OpenCodePapers

action-classification-on-toyota-smarthome

VideoAction Classification
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeCSCV1CV2AccuracyModelNameReleaseDate
Just Add $π$! Pose Induced Video Transformers for Understanding Activities of Daily Living✓ Link72.955.264.8π-ViT2023-11-30
EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition✓ Link71.767.8EPAM-Net2024-08-10
MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos✓ Link70.1MMNet2022-05-26
UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition✓ Link64.336.165.0UNIK2021-07-19
AssembleNet++: Assembling Modality Representations via Attention Connections✓ Link63.6AssembleNet++2020-08-18
Adaptive Intermediate Representations for Video Understanding62.11AIRStreams2021-04-14
VPN: Learning Video-Pose Embedding for Activities of Daily Living✓ Link60.843.853.5VPN (RGB + Pose)2020-07-06
Toyota Smarthome: Real-World Activities of Daily Living54.235.250.3Separable STA (RGB + Pose)2019-10-01
Non-local Neural Networks✓ Link53.634.343.9I3D + Non Local2017-11-21
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset✓ Link53.434.945.1I3D2017-05-22
Improved Dense Trajectory with Cross Streams41.920.923.7Dense Trajectories2016-04-29
Recognizing Actions in Videos from Unseen Viewpoints39.654.6NPL2021-03-30
Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions✓ Link70.22Trans4SOAR (Pose)2022-02-23