Learning Topographic Representations of Nature Images with Pairwise Cumulant

Wang, Zhe; Huang, Yaping; Luo, Xiaoyue; Wang, Liang; Luo, Siwei

doi:10.1007/s11063-011-9189-6

Cited by 5 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each convolution of 7 7 d × is succeeded by a normalization layer and a GELU unit. While the utilization of global attention or large convolutional kernels to expand the sensory field has been extensively studied in recent years [32][33][34][35], these approaches often introduce significant computational cost and memory overhead, especially in dense prediction tasks, due to the large size of the input image. In contrast, the focusing block proposed in this paper introduces only a minimal additional cost.…”

Section: Cascading Fusion Network Cfnetmentioning

confidence: 99%

YOLOv8-CB: Dense Pedestrian Detection Algorithm Based on In-Vehicle Camera

Liu,

Ye,

Wang

et al. 2024

Electronics

View full text Add to dashboard Cite

Recently, the field of vehicle-mounted visual intelligence technology has witnessed a surge of interest in pedestrian detection. Existing algorithms for dense pedestrian detection at intersections face challenges such as high computational weight, complex models that are difficult to deploy, and suboptimal detection accuracy for small targets and highly occluded pedestrians. To address these issues, this paper proposes an improved lightweight multi-scale pedestrian detection algorithm, YOLOv8-CB. The algorithm introduces a lightweight cascade fusion network, CFNet (cascade fusion network), and a CBAM attention module to improve the characterization of multi-scale feature semantics and location information, and it superimposes a bidirectional weighted feature fusion path BIFPN structure to fuse more effective features and improve pedestrian detection performance. It is experimentally verified that compared with the YOLOv8n algorithm, the accuracy of the improved model is increased by 2.4%, the number of model parameters is reduced by 6.45%, and the computational load is reduced by 6.74%. The inference time for a single image is 10.8 ms. The cascade fusion algorithm YOLOv8-CB has higher detection accuracy and is a lighter model for multi-scale pedestrian detection in complex scenes such as streets or intersections. This proposed algorithm presents a valuable approach for device-side pedestrian detection with limited computational resources.

show abstract

Section: Cascading Fusion Network Cfnetmentioning

confidence: 99%

YOLOv8-CB: Dense Pedestrian Detection Algorithm Based on In-Vehicle Camera

Liu,

Ye,

Wang

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…CondenseNet [ 14 ], inspired by DenseNet, utilizes learned group convolutions to reduce computations, resulting in smaller models and faster processing, but this comes at the cost of additional complexity. Similarly, Yulin et al [ 15 ] introduced dynamic transformers for efficient image recognition, addressing the limitations of fixed-size image embeddings by dynamically adapting the number of tokens based on image complexity. On the other hand, this approach may increase computational overhead during inference due to dynamic grid resizing.…”

Section: Related Workmentioning

confidence: 99%

Human Action Recognition and Note Recognition: A Deep Learning Approach Using STA-GCN

Enkhbat,

Shih,

Cheewaprakobkit

2024

Sensors

View full text Add to dashboard Cite

Human action recognition (HAR) is growing in machine learning with a wide range of applications. One challenging aspect of HAR is recognizing human actions while playing music, further complicated by the need to recognize the musical notes being played. This paper proposes a deep learning-based method for simultaneous HAR and musical note recognition in music performances. We conducted experiments on Morin khuur performances, a traditional Mongolian instrument. The proposed method consists of two stages. First, we created a new dataset of Morin khuur performances. We used motion capture systems and depth sensors to collect data that includes hand keypoints, instrument segmentation information, and detailed movement information. We then analyzed RGB images, depth images, and motion data to determine which type of data provides the most valuable features for recognizing actions and notes in music performances. The second stage utilizes a Spatial Temporal Attention Graph Convolutional Network (STA-GCN) to recognize musical notes as continuous gestures. The STA-GCN model is designed to learn the relationships between hand keypoints and instrument segmentation information, which are crucial for accurate recognition. Evaluation on our dataset demonstrates that our model outperforms the traditional ST-GCN model, achieving an accuracy of 81.4%.

show abstract

“…Dynamic neural networks (DNNs) aim to reduce the computational effort and increase the model generalization capability, and multi-exit is also one of the techniques of dynamic neural networks. The idea of multi-exit has been widely used in the fields of computer vision (CV) and natural language processing (NLP) (Liu et al, 2020;Wang et al, 2021), but to our knowledge, no multi-exit network has been specifically designed for the sleep stage classification task to reduce the computational cost of the network as of yet. In this section, we introduce the training and inference process of DynamicSleepNet.…”

Section: Model Training and Inferencementioning

confidence: 99%

DynamicSleepNet: a multi-exit neural network with adaptive inference time for sleep stage classification

et al. 2023

View full text Add to dashboard Cite

Sleep is an essential human physiological behavior, and the quality of sleep directly affects a person’s physical and mental state. In clinical medicine, sleep stage is an important basis for doctors to diagnose and treat sleep disorders. The traditional method of classifying sleep stages requires sleep experts to classify them manually, and the whole process is time-consuming and laborious. In recent years, with the help of deep learning, automatic sleep stage classification has made great progress, especially networks using multi-modal electrophysiological signals, which have greatly improved in terms of accuracy. However, we found that the existing multimodal networks have a large number of redundant calculations in the process of using multiple electrophysiological signals, and the networks become heavier due to the use of multiple signals, and difficult to be used in small devices. To solve these two problems, this paper proposes DynamicSleepNet, a network that can maximize the use of multiple electrophysiological signals and can dynamically adjust between accuracy and efficiency. DynamicSleepNet consists of three effective feature extraction modules (EFEMs) and three classifier modules, each EFEM is connected to a classifier. Each EFEM is able to extract signal features while making the effective features more prominent and the invalid features are suppressed. The samples processed by the EFEM are given to the corresponding classifier for classification, and if the classifier considers the uncertainty of the sample to be below the threshold we set, the sample can be output early without going through the whole network. We validated our model on four datasets. The results show that the highest accuracy of our model outperforms all baselines. With accuracy close to baselines, our model is faster than the baselines by a factor of several to several tens, and the number of parameters of the model is lower or close. The implementation code is available at: https://github.com/Quinella7291/A-Multi-exit-Neural-Network-with-Adaptive-Inference-Time-for-Sleep-Stage-Classification/.

show abstract

Learning Topographic Representations of Nature Images with Pairwise Cumulant

Cited by 5 publications

References 23 publications

YOLOv8-CB: Dense Pedestrian Detection Algorithm Based on In-Vehicle Camera

YOLOv8-CB: Dense Pedestrian Detection Algorithm Based on In-Vehicle Camera

Human Action Recognition and Note Recognition: A Deep Learning Approach Using STA-GCN

DynamicSleepNet: a multi-exit neural network with adaptive inference time for sleep stage classification

Contact Info

Product

Resources

About