AI Paper Atlas

Research map / Video / Video-language understanding

4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding

Wenxuan Zhu, Bing Li, Cheng Zheng, Jinjie Mai, Jun Chen, Letian Jiang, Abdullah Hamdi, Sara Rojas Martinez, Chia-Wen Lin, Mohamed Elhoseiny, Bernard Ghanem

ICCV 2025 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 7 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
increase number of input views (ablation)Gemini 1.5 Flash · 4D-Bench 4D object QAaccuracy (%): 41.3 -> 53.7Improved
increase temporal sampling frequency (ablation)Gemini 1.5 Flash · 4D-Bench 4D object QAaccuracy (%): 46.3 -> 53.7Improved
use more than 3 views or 6 frames (ablation)Gemini 1.5 Flash · 4D-Bench 4D object QAaccuracy (%)Hurt
increase views from 1 to 6 (ablation)Qwen2-VL 7B · 4D-Bench 4D object captioningGPT-Eval: 2.79 -> 2.98Improved
increase frames per view from 1 to 3 (ablation)Qwen2-VL 7B · 4D-Bench 4D object captioningGPT-Eval: 2.48 -> 2.89Improved
increase frames per view to 6 (ablation)Qwen2-VL 7B · 4D-Bench 4D object captioningGPT-Eval: 2.96Improved
increase frames per view from 6 to 9 (ablation)Qwen2-VL 7B · 4D-Bench 4D object captioningGPT-EvalNo clear effect
order frames by time instead of viewpoint (ablation)all 14 MLLMs average · 4D-Bench 4D object QAoverall accuracy (%): 50.69 -> 50.13No clear effect
order frames by time instead of viewpoint (ablation)Qwen2-VL 7B · 4D-Bench 4D object QAoverall accuracy (%): 56.99 -> 49.80Hurt
order frames by time instead of viewpoint (ablation)InternVL2 8B · 4D-Bench 4D object QAoverall accuracy (%): 32.09 -> 38.88Improved
add timestamps to the prompt (ablation)all 14 MLLMs average · 4D-Bench 4D object QAoverall accuracy (%): 50.69 -> 49.95No clear effect
add timestamps to the prompt (ablation)VideoChat2 · 4D-Bench 4D object QAoverall accuracy (%): 32.36 -> 23.04Hurt

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