Deep Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos

By Tomas Pfister, Karen Simonyan, James Charles, Andrew Zisserman. 2014

158 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Human-Computer Interaction

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

In Human-Computer Interaction

Citations in the corpus

2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning (2018, background): “The problem of human pose estimation has been intensively studied in the last years, from Pictorial Structures [2, 17, 37] to more recent CNN approaches [34, 25, 38, 20, 41, 54, 5, 51, 52, 36].”
Flowing ConvNets for Human Pose Estimation in Videos (2015, methodology): “Further improvements may be obtained by using additional inputs for the spatial ConvNet, for example multiple RGB frames [24] or optical flow [18] – although prior work has shown little benefit from this so far.”
Monocular human pose estimation: A survey of deep learning-based methods (2020, methodology): “(1) Direct prediction : (Krizhevsky et al., 2012), on video (Pﬁster et al., 2014) (2) Supervision improvement : transform heatmaps to joint coordinates (Luvizon et al., 2017; Nibali et al., 2018), recursive reﬁnement (Carreira et al., 2016), bone-based constraint (Sun et al., 2017) (3) Multi-task :…”
Learning Individual Styles of Conversational Gesture (2019, methodology): “This includes methods that use video transcripts as a weak source of supervision [3], as well as recent methods based on CNNs [37, 26] and RNNs [13].”
Robust Optimization for Deep Regression (2015, methodology): “Furthermore, temporal information has been included to the ConvNet training for more accurate 2D body pose estimation [31] and the use of ConvNets for 3D body pose estimation from a single image has also been demonstrated in [25].”
Convolutional Models for Joint Object Categorization and Pose Estimation (2015, background): “Although fundamentally different to object pose estimation, some research has explored using CNNs to recognize human pose (Toshev & Szegedy, 2013; LI et al., 2014; Pﬁster et al., 2014).”
Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image (2016, background): “So far CNNs have been successful at estimating 2D human pose [20,34,35,36,51] but not 3D pose and shape from one image.”
Human Pose Regression by Combining Indirect Part Detection and Contextual Information (2017, unknown): “One sequence of Block-A and Block-B is used to build one prediction block , which output is used as intermediate supervision during training.”
Large-Pose Face Alignment via CNN-Based Dense 3D Model Fitting (2016, background): “In [9], a subset of AFLW is selected to have a balanced distribution of yaw angles, including 3, 901 images for training and 1, 299 images for testing.”