Procedural Human Action Videos - Ground Truth Optical Flow
Cesar Roberto de Souza and Adrien Gaidon and Yohann Cabon and Antonio Manuel Lopez Pena

phav_v2-flow (318 files)
flow_5007.tar.bz2 64.04MB
flow_5008.tar.bz2 68.19MB
flow_5009.tar.bz2 60.65MB
flow_5004.tar.bz2 63.54MB
flow_5005.tar.bz2 69.58MB
flow_5006.tar.bz2 59.56MB
flow_5001.tar.bz2 60.46MB
flow_5002.tar.bz2 60.33MB
flow_5003.tar.bz2 54.36MB
flow_4022.tar.bz2 44.63MB
flow_4023.tar.bz2 47.13MB
flow_5000.tar.bz2 56.85MB
flow_4019.tar.bz2 60.43MB
flow_4020.tar.bz2 65.23MB
flow_4021.tar.bz2 88.61MB
flow_4014.tar.bz2 60.90MB
flow_4015.tar.bz2 62.10MB
flow_4016.tar.bz2 57.53MB
flow_4017.tar.bz2 57.41MB
flow_4018.tar.bz2 59.87MB
flow_4011.tar.bz2 54.92MB
flow_4012.tar.bz2 60.43MB
flow_4013.tar.bz2 59.86MB
flow_4009.tar.bz2 60.88MB
flow_4010.tar.bz2 58.16MB
flow_4007.tar.bz2 57.31MB
flow_4008.tar.bz2 59.46MB
flow_3122.tar.bz2 58.52MB
flow_4005.tar.bz2 57.03MB
flow_4006.tar.bz2 61.26MB
flow_3119.tar.bz2 58.91MB
flow_3120.tar.bz2 66.07MB
flow_3121.tar.bz2 59.75MB
flow_3116.tar.bz2 59.64MB
flow_3117.tar.bz2 62.82MB
flow_3118.tar.bz2 67.47MB
flow_3113.tar.bz2 61.32MB
flow_3114.tar.bz2 61.86MB
flow_3115.tar.bz2 60.90MB
flow_3110.tar.bz2 62.16MB
flow_3111.tar.bz2 62.00MB
flow_3112.tar.bz2 60.41MB
flow_3107.tar.bz2 62.02MB
flow_3108.tar.bz2 65.33MB
flow_3109.tar.bz2 58.08MB
flow_3104.tar.bz2 69.70MB
flow_3105.tar.bz2 63.45MB
flow_3106.tar.bz2 55.87MB
flow_3100.tar.bz2 60.20MB
Too many files! Click here to view them all.
Type: Dataset
Tags: deep learning, action recognition, procedural generation, video classification

title= {Procedural Human Action Videos - Ground Truth Optical Flow},
keywords= {Action recognition, procedural generation, deep learning, video classification},
journal= {},
author= {Cesar Roberto de Souza and Adrien Gaidon and Yohann Cabon and Antonio Manuel Lopez Pena},
year= {2017},
url= {},
license= {Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)},
abstract= { Procedural Human Action Videos (PHAV)
 This torrent contains the Procedural Human Action Videos (PHAV) dataset. This 
 version of the dataset contains 39,982 videos that have been generated by a 
 computer. The dataset is made available under the Creative Commons BY-NC-SA
 (Attribution-NonCommercial-ShareAlike 4.0 International) license. This sub-
 directory contains the Horizontal and Vertical Optical Flow Ground Truth data
 modality of these videos.
 A human-readable version of the license terms is available at:
 The full license terms are available at:
 By using PHAV, you agree to abide to the terms of the Creative Commons BY-NC-SA
 license. If you do not agree with the terms of this license, please contact the
 dataset authors for other licensing options.
 For more information, including details about how to parse the different files
 included in this release, how to use them in your experiments, and how to cite
 the PHAV dataset in your academical paper, please visit:

superseded= {},
terms= {By using PHAV, you agree to abide to the terms of the Creative Commons BY-NC-SA license.}

Hosted by users:

Send Feedback