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/THUMOS14

THUMOS14

VideosUnknown

The THUMOS14 (THUMOS 2014) dataset is a large-scale video dataset that includes 1,010 videos for validation and 1,574 videos for testing from 20 classes. Among all the videos, there are 220 and 212 videos with temporal annotations in validation and testing set, respectively.

Source: Learning to Localize Actions from Moments Image Source: http://crcv.ucf.edu/THUMOS14/

Benchmarks

Action Detection/mIoUAction Localization/Avg mAP (0.3:0.7)Action Localization/avg-mAP (0.3-0.7)Action Localization/avg-mAP (0.1:0.7)Action Localization/avg-mAP (0.1-0.5)Action Recognition/AccuracyActivity Recognition/AccuracyTemporal Action Localization/Avg mAP (0.3:0.7)Temporal Action Localization/avg-mAP (0.3-0.7)Temporal Action Localization/avg-mAP (0.1:0.7)Temporal Action Localization/avg-mAP (0.1-0.5)Video/Avg mAP (0.3:0.7)Video/avg-mAP (0.3-0.7)Video/avg-mAP (0.1:0.7)Video/avg-mAP (0.1-0.5)Weakly Supervised Action Localization/avg-mAP (0.3-0.7)Weakly Supervised Action Localization/avg-mAP (0.1:0.7)Weakly Supervised Action Localization/avg-mAP (0.1-0.5)Zero-Shot Learning/Avg mAP (0.3:0.7)Zero-Shot Learning/avg-mAP (0.3-0.7)Zero-Shot Learning/avg-mAP (0.1:0.7)Zero-Shot Learning/avg-mAP (0.1-0.5)

Statistics

Papers
318
Benchmarks
22

Links

Homepage

Tasks

Action ClassificationAction DetectionAction LocalizationAction RecognitionAction Recognition In VideosActivity RecognitionFew Shot Temporal Action LocalizationOnline Action DetectionSemi-Supervised Action DetectionTemporal Action LocalizationTemporal Action Proposal GenerationVideoWeakly Supervised Action LocalizationWeakly-supervised Temporal Action LocalizationZero-Shot Action DetectionZero-Shot Action RecognitionZero-Shot Learning