MIC_TJ at TRECVID 2014

Our MIC_TJ team (Multimedia and Intelligent Computing Lab at Tongji University) participated in the Instance Search (INS) task and the Multimedia Event Detection (MED) task at TRECVID 2014 [1]. In this paper, we mainly present the framework and approaches used in our systems. For the INS task, we submit a speed up system with a GPU cluster, while in the MED task, we adopt the classic Bag-of-Words (BoW) framework with trajectory based features and audio feature. This paper presents the methods and findings for INS and MED task. For the INS task, we submitted 13 runs, and all of the training data are extracted from “BBC Eastenders”. Regarding the MED task, we submitted 1 run. The training data of this run is extracted from the datasets of 000Ex, 010Ex and 100Ex for different sub-tasks, respectively. The corresponding runs for INS and MED tasks are summarized below.

[1]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[2]  Yannis Avrithis,et al.  To Aggregate or Not to aggregate: Selective Match Kernels for Image Search , 2013, 2013 IEEE International Conference on Computer Vision.

[3]  Cordelia Schmid,et al.  Human Detection Using Oriented Histograms of Flow and Appearance , 2006, ECCV.

[4]  Shin'ichi Satoh,et al.  Query-Adaptive Asymmetrical Dissimilarities for Visual Object Retrieval , 2013, 2013 IEEE International Conference on Computer Vision.

[5]  Cordelia Schmid,et al.  Learning realistic human actions from movies , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Naga K. Govindaraju,et al.  Mars: A MapReduce Framework on graphics processors , 2008, 2008 International Conference on Parallel Architectures and Compilation Techniques (PACT).

[7]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[8]  Andrew Zisserman,et al.  Three things everyone should know to improve object retrieval , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Paul Over,et al.  Evaluation campaigns and TRECVid , 2006, MIR '06.

[10]  Georges Quénot,et al.  TRECVID 2015 - An Overview of the Goals, Tasks, Data, Evaluation Mechanisms and Metrics , 2011, TRECVID.

[11]  Cordelia Schmid,et al.  Scale & Affine Invariant Interest Point Detectors , 2004, International Journal of Computer Vision.

[12]  Sanjay Ghemawat,et al.  MapReduce: Simplified Data Processing on Large Clusters , 2004, OSDI.

[13]  Thomas Mensink,et al.  Improving the Fisher Kernel for Large-Scale Image Classification , 2010, ECCV.

[14]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[15]  Koen E. A. van de Sande,et al.  Evaluating Color Descriptors for Object and Scene Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.