AI Paper Atlas

Research map / Video / Video-language understanding

MDP3: A Training-free Approach for List-wise Frame Selection in Video-LLMs

Hui Sun, Shiyin Lu, Huanyu Wang, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Ming Li

ICCV 2025 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 24 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
replace uniform sampling with mDP3 frame selectionVILA-V1.5-8B · Video-MME (w/o subs, 8 frames)accuracy: 47.5 -> 53.3Improved
replace uniform sampling with mDP3 frame selectionMiniCPM-V2.6-7B · Video-MME (w/o subs, 8 frames)accuracy: 52.6 -> 58.0Improved
replace uniform sampling with mDP3 frame selectionLLaVA-OneVision-7B · Video-MME (w/o subs, 8 frames)accuracy: 53.6 -> 59.6Improved
replace uniform sampling with mDP3 frame selectionOvis2-7B · Video-MME (w/o subs, 8 frames)accuracy: 58.9 -> 63.9Improved
add mDP3 instead of Frame-VoyagerVILA-V1.5-8B · Video-MME (w/o subs, 8 frames)accuracy: 50.5 -> 53.3Improved
add sequentiality (Markov segment-wise selection) to DPP (ablation)mDP3 on VILA-V1.5-8B · Video-MME (w/o subs, 8 frames)accuracy: 51.8 -> 53.3Improved
use conditional kernel in RKHS instead of cosine similarity (ablation)mDP3 on VILA-V1.5-8B · Video-MME (w/o subs, 8 frames)accuracy: 50.2 -> 53.3Improved
use conditional multi-gaussian kernel instead of unconditional MGK (ablation)mDP3 on VILA-V1.5-8B · Video-MME (w/o subs, 8 frames)accuracy: 48.9 -> 53.3Improved
add diversity and sequentiality on top of SigLIP query-relevance top-k (ablation)mDP3 on VILA-V1.5-8B · Video-MME (w/o subs, 8 frames)accuracy: 50.6 -> 53.3Improved
use rule-based shot boundary selection (RGB histogram) instead of uniform (ablation)VILA-V1.5-8B · Video-MME (w/o subs, 8 frames)accuracy: 47.5 -> 45.9Hurt
use Edges Change Ratio selection instead of uniform (ablation)VILA-V1.5-8B · Video-MME (w/o subs, 8 frames)accuracy: 47.5 -> 47.3No clear effect
mDP3 on MiniCPM-V2.6 for long videosMiniCPM-V2.6-7B · Video-MME long (w/o subs)accuracy: 46.4 -> 48.4Improved

Later papers that compared with this method

1 later accepted paper reports MDP3 as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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