Articulated pose estimation with tiny synthetic videos

By Dennis Park, Deva Ramanan. 2015

63 citations recorded by the source corpus.

Subfields: Aerospace 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 Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning from Simulated and Unsupervised Images through Adversarial Training (2016, background): “various prediction tasks, including gaze estimation [43], text detection and classification in RGB images [9, 15], font recognition [42], object detection [10, 27], hand pose estimation in depth images [38, 37], scene recognition in RGB-D [11], semantic segmentation of urban scenes [31], and human p”
Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection (2017, methodology): “At one end, we have datasets with images of single objects on random backgrounds [34–36, 47].”
Learning to Learn: Model Regression Networks for Easy Small Sample Learning (2016, background): “, unlabeled examples that do not belong to the concerned classes) for max-margin regularization [98], and 5) synthesize new virtual examples, either rendered explicitly with computer graphics techniques or created implicitly through compositional representations [67, 66, 71, 106, 21, 18].”
Delta-encoder: an effective sample synthesis method for few-shot object recognition (2018, methodology): “fine tuning from pre-trained models [25, 45, 46]; (3) applying domain transfer by borrowing examples from relevant categories [27] or using semantic vocabularies [2, 12]; (4) rendering synthetic examples [32, 7, 40]; (5) augmenting the training examples [23]; (6) example synthesis using Generative A”
MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior (2017, unknown): “, [9], [21], [22], [23], [24], [25], [26].”
MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild (2016, methodology): “Park and Ramanan [22] synthesized hypothetical poses for tracking purposes by applying geometric transformations to the first frame of a video sequence.”
Baby steps towards few-shot learning with multiple semantics (2019, methodology): “ning from pre-trained models [27, 52, 53]; (iii) applying domain transfer by borrowing examples from relevant categories [28] or using semantic vocabularies [3, 14]; (iv) rendering synthetic examples [9, 35, 48]; (v) augmenting the training examples using geometric and photometric transformations [2”
Learning to Sketch with Shortcut Cycle Consistency (2018, unknown): “These discriminative models have been applied to various tasks including gaze estimation [34], hand pose estimation [39, 37] and human pose estimation [29].”
Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images (2016, background): “Taking advantage of high quality graphics models for humanoids, rendered images of people from various viewpoints and body poses provide free data to train pose estimators [29, 34, 35] or person detectors [31].”
Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video (2015, background): “In this section, the models that describe the relationships between 3D poses, 2D poses and images are introduced.”
Lucid Data Dreaming for Object Tracking (2017, background): “The closest work to ours is [39], which also generates video-specific training data using the first frame annotations.”