AI Paper Atlas

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

StoryTailor:A Zero-Shot Pipeline for Action-Rich Multi-Subject Visual Narratives

Jinghao Hu, Yuhe Zhang, Guohua Geng, Kang Li, Han Zhang

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs

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-Boost SVR (ablation)StoryTailor · Multi-subject narrativesCLIP-T: 0.364 -> 0.406Improved
add Selective Forgetting Cache (ablation)StoryTailor · Multi-subject narrativesCLIP-T: 0.341 -> 0.406Improved
add Gaussian-Centered Attention (ablation)StoryTailor · Multi-subject narrativesCLIP-T: 0.319 -> 0.406Improved
add Gaussian-Centered Attention (ablation)StoryTailor · Multi-subject narrativesCLIP-I: 0.684 -> 0.671Hurt
add Gaussian-Centered Attention (ablation)StoryTailor · Multi-subject narrativesSubject confusion: Y -> NImproved
add Action-Boost SVR (ablation)StoryTailor · Multi-subject narrativesCLIP-I: 0.636 -> 0.671Improved
use two-stage anisotropic dynamic Gaussian (GCA) instead of binary box mask (ablation)GCA · Multi-subject action scenesCLIP-T: 0.285 -> 0.416Improved
make Gaussian radii dynamic rather than static (ablation)GCA · Multi-subject action scenesCLIP-T: 0.354 -> 0.416Improved
use two-stage instead of single-stage Gaussian (ablation)GCA · Multi-subject action scenesSubject confusion: Y -> NImproved
use Gaussian diffusion split instead of GCA (ablation)GCA · Multi-subject action scenesLatency (s): 7.57 -> 31.32Hurt
raise AB-SVR energy threshold tau from 0.80 to 0.92 or 0.98 (ablation)AB-SVR · Qualitative sweep, dog and dog+catidentity and pose qualityHurt
lower AB-SVR energy threshold tau to 0.50 or 0.56 (ablation)AB-SVR · Qualitative sweep, dog and dog+cataction fidelityHurt

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