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.

Datasets/HACS

HACS

Human Action Clips and Segments

VideosBSD 3-Clause

HACS is a dataset for human action recognition. It uses a taxonomy of 200 action classes, which is identical to that of the ActivityNet-v1.3 dataset. It has 504K videos retrieved from YouTube. Each one is strictly shorter than 4 minutes, and the average length is 2.6 minutes. A total of 1.5M clips of 2-second duration are sparsely sampled by methods based on both uniform randomness and consensus/disagreement of image classifiers. 0.6M and 0.9M clips are annotated as positive and negative samples, respectively.

Authors split the collection into training, validation and testing sets of size 1.4M, 50K and 50K clips, which are sampled from 492K, 6K and 6K videos, respectively.

Benchmarks

Action Localization/Average-mAPAction Localization/mAP@0.5Action Localization/mAP@0.75Action Localization/mAP@0.95Action Recognition/Top 1 AccuracyAction Recognition/Top 5 AccuracyActivity Recognition/Top 1 AccuracyActivity Recognition/Top 5 AccuracyTemporal Action Localization/Average-mAPTemporal Action Localization/mAP@0.5Temporal Action Localization/mAP@0.75Temporal Action Localization/mAP@0.95Video/Average-mAPVideo/mAP@0.5Video/mAP@0.75Video/mAP@0.95Zero-Shot Learning/Average-mAPZero-Shot Learning/mAP@0.5Zero-Shot Learning/mAP@0.75Zero-Shot Learning/mAP@0.95

Statistics

Papers
75
Benchmarks
20

Links

Homepage

Tasks

Action LocalizationAction RecognitionActivity RecognitionTemporal Action LocalizationVideoZero-Shot Learning