Multimodal Deep Autoencoder for Human Pose Recovery
By Chao-qun Hong, Jun Yu, Jian Wan, Dacheng Tao, Meng Wang. 2015
553 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
- Luc Van Gool
- Pascal Fua
- Mathieu Salzmann
- Jitendra Malik
- Andrew Zisserman
- Vincent Lepetit
- Cordelia Schmid
- Xiaogang Wang
Citations in the corpus
- A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines (2018, background): “The authors of [146] aim to perform multimodal fusion by means of deep AEs, specifically proposing a Multimodal Deep Autoencoder (MDA).”
- SpatialFlow: Bridging All Tasks for Panoptic Segmentation (2019, background): “These methods have dramatically improved the state-of-the-art in many vision tasks, including image recognition[23], [25], [26], [27], [28], [29], [30], image retrieval [31], [32], metric learning [33], [34], [35], object detection [36], [37], [19], image segmentation [38], [39], [4], human pose est”
- Deep Multimodal Representation Learning: A Survey (2019, background): “[108], which learns a mapping from one modality to another based on the features learned from autoencoders.”
- Deep multi-view learning methods: A review (2021, background): “Multi-view Auto-encoder Auto-encoder (AE) is a variation of neural network and has obtained promising results in virous applications, 100 such as data retrieval [35], human pose recovery [55] and disease analysis [56].”
- A survey of deep neural network architectures and their applications (2017, background): “learning models, ideal results have been obtained for video -based human pose recovery [62].”
- Multi-view low-rank sparse subspace clustering (2017, background): “In [37] low-rank representation matrix is learned on each view separately and learned representation matrices are concatenated to a matrix from which a unified graph affinity matrix is obtained.”
- 3D Human pose estimation: A review of the literature and analysis of covariates (2016, methodology): “2015 Hong [101] Yes A multimodal deep autoencoder is used to fuse multiple”
- Structured Prediction of 3D Human Pose with Deep Neural Networks (2016, methodology): “In particular, [10] uses auto-encoders to learn a shared representation for 2D silhouettes and 3D poses.”