Visualizing Semantic Structures of Sequential Data by Learning Temporal Dependencies
This work addresses the challenge of interpreting semantic flows in sequential data for video analysis, but it appears incremental as it builds on graph convolutional methods without claiming major breakthroughs.
The paper tackles the problem of capturing variable-length semantic dependencies in sequential data, specifically videos, by proposing a Temporal Dependency Network (TDN) that visualizes these structures, and demonstrates its effectiveness on the Youtube-8M dataset.
While conventional methods for sequential learning focus on interaction between consecutive inputs, we suggest a new method which captures composite semantic flows with variable-length dependencies. In addition, the semantic structures within given sequential data can be interpreted by visualizing temporal dependencies learned from the method. The proposed method, called Temporal Dependency Network (TDN), represents a video as a temporal graph whose node represents a frame of the video and whose edge represents the temporal dependency between two frames of a variable distance. The temporal dependency structure of semantic is discovered by learning parameterized kernels of graph convolutional methods. We evaluate the proposed method on the large-scale video dataset, Youtube-8M. By visualizing the temporal dependency structures as experimental results, we show that the suggested method can find the temporal dependency structures of video semantic.