Multiple Granularity Modeling: A Coarse-to-Fine Framework for Fine-grained Action Analysis

Ni, Bingbing; Paramathayalan, Vignesh R.; Li, Teng; Moulin, Pierre

doi:10.1007/s11263-016-0891-8

Cited by 8 publications

(2 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The current human pose estimation is mainly divided into overall human pose estimation algorithms and human pose component estimation algorithms [ 15 ]. The algorithms for overall human pose estimation usually use a nonlinear mapping between images and nodal positions to achieve human pose estimation [ 16 , 17 ]. A deep neural network-based human pose estimation algorithm has been proposed to obtain pose estimation values with high accuracy using DNN regression quantities, which has the advantage over other algorithms in that it performs pose inference through a holistic approach [ 18 ].…”

Section: Related Workmentioning

confidence: 99%

Application of Human Posture Recognition Based on the Convolutional Neural Network in Physical Training Guidance

Wang

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The application of sports game video analysis in athlete training and competition analysis feedback has attracted extensive attention, but the traditional sports human body posture estimation method has a large error between the athlete’s human body posture estimation results and the actual results in the complex environment and the athlete’s body parts are blocked. Therefore, this study proposes a convolutional neural network for athlete pose estimation in sports game video. Based on the improved model, multiscale model, and large perception model, a superimposed hourglass network is constructed, and the gradient disappearance problem of the convolutional neural network is solved using intermediate supervision. The experimental results show that the athlete pose estimation model based on the convolutional neural network can improve the accuracy of athlete pose estimation and reduce the negative impact of occlusion environment on athlete pose estimation to a certain extent. In addition, compared with other athletes’ standing posture estimation methods, the model has competitive advantages and high accuracy under widely used standard conditions.

show abstract

Section: Related Workmentioning

confidence: 99%

Application of Human Posture Recognition Based on the Convolutional Neural Network in Physical Training Guidance

Wang

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…A promising direction to further boost the classification accuracy is multigranularity discriminative feature learning, which aims to discover features at multiple scales along the convolutional network backbone. Prior efforts [21][22][23] have explored ways to mine multigranularity features that are fused and then fed into the detection head. In [22], a multigranularity progressive training framework is proposed to learn complementary features at different granularities.…”

Section: Introductionmentioning

confidence: 99%

Semantic Multigranularity Feature Learning for High-Resolution Remote Sensing Image Scene Classification

Xiao

Yun

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

High-resolution remote sensing image scene classification is a challenging visual task due to the large intravariance and small intervariance between the categories. To accurately recognize the scene categories, it is essential to learn discriminative features from both global and local critical regions. Recent efforts focus on how to encourage the network to learn multigranularity features with the destruction of the spatial information on the input image at different scales, which leads to meaningless edges that are harmful to training. In this study, we propose a novel method named Semantic Multigranularity Feature Learning Network (SMGFL-Net) for remote sensing image scene classification. The core idea is to learn both global and multigranularity local features from rearranged intermediate feature maps, thus, eliminating the meaningless edges. These features are then fused for the final prediction. Our proposed framework is compared with a collection of state-of-the-art (SOTA) methods on two fine-grained remote sensing image scene datasets, including the NWPU-RESISC45 and Aerial Image Datasets (AID). We justify several design choices, including the branch granularities, fusion strategies, pooling operations, and necessity of feature map rearrangement through a comparative study. Moreover, the overall performance results show that SMGFL-Net consistently outperforms other peer methods in classification accuracy, and the superiority is more apparent with less training data, demonstrating the efficacy of feature learning of our approach.

show abstract

Action detection and classification in kitchen activities videos using graph decoding

Ramadan

El-Jaroudi

2022

Vis Comput

View full text Add to dashboard Cite

Multiple Granularity Modeling: A Coarse-to-Fine Framework for Fine-grained Action Analysis

Cited by 8 publications

References 49 publications

Application of Human Posture Recognition Based on the Convolutional Neural Network in Physical Training Guidance

Application of Human Posture Recognition Based on the Convolutional Neural Network in Physical Training Guidance

Semantic Multigranularity Feature Learning for High-Resolution Remote Sensing Image Scene Classification

Action detection and classification in kitchen activities videos using graph decoding

Contact Info

Product

Resources

About