AI Paper Atlas

Research map / Point clouds / Point cloud classification

PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences

Hehe Fan, Xin Yu, Yuhang Ding, Yi Yang, Mohan Kankanhalli

ICLR 2021 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 65 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
use PSTNet instead of MeteorNetpoint-cloud action recognition · MSR-Action3D, 24 framesaccuracy: 88.50 -> 91.20Improved
use PSTNet instead of 3DV-PointNet++3D action recognition · NTU RGB+D 120, Subjectaccuracy: 82.4 -> 87.0Improved
use PSTNet instead of MeteorNet4D semantic segmentation · Synthia 4DmIoU: 81.80 -> 82.24Improved
increase temporal kernel size from l=1 to l=3 (ablation)PSTNet · Synthia 4DmIoU: 80.79 -> 82.24; 1.45%Improved
add point tracking across frames (ablation)PSTNet · Moving MNIST Point Cloudaccuracy: 97.15 -> 98.74Improved
replace lightweight spatial convolution with PointConv (ablation)PSTNet · MSR-Action3D, 16 framesaccuracy: 89.90 -> 90.24Improved
replace lightweight spatial convolution with PointConv (ablation)PSTNet · MSR-Action3D, 16 framesrunning time per clip: 31.92 -> 102.72Hurt
remove the sharing kernel (ablation)PSTNet spatial convolution · MSR-Action3D, 16 framesaccuracy: 89.90 -> 58.25Hurt
remove the sharing kernel (ablation)PSTNet spatial convolution · MSR-Action3D, 24 framesaccuracy: 91.20 -> 61.67Hurt
remove the displacement kernel (ablation)PSTNet spatial convolution · MSR-Action3D, 16 framesaccuracy: 89.90 -> 86.35Hurt
remove the displacement kernel (ablation)PSTNet spatial convolution · MSR-Action3D, 24 framesaccuracy: 91.20 -> 87.46Hurt
disentangle spatial and temporal modeling instead of combining space and time in one kernel (ablation)PSTNet · MSR-Action3DaccuracyImproved

Later papers that compared with this method

9 later accepted papers report PSTNet as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.

1 more not listed.

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