Complex Sequential Understanding through the Awareness of Spatial and Temporal Concepts

TL;DR

This paper introduces the Semi-Coupled Structure, a neural network approach that separately learns spatial and temporal concepts, enhancing performance on large-scale sequential tasks like image annotation, video recognition, and radar prediction.

Contribution

The paper proposes a novel Semi-Coupled Structure that explicitly decouples spatial and temporal learning in neural networks, improving their ability to handle complex sequential data.

Findings

Successfully annotates object outlines in images sequentially

Performs effective video action recognition

Predicts future radar images from observed sequences

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.