AI Paper Atlas

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

Image2song: Song Retrieval via Bridging Image Content and Lyric Words

Xuelong Li, Di Hu, Xiaoqiang Lu

ICCV 2017 · Vision-language and multimodal › Human and embodied modeling · approach: Composed and text-based image retrieval · 10 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 tag attention to lyric modeling (ablation)Our baseline · Shuttersong image2song (dataset-S, obj-attr tags)R@10: 4.94 -> 5.63Improved
add tag attention to lyric modeling (ablation)Our baseline · Shuttersong image2song (dataset-dagger, obj-attr tags)R@5: 7.6 -> 9.4Improved
add tag attention to lyric modeling (ablation)Our baseline · Shuttersong image2song (dataset-dagger, obj-attr tags)Med r: 43.30 -> 41.50Improved
use final LSTM output with tag attention instead of attentive poolingAttentive-Reader · Shuttersong image2song (dataset-dagger, obj-attr tags)R@10: 15.0 -> 16.8Improved
use bi-directional LSTM lyric encoder instead of BoWBoW · Shuttersong image2song (dataset-dagger, obj-attr tags)R@1: 1.4 -> 2.2Improved
use both object and attribute tags instead of attribute tags only (ablation)Our-attention · Shuttersong image2song (dataset-dagger, obj-attr tags)R@1: 2.2 -> 2.6Improved
average pooling instead of max pooling for tag attention (ablation)Our-attention · Image2song pooling ablation (obj-attr tags)R@1: 12.08 -> 13.10Improved
use MSE loss instead of marginal ranking loss (ablation)Our-attention · Image2song loss ablation (obj-attr tags)R@1: 9.90 -> 13.10Improved
use MSE loss instead of cosine proximity loss (ablation)Our-attention · Image2song loss ablation (obj-attr tags)R@1: 11.29 -> 13.10Improved
add mood tag to lyric representation (ablation)Our · Image2song (obj-attr tags, supplementary)R@1: 10.95 -> 12.13Improved
train with image-content supervision of lyric modeling instead of lyric poolingSchwarz et al. · Song2image (lyric query, dataset-dagger)R@1: 0.10 -> 0.19Improved

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