Paper Details

Convolutional Neural Networks (CNNs) have acquired a strong reputation as an image recognition modelclass. As a result of these findings, we give a comprehensive empirical evaluation of CNNs for large-scale videoclassification using a fresh dataset of 1 million YouTube videos classified into 487 classes. We study a range of strategiesfor extending the time domain connectivity of a CNN in order to use local spatio-temporal information. We discuss thelimitations of current training methods and propose a multiresolution, foveated architecture as a possible technique ofexpediting training. When compared to strong feature-based networks, our top spatio-temporal networks outperformthem significantly. when compared to single-frame models (59.3 percent), however this is only a marginal improvement(55.3 percent to 63.9 percent). 60.9 percent in total). We delve deeper on the generalisation performance. Retrain our bestmodel's top layers on the UCF101 Action Recognition dataset and observe considerable performance improvements overthe UCF-101 baseline. prototype (63.3 percent up from 43.9 percent ).

Prathamesh Kshirsagar, Pooja Nagawade, “Large-scale Video Classification with Convolutional Neural Networks”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 8, Issue 11, pp. 1-5, November 2021.