AI Paper Atlas

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

Synergistic Prompting for Robust Visual Recognition with Missing Modalities

Zhihui Zhang, Luanyuan Dai, Qika Lin, Yunfeng Diao, Guangyin Jin, Yufei Guo, Jing Zhang, Xiaoshuai Hao

ICCV 2025 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 6 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 synergistic prompts (dynamic plus static) to frozen-encoder classifier (ablation)SyP · Hateful Memes 50% both missingAUROC: 57.35 -> 68.16Improved
add synergistic prompts (dynamic plus static) to frozen-encoder classifier (ablation)SyP · Food101 50% both missingaccuracy: 71.59 -> 86.17Improved
add synergistic prompts (dynamic plus static) to frozen-encoder classifier (ablation)SyP · MM-IMDb 50% both missingF1-Macro: 44.63 -> 54.72Improved
add static prompt to dynamic prompt (ablation)SyP · Food101 50% both missingaccuracy: 82.90 -> 86.17Improved
add dynamic prompt to static prompt (ablation)SyP · Hateful Memes 50% both missingAUROC: 65.62 -> 68.16Improved
add dynamic adapter to base prompt (ablation)SyP · Hateful Memes 50% both missingAUROC: 64.27 -> 66.37Improved
add dynamic adapter to base prompt (ablation)SyP · MM-IMDb 50% both missingF1-Macro: 48.95 -> 51.21Improved
add dynamic adapter to synergistic prompts (ablation)SyP · Food101 50% both missingaccuracy: 84.85 -> 86.17Improved
add dynamic adapter to synergistic prompts (ablation)SyP · MM-IMDb 50% both missingF1-Macro: 51.90 -> 54.72Improved
add dynamic adapter to synergistic prompts (ablation)SyP · Hateful Memes 50% both missingAUROC: 66.19 -> 68.16Improved
use SyP instead of DCP at 90% both-missingSyP · Hateful Memes test 90% both missingAUROC: 66.78 -> 68.93Improved
use SyP instead of DCP at 90% both-missingSyP · MM-IMDb test 90% both missingF1-Macro: 48.04 -> 49.63Improved

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