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/UCF101

UCF101

UCF101 Human Actions dataset

VideosMITIntroduced 2012-12-03

UCF101 dataset is an extension of UCF50 and consists of 13,320 video clips, which are classified into 101 categories. These 101 categories can be classified into 5 types (Body motion, Human-human interactions, Human-object interactions, Playing musical instruments and Sports). The total length of these video clips is over 27 hours. All the videos are collected from YouTube and have a fixed frame rate of 25 FPS with the resolution of 320 × 240.

Source: Two-stream Collaborative Learning with Spatial-Temporal Attention for Video Classification Image Source: https://www.crcv.ucf.edu/data/UCF101.php

Benchmarks

3D Action Recognition/AccuracyAction Detection/AccuracyAction Localization/AccuracyAction Recognition/3-fold AccuracyAction Recognition/AccuracyAction Recognition/Accuracy 20%TestAction Recognition/Pre-Training DatasetAction Recognition/FrozenAction Recognition/split-1 Top-1 AccuracyAction Recognition/1:1 AccuracyAction Recognition In Videos/3-fold AccuracyActivity Recognition/3-fold AccuracyActivity Recognition/AccuracyActivity Recognition/Accuracy 20%TestActivity Recognition/Pre-Training DatasetActivity Recognition/FrozenActivity Recognition/split-1 Top-1 AccuracyActivity Recognition/1:1 AccuracyFew-Shot Learning/Harmonic meanImage Clustering/AccuracyImage Clustering/ARIImage Clustering/NMIMeta-Learning/Harmonic meanPrompt Engineering/Harmonic meanTemporal Action Localization/AccuracyVideo/AccuracyVideo/Top-1Video/PSNRVideo/SSIMVideo/PSNR (sRGB)Video/LPIPSVideo Frame Interpolation/PSNRVideo Frame Interpolation/SSIMVideo Frame Interpolation/PSNR (sRGB)Video Frame Interpolation/LPIPSZero-Shot Action Recognition/Top-1 AccuracyZero-Shot Action Recognition/Top-5 accuracyZero-Shot Learning/Accuracy

Related Benchmarks

UCF101 (finetuned)/Action Recognition/3-fold AccuracyUCF101 (finetuned)/Action Recognition/PretrainUCF101 (finetuned)/Activity Recognition/3-fold AccuracyUCF101 (finetuned)/Activity Recognition/PretrainUCF101-24/Action Detection/Frame-mAP 0.5UCF101-24/Action Detection/Video-mAP 0.1UCF101-24/Action Detection/Video-mAP 0.2UCF101-24/Action Detection/Video-mAP 0.5UCF101-24/Action Localization/mAP@0.2UCF101-24/Open Vocabulary Action Detection/val mAPUCF101-24/Temporal Action Localization/mAP@0.2UCF101-24/Video/mAP@0.2UCF101-24/Weakly-supervised Temporal Action Localization/mAP@0.2UCF101-24/Zero-Shot Learning/mAP@0.2UCF101-MiTv2/Action Recognition/AUROCUCF101-MiTv2/Activity Recognition/AUROC

Statistics

Papers
1,863
Benchmarks
38

Links

Homepage

Tasks

3D Action RecognitionAction ClassificationAction DetectionAction LocalizationAction RecognitionAction Recognition In VideosActivity RecognitionEarly Action PredictionFew Shot Action RecognitionFew-Shot LearningFew-Shot Learning - 4 shotsHuman Activity RecognitionImage ClusteringMeta-LearningOpen Set Action RecognitionPrompt EngineeringSelf-Supervised Action RecognitionSelf-Supervised Action Recognition LinearSelf-supervised Video RetrievalSkeleton Based Action RecognitionTemporal Action LocalizationText-to-Video GenerationTransductive Zero-Shot ClassificationVideoVideo Frame InterpolationVideo GenerationZero-Shot Action RecognitionZero-Shot Learning