AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

LLM-enhanced Action-aware Multi-modal Prompt Tuning for Image-Text Matching

Mengxiao Tian, Xinxiao Wu, Shuo Yang

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Prompt learning for CLIP · 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 action-aware prompts from LLM knowledge versus plain learnable visual prompts (ablation)CLIP ViT-B/16 · COCO 5Kimage-to-text R@1: 55.3 -> 58.4Improved
add action state prompt to action triplet prompt (ablation)CLIP ViT-B/16 · COCO 5Kimage-to-text R@1: 56.2 -> 58.1Improved
use LLM-generated action triplet prompt instead of hand-crafted template (ablation)CLIP ViT-B/16 · COCO 5Kimage-to-text R@1: 55.5 -> 56.2Improved
add visual prompt (ablation)CLIP ViT-B/16 · COCO 5Kimage-to-text R@1: 58.1 -> 58.4Improved
add attribute knowledge to action triplets (ablation)CLIP ViT-B/16 · COCO 5Kimage-to-text R@1: 58.2 -> 58.4Improved
use adaptive interaction module instead of concatenation (ablation)CLIP ViT-B/16 · COCO 5Kimage-to-text R@1: 57.4 -> 58.4Improved
use two-stage training instead of one-stage (ablation)CLIP ViT-B/16 · COCO 5Kimage-to-text R@1: 56.8 -> 58.4Improved
use two-stage training instead of combined losses (ablation)CLIP ViT-B/16 · COCO 5Kimage-to-text R@1: 56.5 -> 58.4Improved
swap GPT-3.5 for smaller open LLM (Vicuna-7B) (ablation)action knowledge generation · COCO 5Kimage-to-text R@1: 58.4 -> 58.4No clear effect
apply method to CLIP ViT-L/14-336CLIP · COCO 5KRsum: 394.2 -> 438.5Mixed
apply method to CLIP ViT-B/32CLIP · Flickr30K 1KRsum: 502.3 -> 535.6Improved

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