PCNN

Reported on 7 benchmarks across 5 tasks · 1 paper

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

Natural Language Processing4 results

Relation ExtractiononNew York Times Corpus
P@10%
61.3
best: 92.3 (KGPOOL)
Relation ExtractiononNew York Times Corpus
P@30%
46.5
best: 86.7 (KGPOOL)
Relationship Extraction (Distant Supervised)onNew York Times Corpus
P@10%
61.3
best: 92.3 (KGPOOL)
Relationship Extraction (Distant Supervised)onNew York Times Corpus
P@30%
46.5
best: 86.7 (KGPOOL)

Computer Vision3 results

Shape Representation Of 3D Point CloudsonModelNet40
Overall Accuracy· 2018-03-27
92.3
best: 95.3 (PointGST)
Point Convolutional Neural Networks by Extension Operators arXiv:1803.10091
3D Point Cloud ClassificationonModelNet40
Overall Accuracy· 2018-03-27
92.3
best: 95.3 (PointGST)
Point Convolutional Neural Networks by Extension Operators arXiv:1803.10091
3D Point Cloud ReconstructiononModelNet40
Overall Accuracy· 2018-03-27
92.3
best: 95.3 (PointGST)
Point Convolutional Neural Networks by Extension Operators arXiv:1803.10091