Hierarchical Video Frame Sequence Representation with Deep Convolutional Graph Network
This work improves video classification accuracy for applications like large-scale video understanding, though it appears incremental as it builds on graph neural networks for a specific domain.
The paper tackles the problem of video classification by addressing the limitations of existing methods in capturing hierarchical relationships between frames, proposing a deep convolutional graph neural network (DCGN) that outperforms RNN-based benchmarks on the YouTube-8M dataset.
High accuracy video label prediction (classification) models are attributed to large scale data. These data could be frame feature sequences extracted by a pre-trained convolutional-neural-network, which promote the efficiency for creating models. Unsupervised solutions such as feature average pooling, as a simple label-independent parameter-free based method, has limited ability to represent the video. While the supervised methods, like RNN, can greatly improve the recognition accuracy. However, the video length is usually long, and there are hierarchical relationships between frames across events in the video, the performance of RNN based models are decreased. In this paper, we proposes a novel video classification method based on a deep convolutional graph neural network(DCGN). The proposed method utilize the characteristics of the hierarchical structure of the video, and performed multi-level feature extraction on the video frame sequence through the graph network, obtained a video representation re ecting the event semantics hierarchically. We test our model on YouTube-8M Large-Scale Video Understanding dataset, and the result outperforms RNN based benchmarks.