AI Paper Atlas

Research map / Point clouds / Point cloud classification

PointCMP: Contrastive Mask Prediction for Self-Supervised Learning on Point Cloud Videos

Zhiqiang Shen, Xiaoxiao Sheng, Longguang Wang, Yulan Guo, Qiong Liu, Xi Zhou

CVPR 2023 · Point clouds › Point cloud classification · approach: Masked point autoencoders · 22 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
Pre-train with PointCMP, then fine-tune PSTNetPSTNet · MSRAction-3D, 8 framesaccuracy (%): 83.50% to 89.56%Improved
Pre-train with PointCMP, then use a frozen encoder with a linear classifierPSTNet · MSRAction-3D, 8 and 12 framesaccuracy (%): 83.50% to 88.55%; 87.88% to 90.24%Improved
Use PointCMP pre-training with 50% of NTU-RGBD training dataPSTNet · NTU-RGBD cross-subjectaccuracy (%): 88.5% vs. 90.5%Mixed
Transfer PointCMP-pretrained representations to PSTNetPSTNet · NvGesture, 35 epochsaccuracy (%): 78.9% vs. 84.0%Improved
Use both local and global branches rather than either branch alone (ablation)PointCMP · MSRAction-3Daccuracy (%): 89.22% and 49.49% -> 89.76%Improved
Add similarity-based augmentation to the local and global branches (ablation)PointCMP · MSRAction-3Daccuracy (%): 89.76% -> 91.92%Improved
Use segment-wise rather than token-wise masking (ablation)PointCMP · MSRAction-3Daccuracy (%)Improved
Use similarity-based rather than random segment masking (ablation)PointCMP · MSRAction-3D, segment masking at 25% and 50%accuracy (%): 90.81%/88.15% -> 91.92%/90.24%Improved
Add hard negative samples (ablation)PointCMP global branch · MSRAction-3Daccuracy (%): 90.52% -> 91.92%Improved
Generate hard negatives by principal-channel erasing rather than random channel erasing (ablation)PointCMP global branch · MSRAction-3Daccuracy (%): 91.29 -> 91.92Improved
Add the spatio-temporal matching module (ablation)PointCMP local branch · MSRAction-3D, local branch onlyaccuracy (%): 86.20 -> 89.22Improved
Add the spatio-temporal matching module (ablation)PointCMP local and global branches · MSRAction-3Daccuracy (%): 90.24 -> 91.92Improved

Later papers that compared with this method

4 later accepted papers report PointCMP as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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