Fine-Grained Action Recognition on a Novel Basketball Dataset

Gu, Xiaofan; Xue, Xinwei; Wang, Feng

doi:10.1109/icassp40776.2020.9053928

Cited by 20 publications

(16 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, CNN can be provided with multiple streams of data, and some layers of the network can be processed separately [ 49 ], so there are applications in sports with two-stream CNNs of different dimensions (e.g., [ 50 , 51 ]). Furthermore, researchers often apply a fusion of different approaches to consider the time dimension for recognizing human actions [ 52 ].…”

Section: Har In the Sports Domainmentioning

confidence: 99%

See 1 more Smart Citation

An overview of Human Action Recognition in sports based on Computer Vision

Host

Ivašić-Kos

2022

Heliyon

View full text Add to dashboard Cite

Section: Har In the Sports Domainmentioning

confidence: 99%

“…In [ 51 ], is released a dataset with fine-grained actions in basketball game videos. They propose an approach by integrating the NTS-Net [ 131 ] into a two-stream network to locate the most informative regions and extract more discriminative features for fine-grained action recognition.…”

Section: Har Implementation In Different Sportsmentioning

confidence: 99%

An overview of Human Action Recognition in sports based on Computer Vision

Host

Ivašić-Kos

2022

Heliyon

View full text Add to dashboard Cite

“…FineBasketball [64] is developed for fine-grained basketball action recognition, containing three broad categoriesdribbling, passing and shooting, and 26 fine-grained categories, such as behind-the-back dribbling, cross-over dribbling, hand-off, one-handed side passing, lay up shot, onehanded dunk and block shot. There are 3,399 video segments in total and each category contains roughly 130 video segments on average.…”

Section: B Basketballmentioning

confidence: 99%

“…One possible reason is that some sports-related datasets lack challenges and two-stream models can achieve high accuracy, for example, 91.4% on TTStroke-21 [130]. While some other datasets like NCAA [58] and FineBasketball [64] are still challenging, requiring more advanced models.…”

Section: B Deep Modelsmentioning

confidence: 99%

A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications

Wu¹,

Wang²,

Bian³

et al. 2022

Preprint

View full text Add to dashboard Cite

To understand human behaviors, action recognition based on videos is a common approach. Compared with imagebased action recognition, videos provide much more information. Reducing the ambiguity of actions and in the last decade, many works focused on datasets, novel models and learning approaches have improved video action recognition to a higher level. However, there are challenges and unsolved problems, in particular in sports analytics where data collection and labeling are more sophisticated, requiring sport professionals to annotate data. In addition, the actions could be extremely fast and it becomes difficult to recognize them. Moreover, in team sports like football and basketball, one action could involve multiple players, and to correctly recognize them, we need to analyse all players, which is relatively complicated. In this paper, we present a survey on video action recognition for sports analytics. We introduce more than ten types of sports, including team sports, such as football, basketball, volleyball, hockey and individual sports, such as figure skating, gymnastics, table tennis, tennis, diving and badminton. Then we compare numerous existing frameworks for sports analysis to present status quo of video action recognition in both team sports and individual sports. Finally, we discuss the challenges and unsolved problems in this area and to facilitate sports analytics, we develop a toolbox using PaddlePaddle 1 , which supports football, basketball, table tennis and figure skating action recognition.

show abstract

“…However, this study only considered a few exploratory examples. Gu et al [ 25 ] proposed a method for fine-grained video action recognition from basketball games. The research looked at 3 broad actions—dribbling, passing, and shooting—which are further divided into 26 fine-grained actions.…”

Section: Related Workmentioning

confidence: 99%

CricShotClassify: An Approach to Classifying Batting Shots from Cricket Videos Using a Convolutional Neural Network and Gated Recurrent Unit

Sen

Deb

Dhar

et al. 2021

Sensors

View full text Add to dashboard Cite

Recognizing the sport of cricket on the basis of different batting shots can be a significant part of context-based advertisement to users watching cricket, generating sensor-based commentary systems and coaching assistants. Due to the similarity between different batting shots, manual feature extraction from video frames is tedious. This paper proposes a hybrid deep-neural-network architecture for classifying 10 different cricket batting shots from offline videos. We composed a novel dataset, CricShot10, comprising uneven lengths of batting shots and unpredictable illumination conditions. Impelled by the enormous success of deep-learning models, we utilized a convolutional neural network (CNN) for automatic feature extraction, and a gated recurrent unit (GRU) to deal with long temporal dependency. Initially, conventional CNN and dilated CNN-based architectures were developed. Following that, different transfer-learning models were investigated—namely, VGG16, InceptionV3, Xception, and DenseNet169—which freeze all the layers. Experiment results demonstrated that the VGG16–GRU model outperformed the other models by attaining 86% accuracy. We further explored VGG16 and two models were developed, one by freezing all but the final 4 VGG16 layers, and another by freezing all but the final 8 VGG16 layers. On our CricShot10 dataset, these two models were 93% accurate. These results verify the effectiveness of our proposed architecture compared with other methods in terms of accuracy.

show abstract

Fine-Grained Action Recognition on a Novel Basketball Dataset

Cited by 20 publications

References 13 publications

An overview of Human Action Recognition in sports based on Computer Vision

An overview of Human Action Recognition in sports based on Computer Vision

A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications

CricShotClassify: An Approach to Classifying Batting Shots from Cricket Videos Using a Convolutional Neural Network and Gated Recurrent Unit

Contact Info

Product

Resources

About