Detecting People Using Mutually Consistent Poselet Activations

By Lubomir D. Bourdev, Subhransu Maji, Thomas Brox, Jitendra Malik. 2010

416 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

Learning Non-maximum Suppression (2017, neutral): “Several other clustering algorithms have been explored for the task of NMS without showing consistent gains: mean-shift clustering [6, 35], agglomerative clustering [2], affinity propagation clustering [17], and heuristic variants [25].”
Hypercolumns for object segmentation and fine-grained localization (2014, positive): “We use keypoint annotations collected by [5].”
Simultaneous Detection and Segmentation (2014, background): “e object detections from the deformable parts model [13] to segment the image, pasting gure-ground masks and reasoning about their relative depth ordering. Arbelaez et al. [2] use poselet detections [4] as features to score region candidates, in addition to appearance-based cues. Ladicky et al. [22]”
Learning to See by Moving (2015, methodology): “The coordinates of the keypoints are provided in the image coordinate system [5].”
Ensemble of exemplar-SVMs for object detection and beyond (2011, methodology): “For this, we present results on a set of tasks including segmentation, qualitative-geometry estimation, 3D model transfer, and related object priming.”
Category-specific object reconstruction from a single image (2014, methodology): “We use the publicly available ground truth class-specific keypoints [9] and object segmentations [19].”
Single Image 3D Interpreter Network (2016, methodology): “Method Poselets [6] Consensus [4] Exemplar [26] Mdshift [37] 3D-INN Human”
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.”
Iterative Instance Segmentation (2015, background): “[1] paste figureground masks for poselet detections [4].”
Viewpoints and keypoints (2014, methodology): “[4] and use ground truth and jittered boxes as training examples.”
A Hierarchical Pose-Based Approach to Complex Action Understanding Using Dictionaries of Actionlets and Motion Poselets (2016, methodology): “We refer to the components of this dictionary as motion poselets [2, 26].”
segDeepM: Exploiting segmentation and context in deep neural networks for object detection (2015, methodology): “In [1], object segmentations are found by aligning the masks obtained from Poselets [1, 17].”
AttentionNet: Aggregating Weak Directions for Accurate Object Detection (2015, methodology): “10 [2] H3D 46.9 N/A Szegedy et al .’”
Strong Appearance and Expressive Spatial Models for Human Pose Estimation (2013, background): “Similarly, state-of-the-art approaches to people detection [3] build on a large collection of pose speciﬁc poselet detectors.”
Beyond Physical Connections: Tree Models in Human Pose Estimation (2013, background): “[9] proposed the idea of poselets as the building blocks for human recognition, which refers to combined parts that are distinctive in training images.”
Articulated part-based model for joint object detection and pose estimation (2011, methodology): “5(a,b) shows that our object detection performance is slightly better than [3] (which achieves the best performance on PASCAL 2010 - human category) on poselet dataset [4] but signiﬁcantly out-performs [3] on [15], respectively.”
Structured Feature Learning for Pose Estimation (2016, background): “Researchers have done pose estimation at different levels: holistic (full body) [28] level, poselet (combination of multiple body joints) level [3, 31, 25, 19] and part (body joint) level [35, 11].”