PFNet: Large-Scale Traffic Forecasting With Progressive Spatio-Temporal Fusion

Wang, Chen; Kai-zhong, Zuo; Zhang, S. C.; Lei, Hongshuai; Hu, Ping; Shen, Zhangyi; Wang, Rui; Zhao, Peize

doi:10.1109/tits.2023.3296697

Cited by 5 publications

(2 citation statements)

References 97 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can also be used for camouflaged object detection, enhancing the perception ability of camouflaged objects by using depth maps as additional input. Wang [4] proposed a camouflage object segmentation method with interference mining (PFNet) for segmenting camouflage objects from complex scenes. This method imitates the predation process in nature, first locating potential objects from a global perspective through a positioning module (PM) and then gradually refining the segmentation results by focusing on fuzzy areas through a focusing module (FM).…”

Section: Related Workmentioning

confidence: 99%

“…Convolutional networks can use GPUs for efficient computation to improve processing speed and propose a series of innovative model structures, such as VGG [3] and ResNet50 [4], which are already sufficiently mature. There has also been a focus on designing efficient feature fusion processors, the corresponding preferences of which can be set for feature extraction from images.However, at present, there are still two obvious problems with CNN-based feature extraction models.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Camouflaged Object Detection Based on Deep Learning with Attention-Guided Edge Detection and Multi-Scale Context Fusion

Wen,

Ke,

Sheng

2024

Applied Sciences

View full text Add to dashboard Cite

In nature, objects that use camouflage have features like colors and textures that closely resemble their background. This creates visual illusions that help them hide and protect themselves from predators. This similarity also makes the task of detecting camouflaged objects very challenging. Methods for camouflaged object detection (COD), which rely on deep neural networks, are increasingly gaining attention. These methods focus on improving model performance and computational efficiency by extracting edge information and using multi-layer feature fusion. Our improvement is based on researching ways to enhance efficiency in the encode–decode process. We have developed a variant model that combines Swin Transformer (Swin-T) and EfficientNet-B7. This model integrates the strengths of both Swin-T and EfficientNet-B7, and it employs an attention-guided tracking module to efficiently extract edge information and identify objects in camouflaged environments. Additionally, we have incorporated dense skip links to enhance the aggregation of deep-level feature information. A boundary-aware attention module has been incorporated into the final layer of the initial shallow information recognition phase. This module utilizes the Fourier transform to quickly relay specific edge information from the initially obtained shallow semantics to subsequent stages, thereby more effectively achieving feature recognition and edge extraction. In the latter phase, which is focused on deep semantic extraction, we employ a dense skip joint attention module to enhance the decoder’s performance and efficiency, ensuring accurate capture of deep-level information, feature recognition, and edge extraction. In the later stage of deep semantic extraction, we use a dense skip joint attention module to improve the decoder’s performance and efficiency in capturing precise deep information. This module efficiently identifies the specifics and edge information of undetected camouflaged objects across channels and spaces. Differing from previous methods, we introduce an adaptive pixel strength loss function for handling key captured information. Our proposed method shows strong competitive performance on three current benchmark datasets (CHAMELEON, CAMO, COD10K). Compared to 26 previously proposed methods using 4 measurement metrics, our approach exhibits favorable competitiveness.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Camouflaged Object Detection Based on Deep Learning with Attention-Guided Edge Detection and Multi-Scale Context Fusion

Wen,

Ke,

Sheng

2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

Deep Learning for Traffic Prediction and Trend Deviation Identification: A Case Study in Hong Kong

Zou,

Chung,

et al. 2024

Data Sci. Transp.

View full text Add to dashboard Cite

This paper introduces a robust methodology for predicting traffic volume and speed on major strategic routes in Hong Kong by leveraging data from data.gov.hk and utilizing deep learning models. The approach offers predictions from 6 min to 1 h, considering detector reliability. By extracting hidden deep features from historical detector data to establish detector profiles and grouping detectors into clusters based on profile similarities, the method employs a CNN-LSTM prediction model for each cluster. The study demonstrates the model’s resilience to detector failures, with tests conducted across failure rates from 1% to 20%, highlighting its ability to maintain accurate predictions despite random failures. In scenarios without failed detectors, the method achieves favorable performance metrics: MAE, RMSE, and MAPE for traffic volume prediction over the next 6 min stand at 5.17 vehicles/6 min, 7.64 vehicles/6 min, and 14.07%, respectively, while for traffic speed prediction, the values are 3.70 km/h, 6.32 km/h, and 6.33%. Considering a failure rate of approximately 6% in the Hong Kong dataset, in simulated scenarios with 6% failures, the model maintains its predictive accuracy, with average MAE, RMSE, and MAPE for traffic volume prediction at 5.24 vehicles/6 min, 7.81 vehicles/6 min, and 14.21%, and for traffic speed prediction at 3.87 km/h, 6.55 km/h, and 6.68%. However, the limitation of the proposed method is its potential to underperform when predicting rare or unseen scenarios, indicating the need for future research to incorporate additional data sources and methods to enhance predictive performance.

show abstract

TADGCN: A Time-Aware Dynamic Graph Convolution Network for long-term traffic flow prediction

Wang,

Zuo,

Zhang

et al. 2024

Expert Systems with Applications

View full text Add to dashboard Cite

PFNet: Large-Scale Traffic Forecasting With Progressive Spatio-Temporal Fusion

Cited by 5 publications

References 97 publications

Camouflaged Object Detection Based on Deep Learning with Attention-Guided Edge Detection and Multi-Scale Context Fusion

Camouflaged Object Detection Based on Deep Learning with Attention-Guided Edge Detection and Multi-Scale Context Fusion

Deep Learning for Traffic Prediction and Trend Deviation Identification: A Case Study in Hong Kong

TADGCN: A Time-Aware Dynamic Graph Convolution Network for long-term traffic flow prediction

Contact Info

Product

Resources

About