AI Paper Atlas

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

Meric: A Unified Framework for Multimodal Music Generation and Retrieval via Representation Space Anchoring

Xihua Wang, Yinbo Wang, Jingchao Zhang, Ruihua Song

ECCV 2026 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval · 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
replace CLIP ViT-H-14 with Qwen3VL-Embedding as vision encoder (ablation)Music Head · MelBenchFADmert: 2.54 -> 1.95Improved
replace CLIP ViT-H-14 with Qwen3VL-Embedding as vision encoder (ablation)Music Head · ARIAFADmert: 4.73 -> 3.98Improved
use diffusion Music Head instead of linear MSE projector (ablation)Meric projector · MelBenchFADmert: 4.37 -> 1.96Improved
use diffusion Music Head instead of contrastive linear projector (ablation)Meric projector · MelBenchFADmert: 12.94 -> 1.96Improved
use diffusion Music Head instead of contrastive linear projector (ablation)Meric projector · MelBenchR@1 / R@10: 1.70 / 9.02 -> 1.52 / 9.30Hurt
use diffusion Music Head instead of CrossVAE projector (ablation)Meric projector · ARIAFADmert: 7.22 -> 4.32Improved
use diffusion Music Head instead of BridgeVAE projector (ablation)Meric projector · MelBenchFADmert: 4.06 -> 1.96Improved
use more than 1 DDIM step in Music Head sampling (ablation)Music Head · Human listening study (100 images)MOS: s=1 significantly worse (p<0.001); s>=5 indistinguishable (p>0.2)Improved
increase Music Head DDIM steps from 5 to 20 (ablation)Music Head · Human listening study (100 images)MOS: p>0.2No clear effect
average predictions over N=10 seeds (ensemble) (ablation)Music Head retrieval · natural-audio datasets (AudioSet-Music, MuImage, MelBench, EmoMV)R@10: +4–10%Improved
average predictions over N=10 seeds (ensemble) (ablation)Music Head retrieval · ARIAR@10No clear effect
replace Meric with ImageBind for image-music retrievalretrieval baseline · MelBenchR@10 (I->M): 18.00 vs 8.62Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 2 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