Software
Datasets
HowToVQA69M datasetlarge-scale video question answering training dataset ICCV 2021 |
iVQA datasetinstructional video question answering benchmark ICCV 2021 |
||
ObMan Datasetsynthetically rendered hand-object images CVPR 2019 |
CrossTask DatasetCVPR 2019 |
||
UNREL Datasetunusual relation dataset ICCV 2017 |
SURREAL Datasetsynthetically rendered person videos CVPR 2017 |
||
THUMOS Datasetchallenges for large-scale action recognition CVIU 2017 |
Charades Datasetvideos of human activities at home environment ECCV 2016 |
||
Inria 3DMovie Dataset v2CVPR 2016 |
PF-WILLOW & PF-PASCAL Datasetsimage annotations for semantic correspondence CVPR 2016 |
||
Thin-slicing for PoseCVPR 2016 |
Tokyo Time Machine DatasetCVPR 2016 |
||
Instruction Videos DatasetCVPR 2016 |
HollywoodHeads DatasetICCV 2015 |
||
24/7 Place RecognitionCVPR 2015 |
Time-lapse videos for long-term observation of peoplecommon human-object interactions ECCV 2012 |
||
Time-lapse sequences of indoor scenessingle-view 3D scene understanding ECCV 2012 |
Annotated video clips for spatio-temporal video segmentationCVPR 2011 |
||
Willow Actionshuman action classification in still images BMVC 2010 |
Annotated movie data of face tracksface tracks from six movies ECCV 2010 |