State Key Laboratory of Management and Control of Complex Systems

Beijing, China

State Key Laboratory of Management and Control of Complex Systems

Beijing, China
SEARCH FILTERS
Time filter
Source Type

Zhou W.,State Key Laboratory of Management and Control of Complex Systems | Wang C.,State Key Laboratory of Management and Control of Complex Systems | Xiao B.,State Key Laboratory of Management and Control of Complex Systems | Zhang Z.,State Key Laboratory of Management and Control of Complex Systems
IET Computer Vision | Year: 2014

Pooling strategies, such as max pooling and sum pooling, have been widely used to obtain the global representations for action videos. However, these pooling strategies have several disadvantages. First, they are easily affected by unwanted background local features, the absence of discriminative local features and the times of actions periodically performed by actors. Second, most pooling strategies only use local features to build the global representation that captures little mid-level features for action representation. In this study, the authors propose a novel weighted pooling strategy based on actionlets representation for action recognition. The actionlets are defined as the movements of large bodies such as legs, arms and head, which capture rich mid-level features for action representation. Besides, the authors' method also incorporates the distribution information of actionlets into pooling procedure. Specifically, a pooling weight, which determines the importance of actionlet on the final video representation, is assigned to each actionlet. To learn the weight, they propose a novel discriminative learning algorithm to capture the discriminative information for pooling operation. They evaluate their weighted pooling on three datasets: KTH actions dataset, UCF sports dataset and Youtube actions dataset. Experimental results show the effectiveness of the proposed method. © The Institution of Engineering and Technology 2014.


Shi C.-Z.,State Key Laboratory of Management and Control of Complex Systems | Wang C.-H.,State Key Laboratory of Management and Control of Complex Systems | Xiao B.-H.,State Key Laboratory of Management and Control of Complex Systems | Gao S.,State Key Laboratory of Management and Control of Complex Systems | Hu J.-L.,State Key Laboratory of Management and Control of Complex Systems
IEEE Transactions on Circuits and Systems for Video Technology | Year: 2014

Scene text recognition has inspired great interests from the computer vision community in recent years. In this paper, we propose a novel scene text-recognition method integrating structure-guided character detection and linguistic knowledge. We use part-based tree structure to model each category of characters so as to detect and recognize characters simultaneously. Since the character models make use of both the local appearance and global structure informations, the detection results are more reliable. For word recognition, we combine the detection scores and language model into the posterior probability of character sequence from the Bayesian decision view. The final word-recognition result is obtained by maximizing the character sequence posterior probability via Viterbi algorithm. Experimental results on a range of challenging public data sets (ICDAR 2003, ICDAR 2011, SVT) demonstrate that the proposed method achieves state-of-The-art performance both for character detection and word recognition. © 1991-2012 IEEE.


Chen X.,State Key Laboratory of Management and Control of Complex Systems | Wang C.,State Key Laboratory of Management and Control of Complex Systems | Xiao B.,State Key Laboratory of Management and Control of Complex Systems | Cai X.,State Key Laboratory of Management and Control of Complex Systems
IET Computer Vision | Year: 2015

View variation is a major challenge in face recognition. In this study, the authors propose a novel cross-view face recognition method by seeking potential intermediate domains between the source and target views to model the connection of varying-views faces. Specifically, each intermediate domain is associated with a dictionary subspace. Learning proceeds in two phases. First, the authors discriminatively train a sub-dictionary for each subclass of data, which then compose a structured dictionary of powerful reconstructive and discriminative capability on the source data. Secondly, the authors gradually adapt the source domain dictionary to the target domain by incrementally reducing the reconstruction error on the target data, which forms a smooth transition path connecting the source and target domains. Instead of updating the structured dictionary integrally, the authors develop a refined sub-dictionarybased updating algorithm, which makes the intermediate dictionaries fit on the target data better and faster. Finally, the authors apply invariant sparse codes across the source, intermediate and target domains to render domain-shared representations, where the sample differences caused by view changes are reduced. Experiments on the CMU-PIE and Multi-PIE dataset demonstrate the effectiveness of the proposed method. © The Institution of Engineering and Technology 2015.


Zhang Z.,State Key Laboratory of Management and Control of Complex Systems | Wang C.,State Key Laboratory of Management and Control of Complex Systems | Xiao B.,State Key Laboratory of Management and Control of Complex Systems | Zhou W.,State Key Laboratory of Management and Control of Complex Systems | Liu S.,State Key Laboratory of Management and Control of Complex Systems
IEEE Signal Processing Letters | Year: 2012

Although traditional bag-of-words model has shown promising results for action recognition, it takes no consideration of the relationship among spatio-temporal points; furthermore, it also suffers serious quantization error. In this letter, we propose a novel coding strategy called context-constrained linear coding (CLC) to overcome these limitations. We first calculate the contextual distance between local descriptors and each codeword by considering the spatio-temporal contextual information. Then, linear coding using contextual distance is adopted to alleviate the quantization error. Our method is verified on two challenging databases (KTH and UCF sports), and the experimental results demonstrate that our method achieves better results than previous methods in action recognition. © 2012 IEEE.


Zhang Z.,State Key Laboratory of Management and Control of Complex Systems | Wang C.,State Key Laboratory of Management and Control of Complex Systems | Xiao B.,State Key Laboratory of Management and Control of Complex Systems | Zhou W.,State Key Laboratory of Management and Control of Complex Systems | Liu S.,State Key Laboratory of Management and Control of Complex Systems
IEEE Transactions on Information Forensics and Security | Year: 2013

Recently, attributes have been introduced as a kind of high-level semantic information to help improve the classification accuracy. Multitask learning is an effective methodology to achieve this goal, which shares low-level features between attributes and actions. Yet such methods neglect the constraints that attributes impose on classes, which may fail to constrain the semantic relationship between the attributes and actions. In this paper, we explicitly consider such attribute-action relationship for human action recognition, and correspondingly, we modify the multitask learning model by adding attribute regularization. In this way, the learned model not only shares the low-level features, but also gets regularized according to the semantic constrains. In addition, since attribute and class label contain different amounts of semantic information, we separately treat attribute classifiers and action classifiers in the framework of multitask learning for further performance improvement. Our method is verified on three challenging datasets (KTH, UIUC, and Olympic Sports), and the experimental results demonstrate that our method achieves better results than that of previous methods on human action recognition. © 2013 IEEE.

Loading State Key Laboratory of Management and Control of Complex Systems collaborators
Loading State Key Laboratory of Management and Control of Complex Systems collaborators