AI Paper Atlas

Research map / Video / Video-language understanding

LensWalk: Agentic Video Understanding by Planning How You See in Videos

Keliang Li, Yansong Li, Hongze Shen, Mengdi Liu, Hong Chang, Shiguang Shan

CVPR 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 10 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 Scan Search tool (ablation)LensWalk (o3/GPT-4.1) · Video-MME (long)accuracy: -4.6% when removedImproved
add Stitch Verify tool (ablation)LensWalk (o3/GPT-4.1) · Video-MME (long)accuracy: -3.2% when removedImproved
add Segment Focus tool (ablation)LensWalk (o3/GPT-4.1) · Video-MME (long)accuracy: -1.9% when removedImproved
add Timestamp Anchor (ablation)LensWalk (o3/GPT-4.1) · Video-MME (long)accuracy: to 69.7Improved
add Subject Memory Table (ablation)LensWalk (o3/GPT-4.1) · Video-MME (long)accuracy: 69.7 -> 70.0Improved
wrap o3 reasoner around GPT-4.1 observerGPT-4.1 · Video-MME (long)accuracy: 63.1 -> 70.0 (+6.9)Improved
use open-source Qwen3-235B-A22B as reasoner instead of o3 (ablation)LensWalk with GPT-4.1 observer · Video-MME (long)accuracy: 63.1 -> 63.2 (+0.1)No clear effect
use open-source Qwen3-235B-A22B as reasoner (ablation)LensWalk with Qwen2.5-VL-72B observer · Video-MME (long)accuracy: 63.1 -> 62.5 (-0.6)Hurt
use open-source Qwen3-235B-A22B as reasoner (ablation)LensWalk with Qwen2.5-VL-7B observer · Video-MME (long)accuracy: 55.4 -> 59.7 (+4.3)Improved
apply LensWalk with o3 as both reasoner and observero3 · LVBenchaccuracy: 57.1 -> 68.6Improved
apply LensWalk with o3 as both reasoner and observero3 · Video-MME (long)accuracy: 64.7 -> 71.4Improved
apply LensWalk with o3 reasoner and GPT-4.1 observero3 · MMVU (MC)accuracy: 78.9 -> 80.9Improved

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