AI Paper Atlas

Research map / Video / Video-language understanding

Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs

Shaojie Zhang, Jiahui Yang, Jianqin Yin, Zhenbo Luo, Jian Luan

ICCV 2025 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 58 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 Q-Frame query-aware selection and multi-resolution to Qwen2-VLQwen2-VL · MLVUaccuracy: 56.9 -> 65.4Improved
add Q-Frame to GPT-4o frame selectionGPT-4o · LongVideoBench valaccuracy: 53.3 -> 58.6Improved
add Q-Frame frame selection to VILA-V1.5 instead of Frame-VoyagerVILA-V1.5 · MLVUaccuracy: 49.8 -> 54.4Improved
add Q-Frame to VILA-V1.5 on very short videos (8s,15s]VILA-V1.5 · LongVideoBench (8s,15s]accuracy: 56.1 -> 52.9Hurt
add Q-Frame to Qwen2-VL on long videos (15m,60m]Qwen2-VL · LongVideoBench (15m,60m]accuracy: 45.9 -> 56.4Improved
add Gumbel-Max QFS sampling to CLIP top-K selection (ablation)Q-Frame · LongVideoBench valaccuracy: 56.0 -> 57.6Improved
add query-aware QFS selection to MRA (ablation)Q-Frame · LongVideoBench valaccuracy: 52.6 -> 58.4Improved
add MRA multi-resolution to QFS (ablation)Q-Frame · LongVideoBench valaccuracy: 57.6 -> 58.4Improved
add medium and low resolution frames to high-only (ablation)Q-Frame MRA · LongVideoBench valaccuracy: 57.6 -> 58.4Improved
use only low-resolution frames instead of mixed resolutions (ablation)Q-Frame MRA · LongVideoBench valaccuracy: 58.4 -> 49.0Hurt
increase low-resolution frames from 32 to 48 (ablation)Q-Frame MRA · LongVideoBench valaccuracy: 58.4 -> 57.4Hurt
use Long-CLIP instead of standard CLIP for retrieval (ablation)Q-Frame CQR · LongVideoBench valaccuracy: 57.8 -> 58.4Improved

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