Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments

By Catalin Ionescu, Dragos Papava, Vlad Olaru, Cristian Sminchisescu. 2014

3,967 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Evaluation & Benchmarks, 3D Vision & Pose

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Evaluation & Benchmarks

In 3D Vision & Pose

Citations in the corpus

2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning (2018, methodology): “6M [21] for respectively 2D and 3D pose estimation, and on Penn Action [59] and NTU RGB+D [44] for 2D and 3D action recognition, respectively.”
Stochastic Variational Video Prediction (2017, background): “6M (Ionescu et al., 2014): Humans and animals are one of the most interesting sources of stochasticity in natural videos, which behave in complex ways as a consequence of unpredictable intentions.”
Structural-RNN: Deep Learning on Spatio-Temporal Graphs (2015, positive): “The applications include: (i) modeling human motion [14] from motion capture data [21]; (ii) human activity detection and anticipation [29, 31]; and (iii) maneuver anticipation from real-world driving data [22].”
Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning (2016, methodology): “Brabandere et al. (2016). Our PredNet model outperforms the model by Brabandere et al. (2016) by 29%. Details can be found in Appendix 5.2. Also in Appendix 5.2, we present results for the Human3.6M (Ionescu et al., 2014) dataset, as reported by Finn et al. (2016). Without re-optimizing hyperparamet”
Learning to Generate Long-term Future via Hierarchical Prediction (2017, methodology): “In this section, we present experiments on pixel-level video prediction of human actions on the Penn Action (Weiyu Zhang & Derpanis, 2013) and Human 3.6M datasets (Ionescu et al., 2014).”
Compositional Human Pose Regression (2017, methodology): “6M [20] is the largest 3D human pose benchmark.”
Convolutional Sequence to Sequence Model for Human Dynamics (2018, methodology): “6M dataset [9] and the CMU Motion Capture dataset (3).”
3D Human Pose Estimation from Monocular Images with Deep Convolutional Neural Network (2014, methodology): “3D Human Pose Estimation from Monocular Images with Deep CNN 5 positions with respect to root joint, which is a common formulation as in [12, 9, 11], we instead aim to predict the joint positions relative to their parents joints,”
Camera Distance-Aware Top-Down Approach for 3D Multi-Person Pose Estimation From a Single RGB Image (2019, methodology): “6M dataset [16] is the largest 3D single-person pose benchmark.”
Pictorial Human Spaces: How Well Do Humans Perceive a 3D Articulated Pose? (2013, background): “6M) dataset[9], and then reproduce the poses seen as well as they could.”