TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

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

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

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

SotA/Computer Vision/Action Localization/AVA-Kinetics

Action Localization on AVA-Kinetics

Metric: val mAP (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕val mAP▼Extra DataPaperDate↕Code
1VideoMAE V2-g42.6YesVideoMAE V2: Scaling Video Masked Autoencoders w...2023-03-29Code
2STAR/L41.7YesEnd-to-End Spatio-Temporal Action Localisation w...2023-04-24-
3InternVideo41.01YesInternVideo: General Video Foundation Models via...2022-12-06Code
4RM (multi-scale, ensemble)40.52YesRelation Modeling in Spatio-Temporal Action Loca...2021-06-15-
5ACAR (multi-scale, ensemble)40.49YesActor-Context-Actor Relation Network for Spatio-...2020-06-14Code
6RM (multi-scale, ir-CSN-152)37.95NoRelation Modeling in Spatio-Temporal Action Loca...2021-06-15-
7ACAR (multi-scale, R-101, 8 × 8)36.36NoActor-Context-Actor Relation Network for Spatio-...2020-06-14Code