Robust human action recognition via long short-term memory

Grushin, Alexander; Monner, Derek; Reggia, James A.; Mishra, Ajay Kumar

doi:10.1109/ijcnn.2013.6706797

Cited by 67 publications

(29 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Recently, RNNs [7], especially Long Short-Term Memory (LSTM) [8] model, is being studied due to the computational capabilities for solving many challenging problems, such as intrusion detection [9], action recognition [10], [11], multilingual machine translation [12], multimodal translation between videos and robot control [13]. In these applications, learning the correlations between different time steps is an important step in achieving artificial intelligence.…”

Section: Introductionmentioning

confidence: 99%

Chemical substance classification using long short-term memory recurrent neural network

Zhang

Liu

Luo

et al. 2017

2017 IEEE 17th International Conference on Communication Technology (ICCT)

View full text Add to dashboard Cite

Abstract-This paper proposed a chemical substance detection method using the Long Short-Term Memory of Recurrent Neural Networks (LSTM-RNN). The chemical substance data was collected using a mass spectrometer which is a time-series data. The classification accuracy using the LSTM-RNN classifier is 96.84%, which is higher than 75.07% of the ordinary feed forward neural networks. The experimental results show that the LSTM-RNN can learn the properties of the chemical substance dataset and achieve a high detection accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%

Chemical substance classification using long short-term memory recurrent neural network

Zhang

Liu

Luo

et al. 2017

2017 IEEE 17th International Conference on Communication Technology (ICCT)

View full text Add to dashboard Cite

show abstract

“…Among the researches of human motion analysis, variant human body models (e.g., stick figure model [19], [20], cardboard model [21], 3D volumetric model [22]) play an important role. These models involve low-level processes on human body structures and cover the kinematic properties of the body, which build the foundation in solving different problems, including human motion tracking [23], [24], [25], action recognition [26], [27], [28], [29], and pose estimation [30], [31], [32]. Motivated by these successful applications based on well-defined human body models, in this paper, we pay attention to another more challenging task that attempts to generate consistent human motion sequences based on the correspondent skeleton and appearance information.…”

Section: Related Workmentioning

confidence: 99%

Skeleton-Aided Articulated Motion Generation

Yan

et al. 2017

Proceedings of the 25th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Abstract-This work makes the first attempt to generate articulated human motion sequence from a single image. On one hand, we utilize paired inputs including human skeleton information as motion embedding and a single human image as appearance reference, to generate novel motion frames based on the conditional GAN infrastructure. On the other hand, a triplet loss is employed to pursue appearance smoothness between consecutive frames. As the proposed framework is capable of jointly exploiting the image appearance space and articulated/kinematic motion space, it generates realistic articulated motion sequence, in contrast to most previous video generation methods which yield blurred motion effects. We test our model on two human action datasets including KTH and Human3.6M, and the proposed framework generates very promising results on both datasets.

show abstract

“…The application of temporal sequence modeling techniques, such as LSTM, to action recognition showed promising results in the past (Baccouche et al, 2010;Grushin et al, 2013). Earlier works did not try to explicitly model the temporal information, but aggregated the class predictions got from individual frame predictions.…”

Section: Temporal Deep Learning Models: Rnn and Lstmmentioning

confidence: 99%

Deep Learning for Action and Gesture Recognition in Image Sequences: A Survey

Asadi-Aghbolaghi

Clapés

Bellantonio

et al. 2017

Gesture Recognition

View full text Add to dashboard Cite

Interest in automatic action and gesture recognition has grown considerably in the last few years. This is due in part to the large number of application domains for this type of technology. As in many other computer vision areas, deep learning based methods have quickly become a reference methodology for obtaining state-of-the-art performance in both tasks. This chapter is a survey of current deep learning based methodologies for action and gesture recognition in sequences of images. The survey reviews both fundamental and cutting edge methodologies reported in the last few years. We introduce a taxonomy that summarizes important aspects of deep learning for approaching both tasks. Details of the proposed architectures, fusion strategies, main datasets, and competitions are reviewed. *. A reduced version of this appeared appeared as: M. Asadi-Aghbolaghi et al. A survey on deep learning based approaches for action and gesture recognition in image sequences. In

show abstract

Robust human action recognition via long short-term memory

Cited by 67 publications

References 16 publications

Chemical substance classification using long short-term memory recurrent neural network

Chemical substance classification using long short-term memory recurrent neural network

Skeleton-Aided Articulated Motion Generation

Deep Learning for Action and Gesture Recognition in Image Sequences: A Survey

Contact Info

Product

Resources

About