Distillhash: Unsupervised deep hashing by distilling data pairs

E Yang, T Liu, C Deng, W Liu… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
Due to storage and search efficiency, hashing has become significantly prevalent for nearest
neighbor search. Particularly, deep hashing methods have greatly improved the search …

View-invariant deep architecture for human action recognition using two-stream motion and shape temporal dynamics

C Dhiman, DK Vishwakarma - IEEE Transactions on Image …, 2020 - ieeexplore.ieee.org
Human action Recognition for unknown views, is a challenging task. We propose a deep
view-invariant human action recognition framework, which is a novel integration of two …

Unsupervised semantic-preserving adversarial hashing for image search

C Deng, E Yang, T Liu, J Li, W Liu… - IEEE transactions on …, 2019 - ieeexplore.ieee.org
Hashing plays a pivotal role in nearest-neighbor searching for large-scale image retrieval.
Recently, deep learning-based hashing methods have achieved promising performance …

A review of computational approaches for human behavior detection

S Nigam, R Singh, AK Misra - Archives of Computational Methods in …, 2019 - Springer
Computer vision techniques capable of detecting human behavior are gaining interest.
Several researchers have provided their review on behavior detection, however most of the …

A dynamic ensemble deep deterministic policy gradient recursive network for spatiotemporal traffic speed forecasting in an urban road network

X Mi, C Yu, X Liu, G Yan, F Yu, P Shang - Digital Signal Processing, 2022 - Elsevier
Traffic congestion is a difficult problem that restricts the construction of urbanization.
Spatiotemporal traffic speed forecasting technologies can provide effective technical support …

[Retracted] Computer Aided Teaching System Based on Artificial Intelligence in Football Teaching and Training

D Li, J Zhang - Mobile Information Systems, 2021 - Wiley Online Library
As the world′ s largest sport, football has affected a wide area and a large number of
participants and had a great impact on political economy and culture, which has become the …

Survey on artificial intelligence-based human action recognition in video sequences

R Kumar, S Kumar - Optical Engineering, 2023 - spiedigitallibrary.org
In the artificial intelligence domain, human action recognition (HAR) has evolved as one of
the major active research topics as a reason of diverse applications, namely video …

Multi-stream convolutional neural networks for action recognition in video sequences based on adaptive visual rhythms

DT Concha, HDA Maia, H Pedrini… - 2018 17th IEEE …, 2018 - ieeexplore.ieee.org
Advances in digital technology have increased event recognition capabilities through the
development of devices with high resolution, small physical dimensions and high sampling …

Weighted voting of multi-stream convolutional neural networks for video-based action recognition using optical flow rhythms

A de Souza Brito, MB Vieira, SM Villela, H Tacon… - Journal of Visual …, 2021 - Elsevier
Two of the most important premises of an ensemble are the diversity of its components and
how to combine their votes. In this paper, we propose a multi-stream architecture based on …

ST-GRF: Spatiotemporal graph neural networks for rainfall forecasting

FH Zhang, ZG Shao - Digital Signal Processing, 2023 - Elsevier
Accurate and real-time rainfall forecasting plays an important role in the weather forecast
system and is of great significance for travel planning, engineering planning, and crop …