Large-Scale Video Classification with Convolutional Neural Networks

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%).

PDF Abstract 2014 IEEE 2014 PDF 2014 IEEE 2014 Abstract

Datasets


Introduced in the Paper:

Sports-1M

Used in the Paper:

ImageNet UCF101

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Benchmark
Action Recognition Sports-1M DeepVideo’s Slow Fusion Clip Hit@1 41.9 # 5
Video hit@1 60.9 # 10
Video hit@5 80.2 # 10
Action Recognition UCF101 Slow Fusion + Finetune top 3 layers 3-fold Accuracy 65.4 # 76

Methods


No methods listed for this paper. Add relevant methods here