Low-Rank Tensor Learning with Discriminant Analysis for Action Classification and Image Recovery

By Chengcheng Jia, Guoqiang Zhong, Yun Raymond Fu. 2014

35 citations recorded by the source corpus.

Tensor completion is an important topic in the area of image processing and computer vision research, which is generally built on extraction of the intrinsic structure of the tensor data. Drawing on this fact, action classification, relying heavily on the extracted features of high-dimensional tensors, may indeed benefit from tensor completion techniques. In this paper, we propose a low-rank tensor completion method for action classification, as well as image recovery. Since there may exist distortion and corruption in the tensor representations of video sequences, we project the tensors into a subspace, which contains the invariant structure of the tensors. In order to integrate useful supervisory information for classification, we adopt a discriminant analysis criterion to learn the projection matrices. The resulting multi-variate optimization problem can be effectively solved using the augmented Lagrange multiplier (ALM) algorithm. Experiments demonstrate that our method results with better accuracy compared with some other state-of-the-art low-rank tensor representation learning approaches on the MSR Hand Gesture 3D database and the MSR Action 3D database. By denoising the Multi-PIE face database, our experimental setup testifies the proposed method can also be employed to recover images.

Subfields: Computational Mathematics, Computational Mechanics, 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 Computational Mathematics

1. Tae-Kyun Kim
2. Zhiyuan Shi
3. Yun Raymond Fu
4. Chengcheng Jia

In Computational Mechanics

1. Tae-Kyun Kim
2. Zhiyuan Shi
3. Yun Raymond Fu
4. Chengcheng Jia
5. Liang Wang

In Computer Vision and Pattern Recognition

1. Yun Raymond Fu
2. Liang Wang
3. Tae-Kyun Kim
4. Zhiyuan Shi
5. G. Wang
6. Jun Liu
7. Chengcheng Jia
8. Yong Du

Citations in the corpus

• Learning and Refining of Privileged Information-Based RNNs for Action Recognition from Depth Sequences (2017, methodology): “Our model takes advantage of the PI-based learning process, which allows to distinguish the subtle motions from depth maps [21].”
• Skeleton based action recognition with convolutional neural network (2015, background): “Based on those coordinates, effective and efficient approaches for action recognition have been developed recently [5, 19, 26].”
• Low-Rank Tensor Subspace Learning for RGB-D Action Recognition (2016, methodology): “…Low-Rank Tensor Subspace Learning (LRTS) The main procedure is detailed in the Algorithm 1, which is different from our previous method [27] and E. Discussion 1) Distinct From Previous Work: In [27], we use Fisher discriminant criteria to integrate the global discriminant information in the model.”