Search

Highlights • Our CMFL model jointly learns shared-specific features and action classifiers. • The proposed RSTPF features extract dynamic local patterns around each human joint. • The CMFL model enables the features to be optimized for classification. • The CMFL performs well even if one or two modalities are missing in the testing stage. • A max-margin framework is introduced to fuse skeleton, depth and RGB data. Abstract The emergence of cost-effective depth sensors opens up a new dimension for RGB-D based human action recognition. In this paper, we propose a collaborative multimodal feature learning (CMFL) model for human action recognition from RGB-D sequences. Specifically, we propose a robust spatio-temporal pyramid feature (RSTPF) to capture dynamic local patterns around each human joint. The proposed CMFL model fuses multimodal data (skeleton, depth and RGB), and learns action classifiers using the fused features. The original low-level feature matrices are factorized to learn shared features and modality-specific features under a supervised fashion. The shared features describe the common structures among the three modalities while the modality-specific features capture intrinsic information of each modality. We formulate shared-specific features mining and action classifiers learning in a unified max-margin framework, and solve the formulation using an iterative optimization algorithm. Experimental results on four action datasets demonstrate the efficacy of the proposed method. [ABSTRACT FROM AUTHOR]

Named entity recognition (NER) is a fundamental task in Chinese natural language processing (NLP) tasks. Recently, Chinese clinical NER has also attracted continuous research attention because it is an essential preparation for clinical data mining. The prevailing deep learning method for Chinese clinical NER is based on long short-term memory (LSTM) network. However, the recurrent structure of LSTM makes it difficult to utilize GPU parallelism which to some extent lowers the efficiency of models. Besides, when the sentence is long, LSTM can hardly capture global context information. To address these issues, we propose a novel and efficient model completely based on convolutional neural network (CNN) which can fully utilize GPU parallelism to improve model efficiency. Moreover, we construct multi-level CNN to capture short-term and long-term context information. We also design a simple attention mechanism to obtain global context information which is conductive to improving model performance in sequence labeling tasks. Besides, a data augmentation method is proposed to expand the data volume and try to explore more semantic information. Extensive experiments show that our model achieves competitive performance with higher efficiency compared with other remarkable clinical NER models. [ABSTRACT FROM AUTHOR]

Unsupervised person re-identification (ReID) is a task that aims to retrieve pedestrians across different cameras from unlabeled data. Existing methods rely on clustering to generate pseudo-labels, but they are inevitably noisy. Although pseudo-label refinement approaches have been presented, the essentiality of patch contours is ignored. The tendency analysis of retrieval between global and patch features has not been well investigated. In this paper, we propose a Patch-based Tendency Camera Multi-Constraint Learning (PTCML) model for unsupervised person ReID. First, to explore the tendentious retrieval of global and patch features, we design a Ranking Tendency Similarity (RTS) score by gauging the distribution discrepancy of distance changes. Second, based on RTS score, we propose a Tendency-based Mutual Complementation (TMC) loss to improve the quality of global and patch pseudo-labels. Third, to resist camera variations, we propose an Adaptive Camera Multi-Constraint (ACM) loss to optimize recognition results with camera distribution constraint and instance constraint simultaneously. Finally, numerous experiments on Market-1501 and MSMT17 demonstrate that our method can significantly surpass the state-of-the-art performance. • We design RTS score to mine the complementary tendency of increased distance between global and patch features. • Based on RTS score, TMC loss is proposed to refine the pseudo-labels. • We propose ACM loss to apply camera distribution and instance constraints simultaneously. [ABSTRACT FROM AUTHOR]

The two-stream convolutional network has been proved to be one milestone in the study of video-based action recognition. Lots of recent works modify internal structure of two-stream convolutional network directly and put top-level features into a 2D/3D convolution fusion module or a simpler one. However, these fusion methods cannot fully utilize features and the way fusing only top-level features lacks rich vital details. To tackle these issues, a novel network called Diverse Features Fusion Network (DFFN) is proposed. The fusion stream of DFFN contains two types of uniquely designed modules, the diverse compact bilinear fusion (DCBF) module and the channel-spatial attention (CSA) module, to distill and refine diverse compact spatiotemporal features. The DCBF modules use the diverse compact bilinear algorithm to fuse features extracted from multiple layers of the base network that are called diverse features in this paper. Further, the CSA module leverages channel attention and multi-size spatial attention to boost key information as well as restraining the noise of fusion features. We evaluate our three-stream network DFFN on three public challenging video action benchmarks: UCF101, HMDB51 and Something-Something V1. Experiment results indicate that our method achieves state-of-the-art performance. • Diverse compact bilinear fusion modules fuse spatial features and temporal features. • Diverse compact bilinear fusion modules fuse diverse features from different layers. • The multi-size spatial-channel attention module can adjust the attention of network. • The proposed network achieves state-of-the-art performance. [ABSTRACT FROM AUTHOR]

As a challenging task of video classification, action recognition has become a significant topic of computer vision community. The most popular methods based on two-stream architecture up to now are still simply fusing the prediction scores of each stream. In that case, the complementary characteristics of two streams cannot be fully utilized and the effect of shallower features is often overlooked. In addition, the equal treatment to features may weaken the role of the feature contributing significantly to the classification. Accordingly, a novel network called Multiple Depth-levels Features Fusion Enhanced Network (MDFFEN) is proposed. It improves on two aspects of two-stream architecture. In terms of the two-stream interaction mechanism, multiple depth-levels features fusion (MDFF) is formed to aggregate spatial–temporal features extracted from several sub-modules of original two streams by spatial–temporal features fusion (STFF). And with respect to further refining the spatiotemporal features, we propose a group-wise spatial-channel enhance (GSCE) module to highlight the meaningful regions and expressive channels automatically by priority assignment. The competitive results are achieved after we validate MDFFEN on three public challenging action recognition datasets, HDMB51, UCF101 and ChaLearn LAP IsoGD. • The proposed Two-Stream Features Fusion extracts diverse hybrid features. • The fusion of three types of features learns more discriminative information. • The Group-wise Spatial-Channel Enhance mechanism reduces interference information. • The proposed network achieves competitive performance. [ABSTRACT FROM AUTHOR]