Large-Scale Video Classification with Convolutional Neural Networks

Citations Over TimeTop 1% of 2014 papers

Abstract

Convolutional Neural Networks (CNNs) have been established as a powerful class of models for image recognition problems. Encouraged by these results, we provide an extensive empirical evaluation of CNNs on large-scale video classification using a new dataset of 1 million YouTube videos belonging to 487 classes. We study multiple approaches for extending the connectivity of a CNN in time domain to take advantage of local spatio-temporal information and suggest a multiresolution, foveated architecture as a promising way of speeding up the training. Our best spatio-temporal networks display significant performance improvements compared to strong feature-based baselines (55.3% to 63.9%), but only a surprisingly modest improvement compared to single-frame models (59.3% to 60.9%). We further study the generalization performance of our best model by retraining the top layers on the UCF-101 Action Recognition dataset and observe significant performance improvements compared to the UCF-101 baseline model (63.3% up from 43.9%).

Related Papers

• → Advancements in Image Classification using Convolutional Neural Network(2018)385 cited
• → A GPU-based convolutional neural network approach for image classification(2017)25 cited
• → Research on Clothing Image Classification by Convolutional Neural Networks(2018)5 cited
• → Comparison of different convolutional neural network techniques for car models classification(2023)1 cited
• → Tree-Based Convolutional Neural Networks for Image Classification(2023)