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 Recognition In Videos/UCF101

Action Recognition In Videos on UCF101

Metric: 3-fold Accuracy (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕3-fold Accuracy▼Extra DataPaperDate↕Code
1STM (ImageNet+Kinetics pretrain)96.2NoSTM: SpatioTemporal and Motion Encoding for Acti...2019-08-07-
23D-SqueezeNet74.94NoResource Efficient 3D Convolutional Neural Netwo...2019-04-04Code
33D-ShuffleNetV2 0.25x56.52NoResource Efficient 3D Convolutional Neural Netwo...2019-04-04Code
43D-MobileNetV2 0.2x55.56NoResource Efficient 3D Convolutional Neural Netwo...2019-04-04Code
5Baseline UCF10143.9NoUCF101: A Dataset of 101 Human Actions Classes F...2012-12-03Code