Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification
arXiv:1711.09550
Abstract
Recently, substantial research effort has focused on how to apply CNNs or RNNs to better extract temporal patterns from videos, so as to improve the accuracy of video classification. In this paper, however, we show that temporal information, especially longer-term patterns, may not be necessary to achieve competitive results on common video classification datasets. We investigate the potential of a purely attention based local feature integration. Accounting for the characteristics of such features in video classification, we propose a local feature integration framework based on attention clusters, and introduce a shifting operation to capture more diverse signals. We carefully analyze and compare the effect of different attention mechanisms, cluster sizes, and the use of the shifting operation, and also investigate the combination of attention clusters for multimodal integration. We demonstrate the effectiveness of our framework on three real-world video classification datasets. Our model achieves competitive results across all of these. In particular, on the large-scale Kinetics dataset, our framework obtains an excellent single model accuracy of 79.4% in terms of the top-1 and 94.0% in terms of the top-5 accuracy on the validation set. The attention clusters are the backbone of our winner solution at ActivityNet Kinetics Challenge 2017. Code and models will be released soon.
The backbone of the winner solution at ActivityNet Kinetics Challenge 2017
References in corpus (9)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Two-Stream Convolutional Networks for Action Recognition in Videos
- Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors
- Multiple Object Recognition with Visual Attention
- Convolutional Two-Stream Network Fusion for Video Action Recognition
- Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
- Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks
- Revisiting the Effectiveness of Off-the-shelf Temporal Modeling Approaches for Large-scale Video Classification
- Real-time Action Recognition with Enhanced Motion Vector CNNs