Better Appearance Models for Pictorial Structures

By Marcin Eichner, Vittorio Ferrari. 2009

251 citations recorded by the source corpus.

Subfields: Computational Mechanics, 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 Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Towards Accurate Multi-person Pose Estimation in the Wild (2017, neutral): “D human pose inference [3, 12, 37, 45, 11, 27, 32, 38, 18].”
DeepPose: Human Pose Estimation via Deep Neural Networks (2013, background): “Earlier attempts to achieve this were based on richer part detectors [19, 1, 4].”
Efficient object localization using Convolutional Networks (2014, methodology): “Following the seminal work of Felzenszwalb et al. [10] on ‘Deformable Part Models’ (DPM) for human-body-pose estimation, many algorithms have been proposed to improve on the DPM archiecture [2, 9, 23, 7].”
Articulated Human Detection with Flexible Mixtures of Parts (2013, neutral): “[53] 98.”
Towards Viewpoint Invariant 3D Human Pose Estimation (2016, background): “In contrast, discriminative methods directly identify individual body parts, labels, or positions and construct the skeleton in a bottom-up approach [51,52,14,54,15].”
Exploring the Spatial Hierarchy of Mixture Models for Human Pose Estimation (2012, methodology): “While several works [4,1] focus on designing better part detectors, in this work, we focus solely on the spatial relationships between parts obtained using the standard HoG features.”
Parsing Clothes in Unrestricted Images (2013, background): “The popular choice to obtain human body part configuration Z are human pose estimation algorithms [2, 6, 11, 18].”
A review on vision techniques applied to Human Behaviour Analysis for Ambient-Assisted Living (2012, background): “3—; similarly to what is described in [5, 14, 31, 33, 86, 101, 106]).”
Learning shape models for monocular human pose estimation from the Microsoft Xbox Kinect (2011, background): “This task has received much attention in the literature [1, 7, 9, 14] because of the many applications including high-level understanding of images and video and markerless motion capture.”
Weakly Supervised Learning of Interactions between Humans and Objects (2012, unknown): “After mapping detection windows from the part detectors to a common reference frame, detections of the same person result in similar windows.”
Articulated part-based model for joint object detection and pose estimation (2011, methodology): “On the other hand, most pose estimators [12, 20, 10, 5, 16, 15, 11] assume that either the object locations, the object scales, or both are predetermined by either a speciﬁc object detector, or given manually.”
Custom Pictorial Structures for Re-identification (2011, methodology): “In [6], a learning strategy estimates relations between body parts and a shared color-based appearance model is used to deal with occlusions.”
We Are Family: Joint Pose Estimation of Multiple Persons (2010, methodology): “[1, 3]; (2) remove the support of the estimated pose from the image, e.”
Adaptive pose priors for pictorial structures (2010, methodology): “This adds robustness to the non-uniform sampling of the example space when using a ﬁnite training set and to outliers which can hurt kernel regression estimates.”
Human Pose Estimation Using Body Parts Dependent Joint Regressors (2013, methodology): “, by learning better appearance [24, 9, 1] or shape models [42] of the body parts.”