 35.30 -> 32.74Hurt
use 32B MLLM rather than 7B for text enhancement (ablation)MemoDetector · MET-MEMEMacro-F1 (%): 41.22 -> 45.33Improved
supervised fine-tune Qwen2.5-VL-7BQwen2.5-VL-7B · MET-MEMEMacro-F1 (%): 32.30 -> 41.03Improved
use MLLM-enhanced text with small model instead of MLLM zero-shotQwen2.5-VL-7B · MOODMacro-F1 (%): 48.04 -> 81.72Improved

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