AI Paper Atlas

Research map / Video / Video-language understanding

KDA: Knowledge Diffusion Alignment with Enhanced Context for Video Temporal Grounding

Ran Ran, Jiwei Wei, Shiyuan He, Zeyu Ma, Chaoning Zhang, Ning Xie, Yang Yang

ICCV 2025 · Video › Video-language understanding · approach: Temporal video grounding · 4 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 MKDM diffusion moment knowledge (ablation)KDA baseline · QVHighlights val (SF+C)R1@0.5: 64.64 -> 66.05Improved
add MVKE multi-layer knowledge extraction (ablation)KDA with MKDM and SED · QVHighlights val (SF+C)mAP avg: 46.08 -> 47.41Improved
add spans-enhanced decoder (ablation)KDA with MKDM and MVKE · QVHighlights val (SF+C)mAP avg: 45.79 -> 47.41Improved
use BRDM instead of DDPM (ablation)KDA diffusion · QVHighlights val (SF+C)mAP avg: 45.53 -> 47.41Improved
use BRDM (4 steps) instead of DDIM (4 steps) (ablation)KDA diffusion · QVHighlights val (SF+C)mAP avg: 44.78 -> 47.41Improved
add diffusion model with 4 steps (ablation)KDA · QVHighlights val (SF+C)mAP avg: 44.86 -> 47.41Improved
increase diffusion steps from 4 to 8 (ablation)KDA · QVHighlights val (SF+C)mAP avg: 47.41 -> 47.30; time 9.3s -> 11.5sNo clear effect
use adaptive spans and query contents instead of spans only (ablation)KDA decoder · QVHighlights val (SF+C)mAP avg: 47.41 -> 44.76Hurt
use static spans and query instead of SED (ablation)KDA decoder · QVHighlights val (SF+C)mAP avg: 47.41 -> 45.86Hurt
KDA vs UVCOM on TACoSKDA · TACoS (SF+C)R1@0.5: 36.39 -> 40.13Improved
KDA vs TR-DETR on Charades-STA VGGKDA · Charades-STA (VGG)R1@0.7: 30.81 -> 34.50Improved

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