Poselets: Body part detectors trained using 3D human pose annotations

By Lubomir D. Bourdev, Jitendra Malik. 2009

1,119 citations recorded by the source corpus.

Subfields: Biomedical Engineering, 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 Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation (2013, background): “Instead, by isolating particular units in the network (as in Figure 3), we can see that the CNN learns a diverse set of rich features ranging from redblob detectors to semantically aligned poselet-like [4] units.”
You Only Look Once: Unified, Real-Time Object Detection (2015, neutral): “458 32 Poselets [2] 36.”
Deformable part models are convolutional neural networks (2014, background): “HOG-based detectors are currently used in a wide range of models and applications, especially those where region-based methods are ill-suited (poselets [1] being a prime example).”
CrossTransformers: spatially-aware few-shot transfer (2020, background): “Discriminative parts [5, 10, 22, 34, 42, 83] and visual words [74, 100] have a rich history, and have found applications in deformable-parts models [26], and classification [70, 100].”
Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation (2014, methodology): “Pishchulin [25] proposes a model that augments the DPM model with Poselet [4] priors.”
Stacked Hourglass Networks for Human Pose Estimation (2016, background): “Early work tackles such diﬃculties using robust image features and sophisticated structured prediction [1,2,3,4,5,6,7,8,9]: the former is used to produce local interpretations, whereas the latter is used to infer a globally consistent pose.”
Part-Based R-CNNs for Fine-Grained Category Detection (2014, methodology): “Starting with pictorial structures [18,19], and continuing through poselets [8] and related work, many methods have jointly localized a set of geometrically related parts.”
Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts (2014, methodology): “Similar to our method, [1, 23, 3] use additional annotations to provide supervision for a part-based model, while Poselets [2] and [14] use keypoints and masks annotations to cluster objects or their parts.”
Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “The approach utilizes the idea of poselets [85], which is widely applied for pose estimation from RGB images.”
Lifting Object Detection Datasets into 3D (2015, background): “When multiple 3D shapes corresponding to different instances of the same class are available, they can be used to build a morphable model for the 3D class, that can then generalize and be ﬁt to unseen instances of the class.”
Efficient object localization using Convolutional Networks (2014, methodology): “Pishchulin [18, 19] use Poselet priors and a DPM model [3] to capture spatial relationships of body-parts.”
PANDA: Pose Aligned Networks for Deep Attribute Modeling (2013, background): “Poselets [5, 3] are part detectors trained on positive examples clustered using keypoint annotations; they capture a salient pattern at a specific viewpoint and pose.”
Efficient Learning of Domain-invariant Image Representations (2013, background): “Learning adaptive representations for linear classifiers is particularly interesting as they are efficient and prevalent in vision applications, with fast linear SVMs forming the core of some of the most popular object detection methods [6, 7].”
Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks (2015, background): “This is a huge benefit compared to other part discovery approaches like poselets [6], which do not necessarily produce parts useful for discrimination of classes a priori.”
Articulated Human Detection with Flexible Mixtures of Parts (2013, background): “Most human pose datasets include images with labeled joint positions [9], [7], [3].”
Beyond frontal faces: Improving Person Recognition using multiple cues (2015, methodology): “A small and complementary subset of such salient patterns is automatically selected as described in [2].”
Part Detector Discovery in Deep Convolutional Neural Networks (2014, neutral): “Examples are the de-formable part model (DPM) [8], regionlets [15], and poselets [16].”