ST-CNN: Spatial-Temporal Convolutional Neural Network for crowd counting in videos

Miao, Yunqi; Han, Jungong; Gao, Yongsheng; Zhang, Baochang

doi:10.1016/j.patrec.2019.04.012

Cited by 53 publications

(13 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, Miao et al used a TCN to estimate density maps from videos. 114 The authors in Ref. 116 also applied a TCN to summarize generic videos.…”

Section: Hardware Performancementioning

confidence: 99%

Deep Learning for Time Series Forecasting: A Survey

et al. 2021

View full text Add to dashboard Cite

Time series forecasting has become a very intensive field of research, which is even increasing in recent years. Deep neural networks have proved to be powerful and are achieving high accuracy in many application fields. For these reasons, they are one of the most widely used methods of machine learning to solve problems dealing with big data nowadays. In this work, the time series forecasting problem is initially formulated along with its mathematical fundamentals. Then, the most common deep learning architectures that are currently being successfully applied to predict time series are described, highlighting their advantages and limitations. Particular attention is given to feed forward networks, recurrent neural networks (including Elman, long-short term memory, gated recurrent units, and bidirectional networks), and convolutional neural networks. Practical aspects, such as the setting of values for hyperparameters and the choice of the most suitable frameworks, for the successful application of deep learning to time series are also provided and discussed. Several fruitful research fields in which the architectures analyzed have obtained a good performance are reviewed. As a result, research gaps have been identified in the literature for several domains of application, thus expecting to inspire new and better forms of knowledge.

show abstract

“…For example, Miao et al used a TCN to estimate density maps from videos. 114 The authors in Ref. 116 also applied a TCN to summarize generic videos.…”

Section: Hardware Performancementioning

confidence: 99%

Deep Learning for Time Series Forecasting: A Survey

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Forecasting based on deep learning allows the integration of complex temporal, relational, spatial, and contextual correlations to infer predictions. Previous work in spatiotemporal study leverages Convolutional Neural Networks (CNN) (Yao et al 2018;Miao et al 2019) and Graph Neural Networks (GNN) (Li et al 2015;Scarselli et al 2009;Wu et al 2020;Bruna et al 2013) to capture the spatial dependency. Recurrent Neural Networks (RNN) and their variants (Sutskever, Vinyals, and Le 2014;Wu et al 2017) have also been used to capture temporal correlations.…”

Section: Related Workmentioning

confidence: 99%

Context Integrated Relational Spatio-Temporal Resource Forecasting

Chen

Rossi

Mahadik

2021

2021 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

Traditional methods for demand forecasting only focus on modeling the temporal dependency. However, forecasting on spatio-temporal data requires modeling of complex nonlinear relational and spatial dependencies. In addition, dynamic contextual information can have a significant impact on the demand values, and therefore needs to be captured. For example, in a bike-sharing system, bike usage can be impacted by weather. Existing methods assume the contextual impact is fixed. However, we note that the contextual impact evolves over time. We propose a novel context integrated relational model, Context Integrated Graph Neural Network (CIGNN), which leverages the temporal, relational, spatial, and dynamic contextual dependencies for multi-step ahead demand forecasting. Our approach considers the demand network over various geographical locations and represents the network as a graph. We define a demand graph, where nodes represent demand time-series, and context graphs (one for each type of context), where nodes represent contextual time-series. Assuming that various contexts evolve and have a dynamic impact on the fluctuation of demand, our proposed CIGNN model employs a fusion mechanism that jointly learns from all available types of contextual information. To the best of our knowledge, this is the first approach that integrates dynamic contexts with graph neural networks for spatio-temporal demand forecasting, thereby increasing prediction accuracy. We present empirical results on two real-world datasets, demonstrating that CIGNN consistently outperforms state-of-the-art baselines, in both periodic and irregular time-series networks.

show abstract

“…This ideology has been widely accepted in academia, and there have been lots of successful cases utilizing this method, e.g. the spatial-temporal-CNN used for crowd counting in videos [15], and LSTM-CNN used for face antispoofing [16]. However, CNN still bears a mathematically natural trait of parallelism and it's time-consuming to use a temporal CNN when the amount of data is huge [17].…”

Section: A Videopose3dmentioning

confidence: 99%

A Training Method For VideoPose3D with Ideology of Action Recognition

Bai

2021

2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)

View full text Add to dashboard Cite

Action recognition and pose estimation from videos are closely related to understand human motions, but more literature focuses on how to solve pose estimation tasks alone from action recognition. This research shows a faster and more flexible training method for VideoPose3D which is based on action recognition. This model is fed with the same type of action as the type that will be estimated, and different types of actions can be trained separately. Evidence has shown that, for common pose-estimation tasks, this model requires a relatively small amount of data to carry out similar results with the original research, and for action-oriented tasks, it outperforms the original research by 4.5% with a limited receptive field size and training epoch on Velocity Error of MPJPE. This model can handle both action-oriented and common pose-estimation problems.

show abstract

ST-CNN: Spatial-Temporal Convolutional Neural Network for crowd counting in videos

Cited by 53 publications

References 13 publications

Deep Learning for Time Series Forecasting: A Survey

Deep Learning for Time Series Forecasting: A Survey

Context Integrated Relational Spatio-Temporal Resource Forecasting

A Training Method For VideoPose3D with Ideology of Action Recognition

Contact Info

Product

Resources

About