FineParser

Reported on 4 benchmarks across 1 task · 1 paper · 1 SOTA

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

Computer Vision4 results

Action Quality AssessmentonFineDiving
RL2(*100)· 2024-05-11
0.2602
best: 0.2838 (RICA^2)
SOTA
FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment arXiv:2405.06887
Action Quality AssessmentonFineDiving
Spearman Correlation· 2024-05-11
0.9435
best: 0.961 (NeuroSymbolic-AQA)
FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment arXiv:2405.06887
Action Quality AssessmentonMTL-AQA
RL2(*100)· 2024-05-11
0.241
best: 0.654 (MUSDL)
FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment arXiv:2405.06887
Action Quality AssessmentonMTL-AQA
Spearman Correlation· 2024-05-11
95.85
best: 96.2 (RICA^2 (Deterministic))
FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment arXiv:2405.06887