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/Time Series/Action Recognition/HMDB51 (finetuned)

Action Recognition on HMDB51 (finetuned)

Metric: Top-1 Accuracy (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕Top-1 Accuracy▼Extra DataPaperDate↕Code
1BraVe:V-FA (TSM-50x2)77.8NoBroaden Your Views for Self-Supervised Video Lea...2021-03-30Code
2MMV70.1NoSelf-Supervised MultiModal Versatile Networks2020-06-29Code
3CVRL (R3D-152 2x; K600)69.9NoSpatiotemporal Contrastive Video Representation ...2020-08-09Code
4XDC68.9NoSelf-Supervised Learning by Cross-Modal Audio-Vi...2019-11-28Code
5CVRL (R3D-50; K600)68NoSpatiotemporal Contrastive Video Representation ...2020-08-09Code
6ELo67.4NoEvolving Losses for Unsupervised Video Represent...2020-02-26-
7CVRL (R3D-50; K400)66.7NoSpatiotemporal Contrastive Video Representation ...2020-08-09Code
8AVID64.7NoAudio-Visual Instance Discrimination with Cross-...2020-04-27Code
9ViCC (S3D; R+F)62.2NoSelf-supervised Video Representation Learning wi...2021-06-18Code
10AVTS61.6NoCooperative Learning of Audio and Video Models f...2018-06-30-
11ViCC (R2+1D; R+F)61.5NoSelf-supervised Video Representation Learning wi...2021-06-18Code
12CoCLR54.6NoSelf-supervised Co-training for Video Representa...2020-10-19Code
13ViCC (R2+1D; RGB)52.4NoSelf-supervised Video Representation Learning wi...2021-06-18Code
14ViCC (S3D; RGB))47.9NoSelf-supervised Video Representation Learning wi...2021-06-18Code