Abstract:Metaphorical imagination, the ability to connect seemingly unrelated concepts, is fundamental to human cognition and communication. While understanding linguistic metaphors has advanced significantly, grasping multimodal metaphors, such as those found in internet memes, presents unique challenges due to their unconventional expressions and implied meanings. Existing methods for multimodal metaphor identification often struggle to bridge the gap between literal and figurative interpretations. Additionally, generative approaches that utilize large language models or text-to-image models, while promising, suffer from high computational costs. This paper introduces \textbf{C}oncept \textbf{D}rift \textbf{G}uided \textbf{L}ayerNorm \textbf{T}uning (\textbf{CDGLT}), a novel and training-efficient framework for multimodal metaphor identification. CDGLT incorporates two key innovations: (1) Concept Drift, a mechanism that leverages Spherical Linear Interpolation (SLERP) of cross-modal embeddings from a CLIP encoder to generate a new, divergent concept embedding. This drifted concept helps to alleviate the gap between literal features and the figurative task. (2) A prompt construction strategy, that adapts the method of feature extraction and fusion using pre-trained language models for the multimodal metaphor identification task. CDGLT achieves state-of-the-art performance on the MET-Meme benchmark while significantly reducing training costs compared to existing generative methods. Ablation studies demonstrate the effectiveness of both Concept Drift and our adapted LN Tuning approach. Our method represents a significant step towards efficient and accurate multimodal metaphor understanding. The code is available: \href{this https URL}{this https URL}.
| Comments: | ICMR'25, June 30-July 3, 2025, Chicago, IL, USA |
| Subjects: | Multimedia (cs.MM); Machine Learning (cs.LG) |
| Cite as: | arXiv:2505.11237 [cs.MM] |
| (or arXiv:2505.11237v4 [cs.MM] for this version) | |
| https://doi.org/10.48550/arXiv.2505.11237 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.1145/3731715.3733296
DOI(s) linking to related resources |
From: Wenhao Qian [view email]
[v1]
Fri, 16 May 2025 13:27:57 UTC (4,561 KB)
[v2]
Tue, 10 Mar 2026 13:05:59 UTC (713 KB)
[v3]
Mon, 13 Apr 2026 06:22:59 UTC (713 KB)
[v4]
Fri, 17 Apr 2026 08:29:44 UTC (713 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。