Exploring Stronger Feature for Temporal Action Localization

06/24/2021
by   Zhiwu Qing, et al.
0

Temporal action localization aims to localize starting and ending time with action category. Limited by GPU memory, mainstream methods pre-extract features for each video. Therefore, feature quality determines the upper bound of detection performance. In this technical report, we explored classic convolution-based backbones and the recent surge of transformer-based backbones. We found that the transformer-based methods can achieve better classification performance than convolution-based, but they cannot generate accuracy action proposals. In addition, extracting features with larger frame resolution to reduce the loss of spatial information can also effectively improve the performance of temporal action localization. Finally, we achieve 42.42 simple combination: BMN+TCANet, which is 1.87 multi-model ensemble. Finally, we achieve Rank 1st on the CVPR2021 HACS supervised Temporal Action Localization Challenge.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/13/2020

Temporal Fusion Network for Temporal Action Localization:Submission to ActivityNet Challenge 2020 (Task E)

This technical report analyzes a temporal action localization method we ...
research
08/26/2019

Deep Concept-wise Temporal Convolutional Networks for Action Localization

Existing action localization approaches adopt shallow temporal convoluti...
research
06/20/2021

Weakly-Supervised Temporal Action Localization Through Local-Global Background Modeling

Weakly-Supervised Temporal Action Localization (WS-TAL) task aims to rec...
research
11/16/2022

Exploring State Change Capture of Heterogeneous Backbones @ Ego4D Hands and Objects Challenge 2022

Capturing the state changes of interacting objects is a key technology f...
research
08/15/2021

Exploring Temporal Coherence for More General Video Face Forgery Detection

Although current face manipulation techniques achieve impressive perform...
research
05/25/2019

Exploring Feature Representation and Training strategies in Temporal Action Localization

Temporal action localization has recently attracted significant interest...
research
09/06/2022

Real-Time Cattle Interaction Recognition via Triple-stream Network

In stockbreeding of beef cattle, computer vision-based approaches have b...

Please sign up or login with your details

Forgot password? Click here to reset