Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection
TL
TL;DR
This paper proposes a network architecture that computes and integrates the most important visual cues for action recognition: pose, motion, and the raw images and introduces a Markov chain model which adds cues successively.
Abstract
General human action recognition requires understanding of various visual cues. In this paper, we propose a network architecture that computes and integrates the most important visual cues for action recognition: pose, motion, and the raw images. For the integration, we introduce a Markov chain model which adds cues successively. The resulting approach is efficient and applicable to action classification as well as to spatial and temporal action localization. The two contributions clearly improve the performance over respective baselines. The overall approach achieves state-of-the-art action classification performance on HMDB51, J-HMDB and NTU RGB+D datasets. Moreover, it yields state-of-the-art spatio-temporal action localization results on UCF101 and J-HMDB.
References54 items
1
Multi-region Two-Stream R-CNN for Action Detection
2
Efficient deep models for monocular road segmentation
3
Efficient Two-Stream Motion and Appearance 3D CNNs for Video Classification
4
Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition
5