arXiv subjects

Di Xie

Publications and source records attributed to Di Xie.

57 records · Page 4Linked to original sources

arXiv2017

Skeleton-based Action Recognition with Convolutional Neural Networks

Current state-of-the-art approaches to skeleton-based action recognition are mostly based on recurrent neural networks (RNN). In this paper, we propose a novel convolutional neural networks (CNN) based framework for both action classification and detection. Raw skeleton coordinates as well as skeleton motion are fed directly into CNN for label prediction. A novel skeleton transformer module is designed to rearrange and select important skeleton joints automatically. With a simple 7-layer network, we obtain 89.3% accuracy on validation set of the NTU RGB+D dataset. For action detection in untrimmed videos, we develop a window proposal network to extract temporal segment proposals, which are further classified within the same network. On the recent PKU-MMD dataset, we achieve 93.7% mAP, surpassing the baseline by a large margin.

cs.CV↗

arXiv2017

All You Need is Beyond a Good Init: Exploring Better Solution for Training Extremely Deep Convolutional Neural Networks with Orthonormality and Modulation

Deep neural network is difficult to train and this predicament becomes worse as the depth increases. The essence of this problem exists in the magnitude of backpropagated errors that will result in gradient vanishing or exploding phenomenon. We show that a variant of regularizer which utilizes orthonormality among different filter banks can alleviate this problem. Moreover, we design a backward error modulation mechanism based on the quasi-isometry assumption between two consecutive parametric layers. Equipped with these two ingredients, we propose several novel optimization solutions that can be utilized for training a specific-structured (repetitively triple modules of Conv-BNReLU) extremely deep convolutional neural network (CNN) WITHOUT any shortcuts/ identity mappings from scratch. Experiments show that our proposed solutions can achieve distinct improvements for a 44-layer and a 110-layer plain networks on both the CIFAR-10 and ImageNet datasets. Moreover, we can successfully train plain CNNs to match the performance of the residual counterparts. Besides, we propose new principles for designing network structure from the insights evoked by orthonormality. Combined with residual structure, we achieve comparative performance on the ImageNet dataset.

cs.CV↗

arXiv2016

Mixed context networks for semantic segmentation

Semantic segmentation is challenging as it requires both object-level information and pixel-level accuracy. Recently, FCN-based systems gained great improvement in this area. Unlike classification networks, combining features of different layers plays an important role in these dense prediction models, as these features contains information of different levels. A number of models have been proposed to show how to use these features. However, what is the best architecture to make use of features of different layers is still a question. In this paper, we propose a module, called mixed context network, and show that our presented system outperforms most existing semantic segmentation systems by making use of this module.

cs.CV↗