【CVPR 2017】Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset

Paper 发表了文章 • 0 个评论 • 291 次浏览 • 2017-08-07 16:47 • 来自相关话题

 
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
 
arXiv: https://arxiv.org/abs/1705.07750
 
CVPR 2017
 
The paucity of videos in current action classification datasets (UCF-101 and HMDB-51) has made it difficult to identify good video architectures, as most methods obtain similar performance on existing small-scale benchmarks. This paper re-evaluates state-of-the-art architectures in light of the new Kinetics Human Action Video dataset. Kinetics has two orders of magnitude more data, with 400 human action classes and over 400 clips per class, and is collected from realistic, challenging YouTube videos. We provide an analysis on how current architectures fare on the task of action classification on this dataset and how much performance improves on the smaller benchmark datasets after pre-training on Kinetics.
We also introduce a new Two-Stream Inflated 3D ConvNet (I3D) that is based on 2D ConvNet inflation: filters and pooling kernels of very deep image classification ConvNets are expanded into 3D, making it possible to learn seamless spatio-temporal feature extractors from video while leveraging successful ImageNet architecture designs and even their parameters. We show that, after pre-training on Kinetics, I3D models considerably improve upon the state-of-the-art in action classification, reaching 80.7% on HMDB-51 and 98.0% on UCF-101.
  查看全部
 
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
 
arXiv: https://arxiv.org/abs/1705.07750
 
CVPR 2017
 
The paucity of videos in current action classification datasets (UCF-101 and HMDB-51) has made it difficult to identify good video architectures, as most methods obtain similar performance on existing small-scale benchmarks. This paper re-evaluates state-of-the-art architectures in light of the new Kinetics Human Action Video dataset. Kinetics has two orders of magnitude more data, with 400 human action classes and over 400 clips per class, and is collected from realistic, challenging YouTube videos. We provide an analysis on how current architectures fare on the task of action classification on this dataset and how much performance improves on the smaller benchmark datasets after pre-training on Kinetics.
We also introduce a new Two-Stream Inflated 3D ConvNet (I3D) that is based on 2D ConvNet inflation: filters and pooling kernels of very deep image classification ConvNets are expanded into 3D, making it possible to learn seamless spatio-temporal feature extractors from video while leveraging successful ImageNet architecture designs and even their parameters. We show that, after pre-training on Kinetics, I3D models considerably improve upon the state-of-the-art in action classification, reaching 80.7% on HMDB-51 and 98.0% on UCF-101.
 

【CVPR 2017】Multi-Context Attention for Human Pose Estimation

Paper 发表了文章 • 0 个评论 • 262 次浏览 • 2017-08-11 00:58 • 来自相关话题

 
Multi-Context Attention for Human Pose Estimation
 
Xiao Chu, Wei Yang, Wanli Ouyang, Cheng Ma, Alan L. Yuille, Xiaogang Wang
 
CVPR 2017
 
code: https://github.com/bearpaw/pose-attention
paper: https://arxiv.org/abs/1702.07432
 
In this paper, we propose to incorporate convolutional neural networks with a multi-context attention mechanism into an end-to-end framework for human pose estimation. We adopt stacked hourglass networks to generate attention maps from features at multiple resolutions with various semantics. The Conditional Random Field (CRF) is utilized to model the correlations among neighboring regions in the attention map. We further combine the holistic attention model, which focuses on the global consistency of the full human body, and the body part attention model, which focuses on the detailed description for different body parts. Hence our model has the ability to focus on different granularity from local salient regions to global semantic-consistent spaces. Additionally, we design novel Hourglass Residual Units (HRUs) to increase the receptive field of the network. These units are extensions of residual units with a side branch incorporating filters with larger receptive fields, hence features with various scales are learned and combined within the HRUs. The effectiveness of the proposed multi-context attention mechanism and the hourglass residual units is evaluated on two widely used human pose estimation benchmarks. Our approach outperforms all existing methods on both benchmarks over all the body parts.
  查看全部
 
Multi-Context Attention for Human Pose Estimation
 
Xiao Chu, Wei Yang, Wanli Ouyang, Cheng Ma, Alan L. Yuille, Xiaogang Wang
 
CVPR 2017
 
code: https://github.com/bearpaw/pose-attention
paper: https://arxiv.org/abs/1702.07432
 
In this paper, we propose to incorporate convolutional neural networks with a multi-context attention mechanism into an end-to-end framework for human pose estimation. We adopt stacked hourglass networks to generate attention maps from features at multiple resolutions with various semantics. The Conditional Random Field (CRF) is utilized to model the correlations among neighboring regions in the attention map. We further combine the holistic attention model, which focuses on the global consistency of the full human body, and the body part attention model, which focuses on the detailed description for different body parts. Hence our model has the ability to focus on different granularity from local salient regions to global semantic-consistent spaces. Additionally, we design novel Hourglass Residual Units (HRUs) to increase the receptive field of the network. These units are extensions of residual units with a side branch incorporating filters with larger receptive fields, hence features with various scales are learned and combined within the HRUs. The effectiveness of the proposed multi-context attention mechanism and the hourglass residual units is evaluated on two widely used human pose estimation benchmarks. Our approach outperforms all existing methods on both benchmarks over all the body parts.