Browsing Journal Articles by Title

UTSePress Research/Manakin Repository

Search UTSePress Research


Advanced Search

Browse

My Account

Browsing Journal Articles by Title

Sort by: Order: Results:

  • Cheng, Joseph; Qiao, Mu; Bian, Wei; Tao, Dacheng (Elsevier Science Bv, 2011)
    In this paper, we propose a new algorithm for partitioning human posture represented by 3D point clouds sampled from the surface of human body. The algorithm is formed as a constrained extension of the recently developed ...
  • Gao, Yue; Wang, Meng; Tao, Dacheng; Ji, Rongrong; Dai, Qh (IEEE-Inst Electrical Electronics Engineers Inc, 2012)
    View-based 3-D object retrieval and recognition has become popular in practice, e.g., in computer aided design. It is difficult to precisely estimate the distance between two objects represented by multiple views. Thus, ...
  • Robertson, Toni; Kan, Ni Min; Sadler, Kirsten; Hagen, Penny (AAIS ACS, 2006)
  • Moulton, Bruce; Forrest, Yvonne (Blackwell Publ Ltd, 2005)
    This article presents findings from a study of control operators that raise concerns about safety-critical knowledge, culture and training. It is argued that the adoption of automated control systems can hinder the transfer ...
  • Robinson, Catherine; Searby, Rose (UTSePress, 2006)
    This research project set out to identify the need for crisis accommodation of single homeless women in Western Sydney. It was hoped that this need would be identified through records of requests for assistance by homeless ...
  • Peng, Yu; Xu, Min; Ni, Zefeng; Jin, Jesse Sheng; Luo, Suhuai (Springer, 2012)
    Accurate pedestrian counting are challenging in real-world due to occlusions, pedestrians? overlays or camera view sensitive. In this paper, we propose an accurate and robust pedestrian detection and counting system to ...
  • Chen, Pu; Li, Jianchun; Wong, Limsoon; Kuwahara, H; Huang, J; Gao, Xiaoshan (Wiley-Blackwell, 2013)
    Hot spot residues of proteins are fundamental interface residues that help proteins perform their functions. Detecting hot spots by experimental methods is costly and time-consuming. Sequential and structural information ...
  • Martincic, Anita; Dovey, Kenneth (Inderscience Publishers, 2011)
    The paper outlines an action research project conducted within an Australian public sector organisation with the purpose of changing a key internal business process. Despite the significant challenges incurred by using a ...
  • Vidal Calleja, Teresa; Sanfeliu, A; Andrade-Cetto, J (IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 2010)
    A method for evaluating, at video rate, the quality of actions for a single camera while mapping unknown indoor environments is presented. The strategy maximizes mutual information between measurements and states to help ...
  • Kumar, Madhu; Sankaran, Shankar (Springer, 2006)
    This paper analyses the actions of Mahabharat from the point of view of action science. From the point of view of action science, the source of the problem of Mahabharat is the undiscussable issue of who should be the ...
  • Zhu, Xingquan; Fu, Yifan; Elmagarmid, Ahmed (IEEE, 2013)
    Active learning (AL) traditionally relies on some instance-based utility measures (such as uncertainty) to assess individual instances and label the ones with the maximum values for training. In this paper, we argue that ...
  • Tian, Xinmei; Tao, Dacheng; Hua, Xian-Sheng; Wu, Xiuqing (IEEE-Inst Electrical Electronics Engineers Inc, 2010)
    Image search reranking methods usually fail to capture the user's intention when the query term is ambiguous. Therefore, reranking with user interactions, or active reranking, is highly demanded to effectively improve the ...
  • Cao, Longbing; Zhao, Yanchang; Zhang, Chengqi; Zhang, Huaifeng (World Scientific Publ Co Pte Ltd, 2008)
    Activity data accumulated in real life, such as terrorist activities and governmental customer contacts, present special structural and semantic complexities. Activity data may lead to or be associated with significant ...
  • Ou, Yuming; Cao, Longbing; Zhang, Chengqi (IEEE, 2009)
    Many real-life applications often involve multiple sequences, which are coupled with each other. It is unreasonable to either study the multiple coupled sequences separately or simply merge them into one sequence, because ...
  • Liu, Xinwang; Yin, Jp; Wang, L; Liu, Lq; Liu, J; Hou, Cp; Zhang, Jian (IEEE-Inst Electrical Electronics Engineers Inc, 2013)
    Learning an optimal kernel plays a pivotal role in kernel-based methods. Recently, an approach called optimal neighborhood kernel learning (ONKL) has been proposed, showing promising classification performance. It assumes ...
  • Yu, Jeffrey; Tao, Dacheng; Wang, Meng (IEEE-Inst Electrical Electronics Engineers Inc, 2012)
    Recent years have witnessed a surge of interest in graph-based transductive image classification. Existing simple graph-based transductive learning methods only model the pairwise relationship of images, however, and they ...
  • Yang, Tao; Kecman, Vojislav (Blackwell Publishing Ltd, 2009)
    It is not unique that only a few samples from medical studies are available for knowledge discovery. Hence, a suitable classifier for the small data set learning problem is very interesting in medical work. In this paper, ...
  • Bakshi, Aishwarya; Talaei-Khoei, Amir; Ray, Pradeep (Elsevier, 2013)
    This paper presents a systematic literature review to gain an understanding of adaptive policies. This review looks at papers published between 1970 and 2011 and examines the background and trends in this area. Based on ...
  • Henderson-Sellers, Brian; Haire, Brendan; Lowe, David (ProQuest Science Journals, 2001)
  • Ying, Mingsheng (Elsevier Science Bv, 2002)
    We propose a new model of probabilistic processes. In this model, a probability is assigned to the action of a prefix and a probability distribution is assigned to the components of a parallel composition. In addition, the ...