π-ViT

Reported on 3 benchmarks across 1 task · 1 paper · 2 SOTA

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

Computer Vision3 results

VideoonToyota Smarthome dataset
CS· uses extra data· 2023-11-30
72.9
SOTA
Just Add $π$! Pose Induced Video Transformers for Understanding Activities of Daily Living arXiv:2311.18840
VideoonToyota Smarthome dataset
CV1· uses extra data· 2023-11-30
55.2
SOTA
Just Add $π$! Pose Induced Video Transformers for Understanding Activities of Daily Living arXiv:2311.18840
VideoonToyota Smarthome dataset
CV2· uses extra data· 2023-11-30
64.8
best: 67.8 (EPAM-Net)
Just Add $π$! Pose Induced Video Transformers for Understanding Activities of Daily Living arXiv:2311.18840