Ice hockey player identification via transformers and weakly supervised learning

Vats, Kanav; McNally, William; Walters, Pascale; Clausi, David A.; Zelek, John

doi:10.1109/cvprw56347.2022.00389

Cited by 17 publications

(8 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Test Acc Challenge Acc Gerke et al [12] 32.57% 35.79% Vats et al [25] 46.73% 49.88% Li et al [17] 47.85% 50.60% Vats et al [26] 52.91% 58.45% Balaji et al [4] 68.53% 73.77% Ours 87.45% 79.31% images and achieve an accuracy of 91.4%. Table 4 shows a comparison with methods previously reported in the literature.…”

Section: Methodsmentioning

confidence: 99%

“…The problem of jersey number recognition has been posed as image-level recognition [6,17,19,20,25] as well as tracklet-level recognition [4,7,26,27]. Some methods detect and localize the jersey number region and then classify the numbers [17,19,20], while others assume that the im-age region containing the jersey number has already been cropped [6,12,25].…”

Section: Jersey Number Recognitionmentioning

confidence: 99%

“…Chan et al [7] and Balaji et al [4] employed an LSTM while Vats et al [27] used a temporal convolutional network to aggregate information over time. Vats et al [26] have also explored the use of transformers for tracklet-level jersey number recognition within the multi-task approach introduced in [25]. They also make use of prior knowledge about the roster of players on the ice.…”

Section: Tracklet-level Jersey Number Recognitionmentioning

confidence: 99%

See 2 more Smart Citations

Contrastive Learning for Sports Video: Unsupervised Player Classification

Koshkina

Pidaparthy

Elder

2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Jersey number recognition is an important task in sports video analysis, partly due to its importance for long-term player tracking. It can be viewed as a variant of scene text recognition. However, there is a lack of published attempts to apply scene text recognition models on jersey number data. Here we introduce a novel public jersey number recognition dataset for hockey and study how scene text recognition methods can be adapted to this problem. We address issues of occlusions and assess the degree to which training on one sport (hockey) can be generalized to another (soccer). For the latter, we also consider how jersey number recognition at the single-image level can be aggregated across frames to yield tracklet-level jersey number labels. We demonstrate high performance on image-and tracklet-level tasks, achieving 91.4% accuracy for hockey images and 87.4% for soccer tracklets. Code, models, and data are available at https://github.com/mkoshkina/jerseynumber-pipeline.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Jersey Number Recognitionmentioning

confidence: 99%

Section: Tracklet-level Jersey Number Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

Contrastive Learning for Sports Video: Unsupervised Player Classification

Koshkina

Pidaparthy

Elder

2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

show abstract

“…In this method, the CNN detects the ball and then the Kalman filter is exploited to predict the location of the ball. Vats et al [22] developed another model for detecting both the players and the ball simultaneously based on semisupervised learning. Their proposed system utilized an iterative teacher-student method alongside three loss parametrizations.…”

Section: Player and Ball Detectionmentioning

confidence: 99%

Automatic Team Assignment and Jersey Number Recognition in Football Videos

Alhejaily¹,

Alhejaily²,

Almdahrsh³

et al. 2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Football is one of the most-watched sports, but analyzing players' performance is currently difficult and labor intensive. Performance analysis is done manually, which means that someone must watch video recordings and then log each player's performance. This includes the number of passes and shots taken by each player, the location of the action, and whether or not the play had a successful outcome. Due to the time-consuming nature of manual analyses, interest in automatic analysis tools is high despite the many interdependent phases involved, such as pitch segmentation, player and ball detection, assigning players to their teams, identifying individual players, activity recognition, etc. This paper proposes a system for developing an automatic video analysis tool for sports. The proposed system is the first to integrate multiple phases, such as segmenting the field, detecting the players and the ball, assigning players to their teams, and identifying players' jersey numbers. In team assignment, this research employed unsupervised learning based on convolutional autoencoders (CAEs) to learn discriminative latent representations and minimize the latent embedding distance between the players on the same team while simultaneously maximizing the distance between those on opposing teams. This paper also created a highly accurate approach for the real-time detection of the ball. Furthermore, it also addressed the lack of jersey number datasets by creating a new dataset with more than 6,500 images for numbers ranging from 0 to 99. Since achieving a high performance in deep learning requires a large training set, and the collected dataset was not enough, this research utilized transfer learning (TL) to first pretrain the jersey number detection model on another large dataset and then fine-tune it on the target dataset to increase the accuracy. To test the proposed system, this paper presents a comprehensive evaluation of its individual stages as well as of the system as a whole. All codes, datasets, and experiments are available on GitHub (https://github.com/ragadalhejaily/project).

show abstract

“…In the context of team sports, there are also other cues that can be helpful in re-identification of a person, such as team affiliation [20,23,48], role information [23], and jersey number [26,46,47]. [20] trains a network that can output embeddings that are close for players on the same team and far from each other for players from different teams.…”

Section: Part-based Re-identificationmentioning

confidence: 99%

Multi-task Learning for Joint Re-identification, Team Affiliation, and Role Classification for Sports Visual Tracking

Mansourian,

Somers,

De Vleeschouwer

et al. 2023

Proceedings of the 6th International Workshop on Multimedia Content Analysis in Sports

View full text Add to dashboard Cite

Effective tracking and re-identification of players is essential for analyzing soccer videos. But, it is a challenging task due to the nonlinear motion of players, the similarity in appearance of players from the same team, and frequent occlusions. Therefore, the ability to extract meaningful embeddings to represent players is crucial in developing an effective tracking and re-identification system. In this paper, a multi-purpose part-based person representation method, called PRTreID, is proposed that performs three tasks of role classification, team affiliation, and re-identification, simultaneously. In contrast to available literature, a single network is trained with multi-task supervision to solve all three tasks, jointly. The proposed joint method is computationally efficient due to the shared backbone. Also, the multi-task learning leads to richer and more discriminative representations, as demonstrated by both quantitative and qualitative results. To demonstrate the effectiveness of PRTreID, it is integrated with a state-of-the-art tracking method, using a part-based post-processing module to handle long-term tracking. The proposed tracking method, outperforms all existing tracking methods on the challenging SoccerNet tracking dataset. CCS CONCEPTS• Computing methodologies → Tracking.

show abstract

Ice hockey player identification via transformers and weakly supervised learning

Cited by 17 publications

References 24 publications

Contrastive Learning for Sports Video: Unsupervised Player Classification

Contrastive Learning for Sports Video: Unsupervised Player Classification

Automatic Team Assignment and Jersey Number Recognition in Football Videos

Multi-task Learning for Joint Re-identification, Team Affiliation, and Role Classification for Sports Visual Tracking

Contact Info

Product

Resources

About