Temporal Reasoning Graph for Activity Recognition

doi:10.1109/TIP.2020.2985219

Return

Temporal Reasoning Graph for Activity Recognition

2020-01-01

Jingran Zhang

Shen Fumin (Fumin Shen) *

Xing Xu

申恒涛 (Heng Tao Shen)

DOI：10.1109/TIP.2020.2985219

Original

Save

View PDF

Abstract

En 中文

Despite great success has been achieved in activity analysis, it still has many challenges. Most existing works in activity recognition pay more attention to designing efficient architecture or video sampling strategy. However, due to the property of fine-grained action and long term structure in video, activity recognition is expected to reason temporal relation between video sequences. In this paper, we propose an efficient temporal reasoning graph (TRG) to simultaneously capture the appearance features and temporal relation between video sequences at multiple time scales. Specifically, we construct learnable temporal relation graphs to explore temporal relation on the multi-scale range. Additionally, to facilitate multi-scale temporal relation extraction, we design a multi-head temporal adjacent matrix to represent multi-kinds of temporal relations. Eventually, a multi-head temporal relation aggregator is proposed to extract the semantic meaning of those features convolving through the graphs. Extensive experiments are performed on widely-used large-scale datasets, such as Something-Something, Charades and Jester, and the results show that our model can achieve state-of-the-art performance. Further analysis shows that temporal relation reasoning with our TRG can extract discriminative features for activity recognition.

Keywords:

Feature extraction

Activity recognition

Convolution

Semantics

Computer architecture

Video sequences

temporal reasoning

graph convolution network

temporal graph construction

activity recognition

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.