Paper
Perception-oriented video saliency detection via spatio-temporal attention analysis
Published Sep 26, 2016 · S. Zhong, Y. Liu, V. Ng
Neurocomputing
Q1 SJR score
14
Citations
0
Influential Citations
Abstract
Abstract removed due to Elsevier request; this does not indicate any issues with the research. Click the full text link above to read the abstract and view the original source.
Study Snapshot
Key takeawayThe proposed perception-oriented video saliency detection model effectively detects interesting objects and dominant motions in video sequences, achieving remarkable performance and consistency with human eye tracking data.
PopulationOlder adults (50-71 years)
Sample size24
MethodsObservational
OutcomesBody Mass Index projections
ResultsSocial networks mitigate obesity in older groups.
Sign up to use Study Snapshot
Consensus is limited without an account. Create an account or sign in to get more searches and use the Study Snapshot.
Full text analysis coming soon...
References
Salient Object Detection via Nonlocal Diffusion Tensor
Our method, using a nonlocal diffusion tensor, effectively detects salient objects in images, outperforming other methods on widely used benchmark datasets.
2015·4citations·Xiujun Zhang et al.·Int. J. Pattern Recognit. Artif. Intell.
Int. J. Pattern Recognit. Artif. Intell.
Visual-Patch-Attention-Aware Saliency Detection
Our visual-attention-aware model effectively mimics the human visual system in detecting salient objects in images, resulting in reliable and effective results.
2015·153citations·Muwei Jian et al.·IEEE Transactions on Cybernetics
IEEE Transactions on Cybernetics
Visual orientation inhomogeneity based scale-invariant feature transform
Visual orientation inhomogeneity SIFT (V-SIFT) improves performance in computer vision tasks like image matching and object recognition with less computational resources and time.
2015·26citations·S. Zhong et al.·Expert Syst. Appl.
Expert Syst. Appl.
Improved perception-based spiking neuron learning rule for real-time user authentication
Our improved PBSNLR algorithm improves efficiency without reducing accuracy in real-time user authentication using sliding dynamic and finger pressure biometrics.
2015·21citations·Hong Qu et al.·Neurocomputing
Neurocomputing
From QoS to QoE: A Tutorial on Video Quality Assessment
Video quality assessment methods have evolved, with data-driven models emerging to predict user experience, and future research directions include incorporating user feedback.
2015·310citations·Yanjiao Chen et al.·IEEE Communications Surveys & Tutorials
IEEE Communications Surveys & Tutorials
Citations
Sports Video Panorama Synthesis Technology Based on Edge Computing and Video Shot Boundary Detection
This research develops sports video panorama synthesis technology using edge computing and video shot boundary detection, enabling easier analysis and mastery of action in sports training.
2022·2citations·Xu Chen·Wireless Communications and Mobile Computing
Wireless Communications and Mobile Computing
Scene Recognition Model in Underground Mines Based on CNN-LSTM and Spatial-Temporal Attention Mechanism
The CNN-LSTM model with spatial-temporal attention mechanism improves the accuracy of underground mine scene recognition by 2.136% compared to traditional convolutional neural networks.
2020·2citations·Tianwei Zheng et al.·2020 International Symposium on Computer, Consumer and Control (IS3C)
2020 International Symposium on Computer, Consumer and Control (IS3C)
Video Saliency Prediction Based on Spatial-Temporal Two-Stream Network
Our two-stream neural network model effectively predicts video saliency without manual tuning, achieving advanced performance compared to state-of-the-art models.
2019·63citations·Kao Zhang et al.·IEEE Transactions on Circuits and Systems for Video Technology
IEEE Transactions on Circuits and Systems for Video Technology
Integrating QDWD with pattern distinctness and local contrast for underwater saliency detection
Our novel framework for underwater image saliency detection combines QDWD, pattern distinctness, and local contrast, achieving reliable and promising results compared to other state-of-the-art models.
2018·88citations·Muwei Jian et al.·J. Vis. Commun. Image Represent.
J. Vis. Commun. Image Represent.
Target detection of hyperspectral image based on spectral saliency
The spectral saliency target detection (SSD) algorithm outperforms traditional methods in hyperspectral image target detection, even in concealed and small target situations.
2018·7citations·Xiaorong Zhang et al.·IET Image Process.
IET Image Process.
Forecasting user attention during everyday mobile interactions using device-integrated and wearable sensors
Our method using device-integrated sensors and body-worn cameras can forecast user attention during mobile interactions, enabling adaptive user interfaces.
2018·41citations·Julian Steil et al.·Proceedings of the 20th International Conference on Human-Computer Interaction with Mobile Devices and Services
Proceedings of the 20th International Conference on Human-Computer Interaction with Mobile Devices and Services
Assessment of liver fibrosis in chronic hepatitis B via multimodal data
Using feature selection and machine learning methods on multimodal data, this study effectively stages liver fibrosis in chronic hepatitis B patients, outperforming single methods and linear combinations.
2017·12citations·B. Lei et al.·Neurocomputing
Neurocomputing
Saliency detection using quaternionic distance based weber local descriptor and level priors
The proposed method, combining QDWLD and object cues, effectively detects image saliency, outperforming existing models and providing reliable results.
2017·36citations·Muwei Jian et al.·Multimedia Tools and Applications
Multimedia Tools and Applications