Convolutional Neural Network (CNN) and GMM Supervectors in Video Concept Detection.

Journal Title: International Journal of Engineering and Science Invention - Year 2018, Vol 7, Issue 8

Abstract

Video concept detectionplays an important role in digital image processing. Video concept detectionis defined as detecting the concepts that are present in the videoshots. Concept canbeanything of users’ interest. Video concept detectionisassigning the labels to the input videoshots. For getting the accuratevideoshots, different types of techniques are used. The basic approach of concept detectionis to use classification algorithm. There are manydifferent CNN structures for video or image classification likeAlexNet, Overfeat, VGG, Network-in-network, GoogLeNet, ResNet. In thispaperwe propose to use CNN and SVM, to build Concept classifierswhichpredict the relevance between images or videoshots and a given concept. DeepConvolutional neural networks (CNN) are a special type of feed-forward networks. DCNN performverywell on visual recognition tasks. We are usingAlexnet architecture pre-trained on the ImageNETdataset on TRECVID dataset and using GMM supervectors corresponding to apply on different types of audio and visualfeatures.

Authors and Affiliations

Ritika D Sangale, Nita S Patil, Sudhir D Sawarkar

Keywords

Related Articles

Experimental Investigation on Behaviour of RC Slabs Under Static Load

The main objective of this investigation is to study the static behavior of RC slabs with different composite materials like steel and synthetic fibres, steel wire mesh, lathe scrap fiber, SBR latex. This includes the st...

Investigations on the Effect of Fouling Factor in the Air Side of Air Cooled Condenser

As the electrical power demand increases and water resources become more limited, fouling on the air side of Air Cooled Condensers (ACC) is a growing concern. ACC’s are widely used as a method to exhaust waste heat from...

F4-TCNQ Concentration Dependent Capacitance-Voltage (C-V) and Conductivity-Voltage (G/w-V) Characteristics of the Au/P3HT:F4-TCNQ/N-Si (MPS) Schottky Barrier Diodes

In this work, the electrical properties of Au/P3HT:F4-TCNQ/n-Si metal-polymer-semiconductor (MPS) Schottky barrier diodes (SBDs) with the F4-TCNQ concentration values of 0.5% and 2%were investigated by capacitance-voltag...

Design of Hybrid Dual Wide Band Antenna with Notch Band Characteristics

In this article, a novel design of microstripline fed dual band microstrip antenna (MSA) with notch band characteristics is presented. By etching a slot on the radiating patch and by truncating the ground plane the notch...

Screening for antimicrobial activity of some medicinal plants.

During present study the antibacterial activity of the petroleum ether extracts of Vitex negundo, Duranta repens, Piper nigrum and Acorus calamus were analysed. The antibacterial potential of these extracts were tested o...

Download PDF file
  • EP ID EP397999
  • DOI -
  • Views 103
  • Downloads 0

How To Cite

Ritika D Sangale, Nita S Patil, Sudhir D Sawarkar (2018). Convolutional Neural Network (CNN) and GMM Supervectors in Video Concept Detection.. International Journal of Engineering and Science Invention, 7(8), 69-75. https://www.europub.co.uk/articles/-A-397999