Documentation Mocap Database HDM05

By Meinard Müller, Tido Röder, Michael Clausen, B. Eberhardt, Björn Krüger, A. Weber. 2007

498 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Evaluation & Benchmarks

Citations in the corpus

Co-Occurrence Feature Learning for Skeleton Based Action Recognition Using Regularized Deep LSTM Networks (2016, methodology): “2012), HDM05 dataset (Müller et al. 2007), and CMU dataset (CMU 2003) whose groundtruth was labeled by ourselves.”
Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “6M [92] MoCap color movies 2014 Northwestern-UCLA Multiview [106] Kinect v1 RGB + depth human daily activities 2014 ORGBD [107] Kinect v1 RGB + depth human-object interactions 2014 SPHERE [108] Kinect depth human daily activities 2014 TST Fall Detection [109] Kinect v2 + IMU depth human daily activi”
RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, neutral): “Motion Capture Database HDM05 [24] (http://resources.mpi-inf.mpg.de/HDM05/) was captured by an optical marker-based technology with the frequency of 120 Hz, which contains 2337 sequences for 130 actions performed by 5 non-professional actors, and 31 joints in each frame.”
Deep Learning on Lie Groups for Skeleton-Based Action Recognition (2016, background): “HDM05 dataset [30] .”
G3D: A gaming action dataset and real time action recognition evaluation framework (2012, background): “The MPI HDM05 Motion Capture Database [13] database does include locomotion on the spot but not a full range of gaming actions.”
WALKING WALKing walking: Action Recognition from Action Echoes (2017, methodology): “For the HDM05, ConvESN-MSMC took 157s to produce all of the 200-”
Spatio-Temporal Graph Convolution for Skeleton Based Action Recognition (2018, methodology): “2013), HDM05 (Müller et al. 2007), Large Scale Combined dataset (Zhang et al.”
Skeletal Quads: Human Action Recognition Using Joint Quadruples (2014, methodology): “Note that deposit floor means “deposit an item on the floor with knees bent” [9].”
Adaptive RNN Tree for Large-Scale Human Action Recognition (2017, methodology): “Further, we create a large-scale SAR dataset that has 140 action classes, which we term as 3D-SAR-140, by aggregating and processing 10 existing smaller-scale datasets [3, 5, 6, 12, 14, 15, 16, 25, 27, 28].”
The KIT Motion-Language Dataset (2016, unknown): “HDM05 7 provides a data set of 1457 human whole-body motion clips with a total run length of around 50 minutes, which have been created by segmenting a continuous motion sequence demonstrated by ﬁve different nonprofes-sional actors.”
Real-Time Gesture Recognition from Depth Data through Key Poses Learning and Decision Forests (2012, methodology): “One way to obtain skeletons is by using a marker based strategy as in the Motion Capture (MoCap) models [16], [17], where a set of markers is attached to the human body at specific points that are tracked during motion.”
MotionBERT: A Unified Perspective on Learning Human Motion Representations (2022, methodology): “AMASS [76] integrates most existing marker-based Mocap datasets [1,2,5,11,15,18,34,37,52,69,72,77,84,97,110,111] and parameterizes them with a common representation.”
LCR-Net: Localization-Classification-Regression for Human Pose (2017, methodology): “To cover a wider set of poses, we merge several MoCap datasets available on the internet, such as Pose Prior [1] and HDM05 [18], and observed a 13% reduction in the matching error, i.”
Ongoing human action recognition with motion capture (2014, methodology): “We have tested our system on the HDM dataset of actions from [26].”
LCR-Net++: Multi-Person 2D and 3D Pose Detection in Natural Images (2018, methodology): “To cover a wider set of poses, we merged several MoCap datasets available on the internet, such as Pose Prior [24] and HDM05 [70], and observed a 13 percent reduction in the matching error, i.”
Action recognition on motion capture data using a dynemes and forward differences representation (2014, methodology): “Figure 1: Walk, hop and run movement sequences from the HDM05 database [3].”
AMASS: Archive of Motion Capture As Surface Shapes (2019, methodology): “A sampling of shapes and poses from a few datasets in AMASS is shown, from left to right: CMU [9], MPI-HDM05 [30, 31], MPIPose Limits [3], KIT [27], BMLrub [42], TCD [21] and ACCAD [34] datasets.”