Strike a pose: tracking people by finding stylized poses

By Deva Ramanan, D.A. Forsyth, Andrew Zisserman. 2005

377 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

Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields (2016, background): “Human 2D pose estimation—the problem of localizing anatomical keypoints or “parts”—has largely focused on finding body parts of individuals [8, 4, 3, 21, 33, 13, 25, 31, 6, 24].”
Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation (2014, background): “Some use a combination of local detectors and structural reasoning (see [27] for coarse tracking and [7] for person-dependent tracking).”
Learning Human Pose Estimation Features with Convolutional Networks (2013, background): “Some use a combination of local detectors and structural reasoning (see [36] for coarse tracking and [10] for person-dependent tracking).”
Pose Machines: Articulated Pose Estimation via Inference Machines (2014, methodology): “Pictorial structure models [1,2,3,4,5,6], express the human body as a tree-structured graphical model with kinematic priors that couple connected limbs.”
Learning hierarchical poselets for human parsing (2011, methodology): “This phenomenon was observed even prior to the work of poselet and was exploited to detect stylized human poses and build appearance models for kinematic tracking [17].”
Monocular Pedestrian Detection: Survey and Experiments (2009, neutral): “For this, either single [4], [26], [55], [70], [76] or multiple cues [32], [43], [50], [58], [65] are used.”
Tracking People by Learning Their Appearance (2007, methodology): “Another is a top-down approach that looks for an entire person in a single frame [36].”
HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion (2010, methodology): “For 2D human pose/motion e stimation, quantitative evaluation is more common and typically uses hand-labeled data [30, 58, 59].”
Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part Detectors (2007, positive): “In Ramanan et al. (2005) a human track is started only when a side view walking pose human is detected, and no termination strategy is mentioned.”
TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement (2023, background): “Semantic Keypoint Tracking is often represented as keypoints or landmarks [24, 42, 51, 56, 59, 65].”
Functional categorization of objects using real-time markerless motion capture (2011, background): “Another important point is that the use of key poses has already been suggested in the human tracking literature [9, 26].”
Progressive search space reduction for human pose estimation (2008, methodology): “[18], which provides the pictorial structure inference engine we use in stage 3, and on the Strike-a-pose work [19].”
Segmentation and Tracking of Multiple Humans in Crowded Environments (2008, methodology): “When the body pose of humans is desired and the video resolution is high enough, more complex models could be used, such as the articulated models in [54] and [34].”
Guiding model search using segmentation (2005, background): “Ioffe and Forsyth [4] use a simple rectangle detector to find candidates and assemble them by sampling based on kinematic constraints.”
Exploring the Trade-off Between Accuracy and Observational Latency in Action Recognition (2012, methodology): “Pose information has also been incorporated into tracking systems, such as Ramanan et al. (2005), which looks for specific poses while tracking users performing specific actions, such as walking.”