Learning hierarchical poselets for human parsing

By Yang Wang, Duan Tran, Zicheng Liao. 2011

176 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Human-Computer Interaction

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 Human-Computer Interaction

Citations in the corpus

Deformable part models are convolutional neural networks (2014, methodology): “Models with loopy graphical structures, such as Wang et al .’s hierarchical poselets model [33], require iterative, approximate inference algorithms that cannot be converted to equivalent ﬁxed-depth CNNs.”
Pose Machines: Articulated Pose Estimation via Inference Machines (2014, methodology): “Recent methods have also explored using part hierarchies [16,17] and condition the detection of smaller parts that model regions around anatomical joints on the localization of larger composite parts or poselets [11,10,18,19] that model limbs in canonical configurations and tend to be easier to dete”
Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments (2014, background): “annotations [33], [35] and extensions of the poselets with 2D annotations [36].”
Articulated part-based model for joint object detection and pose estimation (2011, background): “[ 21] propose a hierarchical poselet model for both detection and pose estimation.”
Deep Learning-based Human Pose Estimation: A Survey (2020, background): “and (2) full-body pose datasets including PASCAL Person Layout [244], Sport [245] and UIUC people [246].”
Multi-source Deep Learning for Human Pose Estimation (2014, methodology): “Existing approaches use log-linear models with pairwise potentials of these three information sources [49, 51, 39, 54, 53] to determine whether an estimated location is correct.”
MODEC: Multimodal Decomposable Models for Human Pose Estimation (2013, background): “The UIUC Sports dataset [21] has 1299 images but consists of a skewed distribution of canonical sports poses, e.”
Human Pose Estimation Using Body Parts Dependent Joint Regressors (2013, background): “Besides of independent part templates for body parts, also hierarchies of part templates have been proposed [33, 38, 35].”
Articulated people detection and pose estimation: Reshaping the future (2012, background): “With a few notable exceptions [2, 17, 31] the task of joint detection and pose estimation of strongly articulated people remains largely unaddressed.”
Object Detection Using Strongly-Supervised Deformable Part Models (2012, unknown): “Part-level supervision has been used for human pose estimation [10, 15, 23, 24] and object part localization [16].”
Articulated Pose Estimation Using Discriminative Armlet Classifiers (2013, background): “Wang et al. [25] use a hierarchy of poselets for human parsing.”
Poselet Conditioned Pictorial Structures (2013, methodology): “2 and wp is the weighting parameter estimated on the validation set.”
Single-Pedestrian Detection Aided by Multi-pedestrian Detection (2013, methodology): “Therefore, the other models like the tree model in [31], [73], [98], the loopy graph model in [64], [84], the complete graphmodel in [6] and the pictorial structures in [1], [31] can be used for both single- and two-pedestrian detection.”
Body Parts Dependent Joint Regressors for Human Pose Estimation in Still Images (2014, background): “This has been addressed by proposing richer structures that aim to resolve the weakness of a tree model by adding additional constraints between the limbs [10], [11], [12], [13] or using a fully connected graphical model [14], [15].”
2D Human Pose Estimation: New Benchmark and State of the Art Analysis (2014, background): “Existing benchmarks cover aspects of the human pose estimation task such as sport scenes [12, 21], frontal-facing people [8, 3, 17], people interacting with objects [23], pose estimation in group photos [5] and pose estimation of people performing synchronized activities [4].”
Incorporating Structural Alternatives and Sharing into Hierarchy for Multiclass Object Recognition and Detection (2013, methodology): “The detection accuracy is calculated as [23]: only the detection with the highest score on the image is considered.”
Urban tribes: Analyzing group photos from a social perspective (2012, background): “It is based on the detection of a type of automatically discovered person parts named poselets, the effectiveness of which has been demonstrated for person analysis in images, such as human parsing [17] or person description by recognizing semantic attributes such as hair style or clothing type [1].”
Towards Unified Human Parsing and Pose Estimation (2014, background): “Due to the large variance in viewpoint and body pose, most recent works utilize mixture of models at a certain level [24, 14].”
R-CNNs for Pose Estimation and Action Detection (2014, methodology): “[25] used a hierarchy of poselets for human parsing.”