AI Paper Atlas

Research map / Video / Video generation

SUV: Suppressing Undesired Video Content via Semantic Modulation Based on Text Embeddings

Xiang Lv, Mingwen Shao, Lingzhuang Meng, Chang Liu, Yecong Wan, Xinyuan Chen

ICCV 2025 · Video › Video generation · approach: Diffusion-based video editing · 1 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 exponential suppression operator on negative-embedding singular values (ablation)SUV · video editing ablationframe accuracy: 0.7549 -> 0.8433Improved
add exponential suppression operator (ablation)SUV · video editing ablationtemporal consistency: 0.9671 -> 0.9748Improved
add embeddings optimization based on attention maps (push NE apart, pull PE closer) (ablation)SUV · video editing ablationframe accuracy: 0.7824 -> 0.8433Improved
add fuzzy feature selection strategy for cross-frame fusion (ablation)SUV · video editing ablationtemporal consistency: 0.9327 -> 0.9748Improved
add fuzzy feature selection strategy (ablation)SUV · video editing ablationframe accuracy: 0.8249 -> 0.8433Mixed
zero out embeddings of negated words only (without glasses) (ablation)baseline editing with text embeddings · qualitative analysispresence of negative contentNo clear effect
also zero out end embeddings (ablation)baseline editing with text embeddings · qualitative analysispresence of negative contentMixed
SUV versus TokenFlowtext-driven video editing · ~36 text-video pairsframe accuracy: 0.6361 -> 0.8681Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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