Related papers: ARN-LSTM: A Multi-Stream Fusion Model for Skeleton…

Spatiotemporal modeling has evolved beyond simple time series analysis to become fundamental in structural time series analysis. While current research extensively employs graph neural networks (GNNs) for spatial feature extraction with…

This paper contributes to the challenge of skeleton-based human action recognition in videos. The key step is to develop a generic network architecture to extract discriminative features for the spatio-temporal skeleton data. In this paper,…

Human motion prediction aims to generate future motions based on the observed human motions. Witnessing the success of Recurrent Neural Networks (RNN) in modeling the sequential data, recent works utilize RNN to model human-skeleton motion…

Effective spatiotemporal feature representation is crucial to the video-based action recognition task. Focusing on discriminate spatiotemporal feature learning, we propose Information Fused Temporal Transformation Network (IF-TTN) for…

Skeleton-based action recognition (SAR) has achieved impressive progress with transformer architectures. However, existing methods often rely on complex module compositions and heavy designs, leading to increased parameter counts, high…

Recent applications of Convolutional Neural Networks (ConvNets) for human action recognition in videos have proposed different solutions for incorporating the appearance and motion information. We study a number of ways of fusing ConvNet…

Skeleton-based gesture recognition methods have achieved high success using Graph Convolutional Network (GCN). In addition, context-dependent adaptive topology as a neighborhood vertex information and attention mechanism leverages a model…

In the last years, the computer vision research community has studied on how to model temporal dynamics in videos to employ 3D human action recognition. To that end, two main baseline approaches have been researched: (i) Recurrent Neural…

We propose a novel multi-modal and multi-task architecture for simultaneous low level gesture and surgical task classification in Robot Assisted Surgery (RAS) videos.Our end-to-end architecture is based on the principles of a long…

In skeleton-based human action recognition, temporal pooling is a critical step for capturing spatiotemporal relationship of joint dynamics. Conventional pooling methods overlook the preservation of motion information and treat each frame…

Sign language is commonly used by deaf or mute people to communicate but requires extensive effort to master. It is usually performed with the fast yet delicate movement of hand gestures, body posture, and even facial expressions. Current…

In this paper, we introduce Coarse-Fine Networks, a two-stream architecture which benefits from different abstractions of temporal resolution to learn better video representations for long-term motion. Traditional Video models process…

Human activity recognition (HAR) in ubiquitous computing has been beginning to incorporate attention into the context of deep neural networks (DNNs), in which the rich sensing data from multimodal sensors such as accelerometer and gyroscope…

We propose a new architecture for the learning of predictive spatio-temporal motion models from data alone. Our approach, dubbed the Dropout Autoencoder LSTM, is capable of synthesizing natural looking motion sequences over long time…

In action recognition, although the combination of spatio-temporal videos and skeleton features can improve the recognition performance, a separate model and balancing feature representation for cross-modal data are required. To solve these…

This paper presents a 2D skeleton-based action segmentation method with applications in fine-grained human activity recognition. In contrast with state-of-the-art methods which directly take sequences of 3D skeleton coordinates as inputs…

Skeleton-based human action recognition (HAR) has achieved remarkable progress with graph-based architectures. However, most existing methods remain body-centric, focusing on large-scale motions while neglecting subtle hand articulations…

Anticipating the future actions of a human is a widely studied problem in robotics that requires spatio-temporal reasoning. In this work we propose a deep learning approach for anticipation in sensory-rich robotics applications. We…

Skeleton-based human action recognition has recently drawn increasing attentions with the availability of large-scale skeleton datasets. The most crucial factors for this task lie in two aspects: the intra-frame representation for joint…

Skeleton-based action recognition has attracted research attentions in recent years. One common drawback in currently popular skeleton-based human action recognition methods is that the sparse skeleton information alone is not sufficient to…