AI Paper Atlas

Research map / Video / Video-language understanding

LLaFEA: Frame-Event Complementary Fusion for Fine-Grained Spatiotemporal Understanding in LMMs

Hanyu Zhou, Gim Hee Lee

ICCV 2025 · Video › Video-language understanding · approach: Long video understanding · 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 event camera input to frame input for LMMs (ablation)LLaFEA · RealEvent-STt-IoU: 22.05 -> 52.80Improved
add frame input to event-only input (ablation)LLaFEA · RealEvent-STs-IoU: 35.75 -> 46.27Improved
add event-based frame interpolation (w/ FI) to frame-only LMM baselinesVTimeLLM · RealEvent-STt-IoU: 21.05 -> 23.55Improved
add coordinate embedding of textual position and duration (ablation)LLaFEA · RealEvent-STs-IoU: 14.15 -> 46.27Improved
add coordinate embedding (ablation)LLaFEA · RealEvent-STDC: 3.62 -> 3.65No clear effect
add cross-attention spatial fusion only (ablation)LLaFEA · RealEvent-STs-IoU: 4.03 -> 15.40Improved
add cross-attention temporal fusion only (ablation)LLaFEA · RealEvent-STt-IoU: 6.15 -> 22.74Improved
add self-attention matching (ablation)LLaFEA · RealEvent-STt-IoU: 6.15 -> 21.02Improved
combine cross-attention fusion with self-attention matching (ablation)LLaFEA · RealEvent-STt-IoU: 21.02 -> 52.80Improved
use attention fusion instead of concatenation (ablation)LLaFEA · RealEvent-STt-IoU: 40.32 -> 52.80Improved
use attention fusion instead of weighting (ablation)LLaFEA · RealEvent-STs-IoU: 36.85 -> 46.27Improved
use staged separate training instead of joint training (ablation)LLaFEA · RealEvent-STs-IoU: 38.05 -> 46.27Improved

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