Exploring Stronger Feature for Temporal Action Localization
share
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