PoseTrack: Joint Multi-person Pose Estimation and Tracking

Iqbal, Umar; Milan, Anton; Gall, Jüergen

doi:10.1109/cvpr.2017.495

Cited by 192 publications

(152 citation statements)

References 46 publications

Supporting

Mentioning

152

Contrasting

Order By: Relevance

“…Out-of-position (OOP) human pose detection is an important problem with regard to the safety of passengers in a car. While, there are very large public datasets for human pose estimation -such as the Pose Track [21] and MPII Pose [3] datasets, among others -these datasets are for generic pose estimation tasks, and neither they contain any in-vehicle poses as captured by a dashboard camera, nor are they annotated for pose anomalies. To this end, we collected about 104 videos, each 20-30 min long from the Internet (including Youtube, ShutterStock, and Hollywood road movies).…”

Section: Dash-cam-pose: Data Collectionmentioning

confidence: 99%

GODS: Generalized One-Class Discriminative Subspaces for Anomaly Detection

Wang

Cherian

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

101

View full text Add to dashboard Cite

One-class learning is the classic problem of fitting a model to data for which annotations are available only for a single class. In this paper, we propose a novel objective for one-class learning. Our key idea is to use a pair of orthonormal frames -as subspaces -to "sandwich" the labeled data via optimizing for two objectives jointly: i) minimize the distance between the origins of the two subspaces, and ii) to maximize the margin between the hyperplanes and the data, either subspace demanding the data to be in its positive and negative orthant respectively. Our proposed objective however leads to a non-convex optimization problem, to which we resort to Riemannian optimization schemes and derive an efficient conjugate gradient scheme on the Stiefel manifold.To study the effectiveness of our scheme, we propose a new dataset Dash-Cam-Pose, consisting of clips with skeleton poses of humans seated in a car, the task being to classify the clips as normal or abnormal; the latter is when any human pose is out-of-position with regard to say an airbag deployment. Our experiments on the proposed Dash-Cam-Pose dataset, as well as several other standard anomaly/novelty detection benchmarks demonstrate the benefits of our scheme, achieving state-of-the-art oneclass accuracy. 5 The data follows the formula f (x) = √ x * (x + sign(randn) * rand), where randn and rand are standard MATLAB functions.

show abstract

Section: Dash-cam-pose: Data Collectionmentioning

confidence: 99%

GODS: Generalized One-Class Discriminative Subspaces for Anomaly Detection

Wang

Cherian

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

101

View full text Add to dashboard Cite

show abstract

“…Recent datasets for pose estimation in time focus on more challenging, multi-person videos as e.g. [17,15], but are smaller in scale -in particular due to the challenging nature of the task. Regarding establishing dense correspondences between images and surface-based body models DensePose-COCO was introduced in [12], providing annotations for 50K images of humans appearing in the COCO dataset.…”

Section: Densepose-trackmentioning

confidence: 99%

Slim DensePose: Thrifty Learning From Sparse Annotations and Motion Cues

Neverova

Thewlis

Güler

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Figure 1: The goal of this work is to discover effective and cost-efficient data annotation strategies for the task of learning dense correspondences in the wild (DensePose). We significantly reduce the annotation effort by exploiting (a) sparse subsets of the DensePose labels augmented with cheaper kinds of annotations, such as object masks or keypoints, and (b) temporal information in videos to propagate ground truth and enforce dense spatio-temporal equivariance constraints. AbstractDensePose supersedes traditional landmark detectors by densely mapping image pixels to body surface coordinates. This power, however, comes at a greatly increased annotation time, as supervising the model requires to manually label hundreds of points per pose instance. In this work, we thus seek methods to significantly slim down the Dense-Pose annotations, proposing more efficient data collection strategies. In particular, we demonstrate that if annotations are collected in video frames, their efficacy can be multiplied for free by using motion cues. To explore this idea, we introduce DensePose-Track, a dataset of videos where selected frames are annotated in the traditional DensePose manner. Then, building on geometric properties of the DensePose mapping, we use the video dynamic to propagate ground-truth annotations in time as well as to learn from Siamese equivariance constraints. Having performed exhaustive empirical evaluation of various data annotation and learning strategies, we demonstrate that doing so can deliver significantly improved pose estimation results over strong baselines. However, despite what is suggested by some recent works, we show that merely synthesizing motion patterns by applying geometric transformations to isolated frames is significantly less effective, and that motion cues help much more when they are extracted from videos. * James Thewlis and Iasonas Kokkinos were with Facebook AI Research (FAIR) during this work.

show abstract

“…Several methods have been proposed to estimate and track human poses on videos [2], [4], [5], [12], [15], [16], [27]. These methods can be divided into two groups depending on whether the learned temporal information is used or not.…”

Section: Human Pose Estimation With Trackingmentioning

confidence: 99%

Pose estimator and tracker using temporal flow maps for limbs

Hwang

Lee

Park

et al. 2019

2019 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

For human pose estimation in videos, it is significant how to use temporal information between frames. In this paper, we propose temporal flow maps for limbs (TML) and a multi-stride method to estimate and track human poses. The proposed temporal flow maps are unit vectors describing the limbs' movements. We constructed a network to learn both spatial information and temporal information end-to-end. Spatial information such as joint heatmaps and part affinity fields is regressed in the spatial network part, and the TML is regressed in the temporal network part. We also propose a data augmentation method to learn various types of TML better. The proposed multi-stride method expands the data by randomly selecting two frames within a defined range. We demonstrate that the proposed method efficiently estimates and tracks human poses on the PoseTrack 2017 and 2018 datasets.

show abstract

PoseTrack: Joint Multi-person Pose Estimation and Tracking

Cited by 192 publications

References 46 publications

GODS: Generalized One-Class Discriminative Subspaces for Anomaly Detection

GODS: Generalized One-Class Discriminative Subspaces for Anomaly Detection

Slim DensePose: Thrifty Learning From Sparse Annotations and Motion Cues

Pose estimator and tracker using temporal flow maps for limbs

Contact Info

Product

Resources

About