Recently, paper titled “Complex sequential understanding through the awareness of spatial and temporal concepts” by Assoc.Prof. Lu Cewu ’s team has been published on Nature Machine Intelligence. It is the first time for Shanghai Jiao Tong University to have paper published on this journal. Meanwhile, codes in this paper and advanced research results of the team in recent two years have been rendered into a open source video understanding toolkit “AlphaVideo”, which has the highest precision rate regarding MOT and AVA single model.

Below is the abstract of the paper:

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.