Spatially and Temporally Structured Global to Local Aggregation of Dynamic Depth Information for Action Recognition

By Yonghong Hou, Shuang Wang, Pichao Wang, Zhimin Gao, Wanqing Li. 2018

18 citations recorded by the source corpus.

This paper presents an effective yet simple video representation for RGB-D-based action recognition. It proposes to represent a depth map sequence into three pairs of structured dynamic images (DIs) at body, part, and joint levels, respectively, through hierarchical bidirectional rank pooling. Different from previous works that applied one convolutional neural network (ConvNet) for each part/joint separately, one pair of structured DIs is constructed from depth maps at each granularity level and serves as the input of a ConvNet. The structured DI not only preserves the spatial-temporal information but also enhances the structure information across both body parts/joints and different temporal scales. In additionally, it requires low computational cost and memory to construct. This new representation, referred to as Spatially and Temporally Structured Dynamic Depth Images, aggregates from global to fine-grained levels motion and structure information in a depth sequence, and enables us to fine-tune the existing ConvNet models trained on image data for classification of depth sequences, without a need for training the models afresh. The proposed representation is evaluated on six benchmark data sets, namely, MSRAction3D, G3D, MSRDailyActivity3D, SYSU 3D HOI, UTD-MHAD, and M2I data sets and achieves the state-of-the-art results on all six data sets.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Endocrinology, Diabetes and Metabolism

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Endocrinology, Diabetes and Metabolism

Citations in the corpus

RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, background): “Huang et al. (2016) proposed a weakly-supervised framework for action labeling in video (see Fig.”
Depth Pooling Based Large-Scale 3-D Action Recognition With Convolutional Neural Networks (2018, unknown): “[43] proposed the concept of structured images for depth based action recognition, but the proposed methods need the help of skeleton data to locate the position of human body, parts and joints.”