Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/PSTNet

PSTNet

Reported on 18 benchmarks across 11 tasks · 2 papers · 7 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision7 results

VideoonNTU RGB+D
Cross View Accuracy· 2022-05-27
96.5
best: 96.7 (PSTNet++)
SOTA
PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences arXiv:2205.13713
Temporal Action LocalizationonNTU RGB+D
Cross View Accuracy· 2022-05-27
96.5
best: 96.7 (PSTNet++)
SOTA
PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences arXiv:2205.13713
Action LocalizationonNTU RGB+D
Cross View Accuracy· 2022-05-27
96.5
best: 96.7 (PSTNet++)
SOTA
PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences arXiv:2205.13713
VideoonNTU RGB+D
Cross Subject Accuracy· 2022-05-27
90.5
best: 92.3 (Kinet)
PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences arXiv:2205.13713
Temporal Action LocalizationonNTU RGB+D
Cross Subject Accuracy· 2022-05-27
90.5
best: 92.3 (Kinet)
PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences arXiv:2205.13713
Action LocalizationonNTU RGB+D
Cross Subject Accuracy· 2022-05-27
90.5
best: 92.3 (Kinet)
PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences arXiv:2205.13713
Scene SegmentationonPST900
mIoU· 2019-09-20
68.4
best: 89.8 (SHIFNet)
PST900: RGB-Thermal Calibration, Dataset and Segmentation Network arXiv:1909.10980

Methodology3 results

Zero-Shot LearningonNTU RGB+D
Cross View Accuracy· 2022-05-27
96.5
best: 96.7 (PSTNet++)
SOTA
PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences arXiv:2205.13713
Zero-Shot LearningonNTU RGB+D
Cross Subject Accuracy· 2022-05-27
90.5
best: 92.3 (Kinet)
PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences arXiv:2205.13713
2D Object DetectiononPST900
mIoU· 2019-09-20
68.4
best: 89.8 (SHIFNet)
PST900: RGB-Thermal Calibration, Dataset and Segmentation Network arXiv:1909.10980

Robots2 results

Activity RecognitiononNTU RGB+D
Cross View Accuracy· 2022-05-27
96.5
best: 96.7 (PSTNet++)
SOTA
PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences arXiv:2205.13713
Activity RecognitiononNTU RGB+D
Cross Subject Accuracy· 2022-05-27
90.5
best: 92.3 (Kinet)
PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences arXiv:2205.13713

Natural Language Processing2 results

3D Action RecognitiononNTU RGB+D
Cross View Accuracy· 2022-05-27
96.5
best: 96.7 (PSTNet++)
SOTA
PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences arXiv:2205.13713
3D Action RecognitiononNTU RGB+D
Cross Subject Accuracy· 2022-05-27
90.5
best: 92.3 (Kinet)
PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences arXiv:2205.13713

Time Series2 results

Action RecognitiononNTU RGB+D
Cross View Accuracy· 2022-05-27
96.5
best: 96.7 (PSTNet++)
SOTA
PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences arXiv:2205.13713
Action RecognitiononNTU RGB+D
Cross Subject Accuracy· 2022-05-27
90.5
best: 92.3 (Kinet)
PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences arXiv:2205.13713

Medical1 result

Semantic SegmentationonPST900
mIoU· 2019-09-20
68.4
best: 89.8 (SHIFNet)
PST900: RGB-Thermal Calibration, Dataset and Segmentation Network arXiv:1909.10980

Audio1 result

10-shot image generationonPST900
mIoU· 2019-09-20
68.4
best: 89.8 (SHIFNet)
PST900: RGB-Thermal Calibration, Dataset and Segmentation Network arXiv:1909.10980