AI Paper Atlas

Research map / Point clouds / Point cloud classification

Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videos

Zhiqiang Shen, Xiaoxiao Sheng, Hehe Fan, Longguang Wang, Yulan Guo, Qiong Liu, Hao Wen, Xi Zhou

ICCV 2023 · Point clouds › Point cloud classification · approach: Masked point autoencoders · 27 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 MaST-Pre pre-training then fine-tuneP4Transformer · NTU-RGBD cross-subjectaccuracy: 90.2 -> 90.8Improved
add MaST-Pre pre-training then fine-tuneP4Transformer · MSRAction-3Daccuracy: 90.94 -> 91.29Improved
add MaST-Pre pre-training then fine-tunePST-Transformer · MSRAction-3Daccuracy: 93.73 -> 94.08Improved
transfer NTU-RGBD pre-trained encoder to gesture recognition (30 epochs)P4Transformer · NvGestureaccuracy: 84.8 -> 87.6Improved
transfer NTU-RGBD pre-trained encoder to gesture recognition (30 epochs)P4Transformer · SHREC'17accuracy: 87.5 -> 90.2Improved
add motion (temporal cardinality difference) prediction stream (ablation)MaST-Pre · 10% NTU-RGBDaccuracy: 70.13 -> 78.25Improved
add appearance stream only pre-training (ablation)P4Transformer · 10% NTU-RGBDaccuracy: 65.85 -> 70.13Improved
use 75% masking ratio instead of 65% or 85% (ablation)MaST-Pre · 10% NTU-RGBDaccuracy: 76.91 / 77.20 -> 78.25Improved
use decoupled instead of coupled reconstruction loss in point tubes (ablation)appearance stream · 10% NTU-RGBDaccuracy: 58.60 -> 78.25Improved
use 8 sections instead of 16 in cardinality difference (ablation)MaST-Pre · 10% NTU-RGBDaccuracy: 69.50 -> 78.25Improved
add interpolation in cardinality difference (ablation)MaST-Pre · 10% NTU-RGBDaccuracy: 76.69 -> 78.25Improved
use temporal stride 1 instead of 2 (ablation)cardinality difference · 10% NTU-RGBDaccuracy: 75.85 -> 78.25Improved

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