PAN: Towards Fast Action Recognition via Learning Persistence of Appearance

8 Aug 2020Can ZhangYuexian ZouGuang ChenLei Gan

Efficiently modeling dynamic motion information in videos is crucial for action recognition task. Most state-of-the-art methods heavily rely on dense optical flow as motion representation... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Action Recognition Jester PAN ResNet101 (RGB only, no Flow) Val 97.4 # 1
Action Recognition Something-Something V1 PAN ResNet101 (RGB only, no Flow) Top 1 Accuracy 55.3 # 1
Top 5 Accuracy 82.8 # 2
Action Recognition Something-Something V2 PAN ResNet101 (RGB only, no Flow) Top-1 Accuracy 66.5 # 2
Top-5 Accuracy 90.6 # 3

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet