11 April 2019 in IEEE Transactions on Circuits and Systems for Video Technology
Microsoft’s Kinect sensors are receiving an increasing amount of interest by security researchers since they are cost-effective and can provide both visual and depth modality data at the same time. Unfortunately, depth or RGB modalities are unavailable in training or testing procedures in some realistic scenarios. Therefore, we explore a new problem focusing on arbitrary absence of modality, which is completely different from conventional action recognition. The new problem in action recognition aims to deal with cross modality data (e.g., RGB training and depth testing data), “missing” modality data (e.g., RGB training and RGB-D test data), and single modality data (e.g., RGB/depth in both phases). Accordingly, our method aims to borrow some information (e.g., correlation between two modalities) from the well-established RGB-D dataset and apply it to the existing dataset to recover some latent information to improve the performance of recognition. For instance, a crossmodality regularizer is used to preserve the correlation of RGB and depth modalities. The “missing” knowledge is considered as latent information, which is recovered by low-rank learning in our model. In the real world, the target data is usually sparsely labeled or completely unlabeled, however, we could exploit the pseudo labels of the target as prior knowledge for “supervised” learning in target domain. Accordingly, we propose a semisupervised model for transfer learning. Experiments on three widely used RGB-D action datasets show that the our method performs better than that of the state-of-art transfer learning methods in most cases in terms of accuracy and time efficiency.
8 December 2017 in IEEE Transactions on Image Processing
Spatially or temporally corrupted action videos are impractical for recognition via vision or learning models. It usually happens when streaming data are captured from unintended moving cameras, which bring occlusion or camera vibration and accordingly result in arbitrary loss of spatiotemporal information. In reality, it is intractable to deal with both spatial and temporal corruptions at the same time. In this paper, we propose a Coupled Stacked Denoising Tensor Auto-Encoder (CSDTAE) model, which approaches this corruption problem in a divide-and-conquer fashion by jointing both the spatial and temporal schemes together. In particular, each scheme is a Stacked Denoising Tensor Auto-Encoder (SDTAE) designed to handle either spatial or temporal corruption, respectively. SDTAE is composed of several blocks, each of which is a Denoising Tensor Auto-Encoder (DTAE). Therefore, CSDTAE is designed based on several DTAE building blocks to solve the spatiotemporal corruption problem simultaneously. In one DTAE, the video features are represented as a high-order tensor to preserve the spatiotemporal structure of data, where the temporal and spatial information are processed separately in different hidden layers via tensor unfolding. In summary, DTAE explores the spatial and temporal structure of the tensor representation, and SDTAE handles different corrupted ratios progressively to extract more discriminative features. CSDTAE couples temporal and spatial corruptions of the same data through a thorough step-by-step procedures based on Canonical Correlation Analysis (CCA), which integrates the two sub-problems into one problem. The key point is solving spatiotemporal corruption in one model by considering them as noises in either spatial and temporal direction. Extensive experiments on three action datasets demonstrate the effectiveness of our model, especially when large volumes of corruption in the video.
16 December 2011 in IEEE Signal Processing Letters
This letter addresses the problem of analyzing spatio-temporal patterns for action recognition. In this letter we organize the whole training set in a single tensor, with each mode indicating one factor which influences the result of recognition, e.g., various view points. A novel method is proposed for tensor decomposition by discriminant analysis of multiscale features which represent the motion details on different scales. In addition, the nearest neighbor classifier (NNC) is employed for action classification. Experiments on the self-manufactured action database under ideal conditions showed that the proposed method was better than state-of-the-art methods under various view angles in terms of accuracy. Experiments on the commonly used KTH database also showed that the proposed method had low time complexity and was robust against changing view points.