AI Paper Atlas

Research map / Video / Video-language understanding

MetaphorVU: Towards Metaphorical Video Understanding

Zhuoqun Li, Boxi Cao, Guiping Jiang, Fangrui Lv, Ruotong Pan, Jianan Wang, Xiangyu Wu, Hongyu Lin, Yaojie Lu, Yong Du, Ruyin Jia, Liyan and 4 more

ICML 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 0 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 MetaphorBoost knowledge-graph mapping augmentationGemini-3-Pro · MetaphorVU-Benchaverage score: 63.8 -> 66.1Improved
add MetaphorBoost knowledge-graph mapping augmentationQwen2.5-VL-7B-Instruct · MetaphorVU-Benchaverage score: 33.8 -> 37.9Improved
add MetaphorBoost knowledge-graph mapping augmentationQwen3-VL-8B-Thinking · MetaphorVU-Benchaverage score: 52.0 -> 55.9Improved
add external knowledge augmentation (ablation)MetaphorBoost (Qwen3-VL-8B-Thinking) · MetaphorVU-Benchaverage score: 53.4 -> 55.9Improved
use graph-structure augmentation instead of plain text (ablation)MetaphorBoost (Qwen3-VL-8B-Thinking) · MetaphorVU-Benchaverage score: 54.3 -> 55.9Improved
use metaphor-oriented knowledge instead of commonsense knowledge (ablation)MetaphorBoost (Qwen3-VL-8B-Thinking) · MetaphorVU-Benchaverage score: 52.5 -> 55.9Improved
add common connection in query (ablation)MetaphorBoost (Qwen3-VL-8B-Thinking) · MetaphorVU-Benchaverage score: 54.8 -> 55.9Improved
use 2 hops instead of 1 hop (ablation)MetaphorBoost (Qwen3-VL-8B-Thinking) · MetaphorVU-Benchaverage score: 54.5 -> 55.9Improved
retain 10 results instead of 5 (ablation)MetaphorBoost (Qwen3-VL-8B-Thinking) · MetaphorVU-Benchaverage score: 55.7 -> 55.9No clear effect
apply LTR inference-time scalingQwen3-VL-8B-Thinking · MetaphorVU-Benchaverage score: 52.0 -> 44.5Hurt
apply ViTCoT inference-time scalingQwen3-VL-8B-Thinking · MetaphorVU-Benchaverage score: 52.0 -> 46.2Hurt
add metaphor-tailored prompt engineeringQwen3-VL-8B-Thinking · MetaphorVU-Benchaverage score: 52.0 -> 52.4No clear effect

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