완전 관련
-1. A Transformer-based System for Action Spotting in Soccer Video
- https://dl.acm.org/doi/pdf/10.1145/3552437.3555693
- End-to-end 방법론
0. Feature combination meets attention: Baidu soccer embeddings and transformer based temporal detection
- https://arxiv.org/pdf/2106.14447.pdf
- the extraction features of five 3D CNN models pretrained on Kinetics [32] and finetuned on SoccerNet-v2.
1. Action Spotting using Dense Detection Anchors Revisited: Submission to the SoccerNet Challenge 2022
- 2022 7회 인용
- https://arxiv.org/pdf/2206.07846v2.pdf
- https://github.com/yahoo/spivak
- https://velog.io/@hsbc/Action-Spotting-using-Dense-Detection-Anchors-Revisited-Submission-to-the-SoccerNet-Challenge-2022
- Tight AP: 65.1% (2등)
2. COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformers
- 2024 인용 X
- https://arxiv.org/pdf/2309.01270v2.pdf
- https://github.com/juliendenize/eztorch
- Tight AP: 73.1% (1등)
3. Temporally-Aware Feature Pooling for Action Spotting in Soccer Broadcasts
- https://arxiv.org/pdf/2104.06779v1.pdf
- 2021, 33회 인용
- https://github.com/SilvioGiancola/SoccerNetv2-DevKit/tree/main/Task1-ActionSpotting/TemporallyAwarePooling
4. Spotting Temporally Precise, Fine-Grained Events in Video
-
ECCV 2022 14회 인용.
-
End-to-End 방법론
5. Towards Active Learning for Action Spotting in Association Football Videos
6. A Graph-Based Method for Soccer Action Spotting Using Unsupervised Player Classification
7. A Context-Aware Loss Function for Action Spotting in Soccer Videos
- CVPR 2020 76회 인용
- https://arxiv.org/pdf/1912.01326.pdf
- https://github.com/SilvioGiancola/SoccerNetv2-DevKit/tree/main/Task1-ActionSpotting/CALF
8. TEMPORALLY PRECISE ACTION SPOTTING IN SOCCER VIDEOS USING DENSE DETECTION ANCHORS
- ICIP 2022 14회 인용
- https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9897256
- No code
- used 0. paper Baidu features coupled with features from a pre- trained ResNet-152 to train an anchor-based approach that first classifies actions falling in a few-second temporal ra- dius and shifts the predictions using a temporal regressor.
9. Improved Soccer Action Spotting using both Audio and Video Streams
- CVPR 2020, 40회 인용
- https://openaccess.thecvf.com/content_CVPRW_2020/papers/w53/Vanderplaetse_Improved_Soccer_Action_Spotting_Using_Both_Audio_and_Video_Streams_CVPRW_2020_paper.pdf
- https://github.com/bastienvanderplaetse/SoccerNetMultimodalActionSpotting
덜 관련
10. A Comprehensive Review of Computer Vision in Sports: Open Issues, Future Trends and Research Directions
11. An overview of Human Action Recognition in sports based on Computer Vision
12. SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos
13. A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications
14. Scaling up SoccerNet with multi-view spatial localization and re-identification
15. SoccerTrack: A Dataset and Tracking Algorithm for Soccer with Fish-eye and Drone Videos
16. Semi-Supervised Training to Improve Player and Ball Detection in Soccer
모든 의사 결정 과정을 지나칠 정도로 모두 기록하고, 나중에 스스로 피드백 하는 것