paper-with-me

홈 › Papers

A Circular Window-based Cascade Transformer for Online Action Detection

2022-08-30 · Shuqiang Cao, Weixin Luo, Bairui Wang, Wei zhang, Lin Ma

Online action detection aims at the accurate action prediction of the current frame based on long historical observations. Meanwhile, it demands real-time inference on online streaming videos. In this paper, we advocate a novel and efficient principle for online action detection. It merely updates the latest and oldest historical representations in one window but reuses the intermediate ones, which have been already computed. Based on this principle, we introduce a window-based cascade Transformer with a circular historical queue, where it conducts multi-stage attentions and cascade refinement on each window. We also explore the association between online action detection and its counterpart offline action segmentation as an auxiliary task. We find that such an extra supervision helps discriminative history clustering and acts as feature augmentation for better training the classifier and cascade refinement. Our proposed method achieves the state-of-the-art performances on three challenging datasets THUMOS'14, TVSeries, and HDD. Codes will be available after acceptance.

📄 PDF Abstract BibTeX arXiv:2208.14209

Code (0)

등록된 구현이 없습니다.

Tasks

Action DetectionAction SegmentationOnline Action Detection

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

von Mises Tapering: A Circular Data Windowing

2018-06-27

Continuous standard windowing is revisited and a new taper shape is introduced, which is based on the normal circular distribution by von Mises. Continuous-time windows are considered and their spectra obtained. A brief …

BolT: Fused Window Transformers for fMRI Time Series Analysis

2022-05-23 · Hasan Atakan Bedel, Irmak Şıvgın, Onat Dalmaz, Salman Ul Hassan Dar 외

Deep-learning models have enabled performance leaps in analysis of high-dimensional functional MRI (fMRI) data. Yet, many previous methods are suboptimally sensitive for contextual representations across diverse time sca…

Time SeriesTime Series Analysis

Von Mises Tapering: A New Circular Windowing

2021-10-30 · H. M. de Oliveira, R. J. Cintra

Discrete and continuous standard windowing are revisited and a a new taper is introduced, which is derived from the normal circular distribution by von Mises. Both the continuous-time and the discrete-time windows are co…

Cascaded Boundary Regression for Temporal Action Detection

2017-05-02 · Jiyang Gao, Zhenheng Yang, Ram Nevatia

Temporal action detection in long videos is an important problem. State-of-the-art methods address this problem by applying action classifiers on sliding windows. Although sliding windows may contain an identifiable port…

Action Detectionregression

Long Short-Term Transformer for Online Action Detection

2021-07-07 · NeurIPS 2021 12 · Mingze Xu, Yuanjun Xiong, Hao Chen, Xinyu Li 외

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 enc…

Action DetectionDecoderOnline Action DetectionPlaying the Game of 2048