AI Paper Atlas

Research map / Point clouds / Point cloud classification

4DPC$^2$hat: Towards Dynamic Point Cloud Understanding with Failure-Aware Bootstrapping

Xindan Zhang, Weilong Yan, YUFEI SHI, Xuerui Qiu, Tao He, Ying Li, Ming Li, Hehe Fan

ICML 2026 · Point clouds › Point cloud classification · approach: Self-supervised point cloud pretraining · 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
replace temporal Transformer with bidirectional Mamba (ablation)4DPC2hat · 4D object captioning (Objaverse)GPT-4 score: 69.08 -> 73.27Improved
replace temporal Transformer with bidirectional Mamba (ablation)4DPC2hat · 4D object QA (Objaverse)GPT-4 average score: 74.41 -> 78.01Improved
add two rounds of failure-aware bootstrapping after SFT (ablation)4DPC2hat · 4D object QA (Objaverse)GPT-4 average score: 74.40 -> 78.01Improved
add failure-aware bootstrapping, temporal category (ablation)4DPC2hat · 4D object QA (Objaverse)SimCSE temporal reasoning: 71.41 -> 76.52Improved
add failure-aware bootstrapping, counting category (ablation)4DPC2hat · 4D object QA (Objaverse)SimCSE counting: 73.19 -> 77.03Improved
naive data augmentation with failure-targeted QA instead of bootstrapping (ablation)4DPC2hat · 4D object QA (Objaverse)GPT-4 average score: 74.40 -> 75.87Mixed
second bootstrapping round beyond the first (ablation)4DPC2hat · 4D object QA (Objaverse)scoreMixed
increase bootstrapping data from 12k to 15k samples (ablation)4DPC2hat · 4D object QA (Objaverse)scoreNo clear effect
process frames independently with static 3D MLLMs plus temporal aggregation instead of sequence modelingPointLLM, ShapeLLM, MiniGPT-3D · 4D object captioning (Objaverse)GPT-4 score: 54.70 -> 73.27Hurt

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