Latent structured models for human pose estimation

By Catalin Ionescu, Fuxin Li, Cristian Sminchisescu. 2011

293 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

3D Human Pose Estimation in Video With Temporal Convolutions and Semi-Supervised Training (2018, unknown): “6M [20, 19] and HumanEva-I [47].”
Synthesizing Training Images for Boosting Human 3D Pose Estimation (2016, background): “However, we found that the performance of their CNN drops significantly when tested on other datasets, which indicates a strong overfit on the Human3.”
Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments (2014, methodology): “motion capture in natural environments[37], [6], [38], [7].”
Spatio-temporal Matching for Human Detection in Video (2014, background): “[7] reconstructed 3D human pose by inferring over multiple human localization hypotheses on images.”
HP-GAN: Probabilistic 3D Human Motion Prediction via GAN (2017, background): “6M[15, 14] dataset, which is one of the largest available datasets derived from motion capture (MoCap) data.”
Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation (2016, unknown): “Discriminative methods aim at predicting 3D pose directly from the input data, may it be single images [28, 29, 37, 38, 39, 46, 52, 55, 64, 74], depth images [23, 50, 59], or short image sequences [65].”
Semantic Graph Convolutional Networks for 3D Human Pose Regression (2019, unknown): “Later approaches either exploited nearest neighbors to refine the results of pose inference [18, 25] or extracted hand-crafted features [1, 23, 47] for later regression.”
Robust Optimization for Deep Regression (2015, background): “It has been extensively studied from the single-and multi-view perspective, where the standard ways to tackle the problem are based on part-based models [2, 4, 11, 32, 37, 46] and holistic approaches [8, 12, 28, 33].”
Geodesic Finite Mixture Models (2014, background): “6M Dataset [14, 15] which has many subjects performing different activities.”
3D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Information (2016, methodology): “Similar to the 2D case, early stage of 3D human pose estimation is also based on the low-level features such as local shape context [16] or segmentation results [17].”
MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video (2022, background): “[0] Hip [1] R Hip [2] R Knee [3] R Foot [4] L Hip [5] L Knee [6] L Foot [7] Spine [8] Thorax [9] Neck [10] Head [11] L Shoulder [12] L Elbow [13] L Wrist [14] R Shoulder [15] R Elbow [16] R Wrist”
Iterated Second-Order Label Sensitive Pooling for 3D Human Pose Estimation (2014, background): “Discriminative regression methods[1, 31, 28, 20, 17] focus on prediction from image descriptors, but depend on the existence of a sufficiently large and diverse training set, which until recently has not been available.”
3D Human pose estimation: A review of the literature and analysis of covariates (2016, unknown): “6M dataset [143, 152] or the KTH Multiview Football Dataset II [144]).”
Learning from Synthetic Humans (2017, background): “6M dataset [16, 17] provides ground truth for 2D and 3D human poses.”
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,”