Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection
arXiv:1704.00616
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.
10 pages, 7 figures, ICCV 2017 submission
References in corpus (11)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors
- NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis
- Convolutional Two-Stream Network Fusion for Video Action Recognition
- Learning Spatiotemporal Features with 3D Convolutional Networks
- Long-term Temporal Convolutions for Action Recognition
- Learning to track for spatio-temporal action localization
- Finding Action Tubes
- Improved Dense Trajectory with Cross Streams