AI Paper Atlas

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

SEPS: Semantic-Enhanced Patch Slimming Framework for Fine-Grained Cross-Modal Alignment

Xinyu Mao, Junsi Li, Haoji Zhang, Yu Liang, Ming Sun

ICML 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Multimodal retrieval-augmented modeling · 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
add dense-text guidance alongside sparse text in patch selection (vs sparse only) (ablation)SEPS · Flickr30K 1Ktext-to-image R@1: 67.2 -> 80.5Improved
add the full consensus scoring rather than concatenating sparse and dense text (ablation)SEPS · Flickr30K 1Ktext-to-image R@1: 80.8 -> 86.9Improved
use weighted consensus instead of summing sparse and dense scores (ablation)SEPS · Flickr30K 1Ktext-to-image R@1: 81.1 -> 86.9Improved
add the adaptive aggregation network (ablation)SEPS · Flickr30K 1Ktext-to-image R@1: 83.7 -> 86.9Improved
add mean-value term to relevance-aware selection in SGMA (ablation)SEPS · Flickr30K 1Ktext-to-image R@1: 84.1 -> 86.9Improved
use salience-guided aggregation instead of mean pooling only (ablation)SEPS · Flickr30K 1Ktext-to-image R@1: 82.4 -> 86.9Improved
use dense text of the same image instead of another image from same dataset (ablation)SEPS · Flickr30K 1Ktext-to-image R@1: 79.3 -> 86.9Improved
use dense text from the same dataset rather than a different dataset (ablation)SEPS · Flickr30K 1Ktext-to-image R@1: 71.7 -> 79.3Improved
replace LAPS with SEPS on zero-shot COCO transferLAPS · MS-COCO 5K (zero-shot)text-to-image R@1: 19.0 -> 44.3Improved
replace D2S-VSE with SEPS in online inference latencyD2S-VSE · Flickr30K inferenceonline inference latency: 78ms -> 107msHurt
replace LAPS with SEPS on CLIP ViT-Base fine-tuningLAPS · Flickr30K 1K (CLIP)text-to-image R@1: 80.6 -> 93.1Improved
replace LAPS with SEPS on zero-shot RefCOCO groundingLAPS · RefCOCO valaccuracy: 44.2 -> 48.7Improved

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