AI Paper Atlas

Research map / Video / Video-language understanding

TripleSumm: Adaptive Triple-Modality Fusion for Video Summarization

Sumin Kim, Hyemin Jeong, Mingu Kang, Yejin Kim, Yoori Oh, Joonseok Lee

ICLR 2026 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 2 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 text and audio to visual input (trimodal) (ablation)TripleSumm · MoSuKendall tau: 0.298 -> 0.351Improved
add multi-scale temporal block to cross-modal fusion only (ablation)TripleSumm · MoSuKendall tau: 0.250 -> 0.351Improved
add cross-modal fusion block to MST only (ablation)TripleSumm · MoSuKendall tau: 0.337 -> 0.351Improved
use dynamic per-frame fusion instead of static averaging (ablation)TripleSumm · MoSuKendall tau: 0.338 -> 0.351Improved
use dynamic per-frame fusion instead of global weights (ablation)TripleSumm · MoSuKendall tau: 0.344 -> 0.351Improved
use local-to-global window schedule instead of constant global window (ablation)TripleSumm · MoSuKendall tau: 0.317 -> 0.351Improved
use local-to-global instead of global-to-local window schedule (ablation)TripleSumm · MoSuKendall tau: 0.345 -> 0.351Improved
share temporal block parameters across modalities (ablation)TripleSumm · MoSuKendall tau: 0.343 -> 0.351; params 2.95M -> 1.37MImproved
use average of modalities as fusion token instead of learnable (ablation)TripleSumm · MoSuKendall tau: 0.341 -> 0.351Improved
use average fusion token instead of visual-only token (ablation)TripleSumm · MoSuKendall tau: 0.337 -> 0.351Improved
add learnable Gaussian window modulation (ablation)TripleSumm · MoSuKendall tau: 0.351 -> 0.353No clear effect
increase layers from 2 to 8 (ablation)TripleSumm · MoSuKendall tau: 0.351 -> 0.326Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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