Long Short-Term Transformer for Online Action Detection

Mingze Xu, Yuanjun Xiong, Hao Chen, Xinyu Li, Wei Xia, Zhuowen Tu, Stefano Soatto

Keywords: Online Action Detection, Action and Behavior Recognition, Video Analysis, Transformers, Recurrent Neural Networks

Abstract: We present Long Short-term TRansformer (LSTR), a temporal modeling algorithm for online action detection, which employs a long- and short-term memory mechanism to model prolonged sequence data. It consists of an LSTR encoder that dynamically leverages coarse-scale historical information from an extended temporal window (e.g., 2048 frames spanning of up to 8 minutes), together with an LSTR decoder that focuses on a short time window (e.g., 32 frames spanning 8 seconds) to model the fine-scale characteristics of the data. Compared to prior work, LSTR provides an effective and efficient method to model long videos with fewer heuristics, which is validated by extensive empirical analysis. LSTR achieves state-of-the-art performance on three standard online action detection benchmarks, THUMOS'14, TVSeries, and HACS Segment. Code has been made available at: https://xumingze0308.github.io/projects/lstr.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

TL;DR: We propose a new Transformer based architecture for online action detection by employing a long- and short-term memory mechanism that models prolonged sequence data.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2107.03377/code)