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 visual activities 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.