Machine Intelligence Prospective for Large Scale Video based Visual Activities Analysis

Machine learning has been proved highly active research to solve data analytics problems by last few decades. Real life video analysis comprises highly unstructured and complex data which challenge the storage capacity and modern machine intelligence. Due to large scale of data continuously developed by several sensors in every domain of social media, traditional machine learning approaches fail to deal with huge amount of data. Social media analytics may have high range of activities like business, financial, research, medicine and entertainment. In this work, we focus on unstructured data of visualactivities social media in unconstraint environment. We discuss the issues of complex data sets like Hollywood2, ImageNet, HMBD and UCF as a big data prospective and introduce how deep learning techniques are efficient to resolve the detection and recognition issues. Recent developments of deep learning, Convolutional 3D, RCNN, LSTM, SSD, YOLO and its fastest versions, YOLO9000 have been discussed for solving highly massive data analytics problems. Deep learning is still in scope to resolve many issues like VGGNet16 outperforms to the higher layer network VGGNet19 and what if the perceptive area of the nodes at every layer does not keep fixed size. It has been concluded that this work produces a sounding challenge of unstructured and large scale training data of video analytics and frame out deep learning aspects to resolve the social media activity issues in unconstraint environment. This research leads highly resourceful scope for data science problems in various fields of study in which high performance computing is expected.

[1]  Shaogang Gong,et al.  Recognising action as clouds of space-time interest points , 2009, CVPR.

[2]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[3]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[4]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[5]  R. Manmatha,et al.  Formulating Action Recognition as a Ranking Problem , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[6]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Trevor Darrell,et al.  Long-term recurrent convolutional networks for visual recognition and description , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  David Silver,et al.  Deep Reinforcement Learning with Double Q-Learning , 2015, AAAI.

[9]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[11]  Marc'Aurelio Ranzato,et al.  Large Scale Distributed Deep Networks , 2012, NIPS.

[12]  Yuval Tassa,et al.  Continuous control with deep reinforcement learning , 2015, ICLR.

[13]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  John Langford,et al.  Learning Deep ResNet Blocks Sequentially using Boosting Theory , 2017, ICML.

[15]  Marc'Aurelio Ranzato,et al.  Building high-level features using large scale unsupervised learning , 2011, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[16]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[17]  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).

[18]  Tinne Tuytelaars,et al.  Modeling video evolution for action recognition , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Jitendra Malik,et al.  Region-Based Convolutional Networks for Accurate Object Detection and Segmentation , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Tao Wang,et al.  Deep learning with COTS HPC systems , 2013, ICML.

[21]  Peter Stone,et al.  Deep Reinforcement Learning in Parameterized Action Space , 2015, ICLR.

[22]  Ivan Laptev,et al.  On Space-Time Interest Points , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[23]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[24]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[25]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.