DeepAI AI Chat
Log In Sign Up

Temporal Pyramid Network for Action Recognition

by   Ceyuan Yang, et al.
SenseTime Corporation
The Chinese University of Hong Kong

Visual tempo characterizes the dynamics and the temporal scale of an action. Modeling such visual tempos of different actions facilitates their recognition. Previous works often capture the visual tempo through sampling raw videos at multiple rates and constructing an input-level frame pyramid, which usually requires a costly multi-branch network to handle. In this work we propose a generic Temporal Pyramid Network (TPN) at the feature-level, which can be flexibly integrated into 2D or 3D backbone networks in a plug-and-play manner. Two essential components of TPN, the source of features and the fusion of features, form a feature hierarchy for the backbone so that it can capture action instances at various tempos. TPN also shows consistent improvements over other challenging baselines on several action recognition datasets. Specifically, when equipped with TPN, the 3D ResNet-50 with dense sampling obtains a 2 also reveals that TPN gains most of its improvements on action classes that have large variances in their visual tempos, validating the effectiveness of TPN.


page 1

page 3


Slow-Fast Visual Tempo Learning for Video-based Action Recognition

Action visual tempo characterizes the dynamics and the temporal scale of...

Action Recognition with Image Based CNN Features

Most of human actions consist of complex temporal compositions of more s...

CTM: Collaborative Temporal Modeling for Action Recognition

With the rapid development of digital multimedia, video understanding ha...

Temporal Extension of Scale Pyramid and Spatial Pyramid Matching for Action Recognition

Historically, researchers in the field have spent a great deal of effort...

DIR-AS: Decoupling Individual Identification and Temporal Reasoning for Action Segmentation

Fully supervised action segmentation works on frame-wise action recognit...

Feature sampling and partitioning for visual vocabulary generation on large action classification datasets

The recent trend in action recognition is towards larger datasets, an in...

YOWOv2: A Stronger yet Efficient Multi-level Detection Framework for Real-time Spatio-temporal Action Detection

Designing a real-time framework for the spatio-temporal action detection...

Code Repositories


[CVPR 2020] Temporal Pyramid Network for Action Recognition

view repo


CVPR2020 TPN with Paddlepaddle

view repo