Papers › Deep Hierarchical Representation of Point Cloud Videos via Spatio-Temporal Decomposition

Deep Hierarchical Representation of Point Cloud Videos via Spatio-Temporal Decomposition

14 Dec 2021IEEE Transactions on Pattern Analysis and Machine Intelligence 2021 12archive 2025-07-28

Fan, Hehe; Yu, Xin; Yang, Yi; Kankanhalli, Mohan

In point cloud videos, point coordinates are irregular and unordered but point timestamps exhibit regularities and order. Grid-based networks for conventional video processing cannot be directly used to model raw point cloud videos. Therefore, in this work, we propose a point-based network that directly handles raw point cloud videos. First, to preserve the spatio-temporal local structure of point cloud videos, we design a point tube covering a local range along spatial and temporal dimensions. By progressively subsampling frames and points and enlarging the spatial radius as the point features are fed into higher-level layers, the point tube can capture video structure in a spatio-temporally hierarchical manner. Second, to reduce the impact of the spatial irregularity on temporal modeling, we decompose space and time when extracting point tube representations. Specifically, a spatial operation is employed to capture the local structure of each spatial region in a tube and a temporal operation is used to model the dynamics of the spatial regions along the tube.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Action Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Action Recognition NTU RGB+D PSTNet++ Cross Subject Accuracy 91.4 #2 of 5 Archive leaderboard report
3D Action Recognition NTU RGB+D PSTNet++ Cross View Accuracy 96.7 #2 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections