Action Machine: Rethinking Action Recognition in Trimmed Videos

14 Dec 2018 Jiagang Zhu Wei Zou Liang Xu Yiming Hu Zheng Zhu Manyu Chang Jun-Jie Huang Guan Huang Dalong Du

Existing methods in video action recognition mostly do not distinguish human body from the environment and easily overfit the scenes and objects. In this work, we present a conceptually simple, general and high-performance framework for action recognition in trimmed videos, aiming at person-centric modeling... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Multimodal Activity Recognition MSR Daily Activity3D dataset Action Machine (RGB only) Accuracy 93.0 # 3
Action Recognition NTU RGB+D Action Machine (RGB only) Accuracy (CS) 94.3 # 2
Accuracy (CV) 97.2 # 2
Skeleton Based Action Recognition N-UCLA Action Machine Accuracy 92.3% # 2
Multimodal Activity Recognition UTD-MHAD Action Machine Accuracy (CS) 92.5 # 5
Action Recognition UTD-MHAD Action Machine (RGB only) Accuracy 92.5 # 1

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