AI Paper Atlas

Research map / Video / Video-language understanding

LENS: Adaptive Spatio-Temporal Zooming for Keyframe Sampling in Long-Form Videos

Ce Zhang, Jinxi He, Yaqi Xie, Katia Sycara

ECCV 2026 · Video › Video-language understanding · approach: Video LLMs with fine-grained 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 CLIP query-aware frame scoring (ablation)Qwen2.5-VL · Video-MME overall, 8 framesaccuracy (%): 53.3 -> 56.6Improved
use BLIP instead of CLIP for frame scoring (ablation)Qwen2.5-VL · Video-MME overall, 8 framesaccuracy (%): 56.6 -> 57.0Improved
add spatial zoom-in visual prompting (ablation)Qwen2.5-VL · Video-MME overall, 8 framesaccuracy (%): 57.0 -> 59.6Improved
add temporal zoom-out via video graph and hyperframes (all frames) (ablation)Qwen2.5-VL · Video-MME overall, 8 framesaccuracy (%): 57.0 -> 59.2Improved
combine spatial and temporal branches with fixed 4/4 split (ablation)Qwen2.5-VL · Video-MME overall, 8 framesaccuracy (%): 59.6 -> 60.2Improved
add adaptive budget allocation instead of fixed 4/4 split (ablation)Qwen2.5-VL · Video-MME overall, 8 framesaccuracy (%): 60.2 -> 60.7Improved
use stronger allocator (GPT-5-Mini or Gemini-2.5-Pro) instead of default (ablation)LENS · Video-MME overallaccuracy (%): +0.4% and +0.7%No clear effect
add graph propagation (alpha 0.8 instead of 0) (ablation)LENS · Video-MME overall, 8 framesaccuracy (%): 60.2 -> 60.7Improved
use moderate propagation alpha 0.8 instead of 1 (ablation)LENS · Video-MME overall, 8 framesaccuracy (%): 59.0 -> 60.7Improved
use hyperframe size tau 4 instead of 1 (ablation)LENS · Video-MME overall, 8 framesaccuracy (%): 59.7 -> 60.7Improved
use hyperframe size tau 4 instead of 9 (ablation)LENS · Video-MME overall, 8 framesaccuracy (%): 60.3 -> 60.7Improved
use sigma 0.3 instead of 0.1 (ablation)LENS · Video-MME overall, 8 framesaccuracy (%): 60.4 -> 60.7Improved

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