Complex Sequential Understanding through the Awareness of Spatial and Temporal Concepts

Abstract

Understanding sequential information is a fundamental task for artificial intelligence. Current neural networks attempt to learn spatial and temporal information as a whole, limited their abilities to represent large scale spatial representations over long-range sequences. Here, we introduce a new modeling strategy called Semi-Coupled Structure (SCS), which consists of deep neural networks that decouple the complex spatial and temporal concepts learning. Semi-Coupled Structure can learn to implicitly separate input information into independent parts and process these parts respectively. Experiments demonstrate that a Semi-Coupled Structure can successfully annotate the outline of an object in images sequentially and perform video action recognition. For sequence-to-sequence problems, a Semi-Coupled Structure can predict future meteorological radar echo images based on observed images. Taken together, our results demonstrate that a Semi-Coupled Structure has the capacity to improve the performance of LSTM-like models on large scale sequential tasks.

15 pages, 5 figures, 8 tables

References in corpus (4)

• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
• An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data
• Beyond Short Snippets: Deep Networks for Video Classification

Cited by in corpus (7)

• HOI Analysis: Integrating and Decomposing Human-Object Interaction
• Muti-view Mouse Social Behaviour Recognition with Deep Graphical Model
• HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation
• ASAP-Net: Attention and Structure Aware Point Cloud Sequence Segmentation
• SDMTL: Semi-Decoupled Multi-grained Trajectory Learning for 3D human motion prediction
• PGT: A Progressive Method for Training Models on Long Videos
• Learning Multiscale Correlations for Human Motion Prediction