Effective and efficient sports play retrieval with deep representation learning
With the proliferation of commercial tracking systems, sports data is being generated at an unprecedented speed and the interest in sports play retrieval has grown dramatically as well. However, it is challenging to design an effective, efficient and robust similarity measure for sports play retriev...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/148149 |
| _version_ | 1826112720568582144 |
|---|---|
| author | Wang, Zheng Long, Cheng Cong, Gao Ju, Ce |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Wang, Zheng Long, Cheng Cong, Gao Ju, Ce |
| author_sort | Wang, Zheng |
| collection | NTU |
| description | With the proliferation of commercial tracking systems, sports data is being generated at an unprecedented speed and the interest in sports play retrieval has grown dramatically as well. However, it is challenging to design an effective, efficient and robust similarity measure for sports play retrieval. To this end, we propose a deep learning approach to learn the representations of sports plays, called play2vec, which is robust against noise and takes only linear time to compute the similarity between two sports plays. We conduct experiments on real-world soccer match data, and the results show that our solution performs more effectively and efficiently compared with the state-of-the-art methods. |
| first_indexed | 2024-10-01T03:11:44Z |
| format | Conference Paper |
| id | ntu-10356/148149 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:11:44Z |
| publishDate | 2021 |
| record_format | dspace |
| spelling | ntu-10356/1481492021-05-06T01:36:53Z Effective and efficient sports play retrieval with deep representation learning Wang, Zheng Long, Cheng Cong, Gao Ju, Ce School of Computer Science and Engineering Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining Engineering::Computer science and engineering::Information systems::Database management Similar Play Retrieval Deep Learning With the proliferation of commercial tracking systems, sports data is being generated at an unprecedented speed and the interest in sports play retrieval has grown dramatically as well. However, it is challenging to design an effective, efficient and robust similarity measure for sports play retrieval. To this end, we propose a deep learning approach to learn the representations of sports plays, called play2vec, which is robust against noise and takes only linear time to compute the similarity between two sports plays. We conduct experiments on real-world soccer match data, and the results show that our solution performs more effectively and efficiently compared with the state-of-the-art methods. Nanyang Technological University This work is supported in part by a MOE Tier-2 grant MOE2016-T2-1-137, a MOE Tier-1 grant RG31/17 and NTU SUG grant M4082302.020. 2021-05-06T01:36:52Z 2021-05-06T01:36:52Z 2019 Conference Paper Wang, Z., Long, C., Cong, G. & Ju, C. (2019). Effective and efficient sports play retrieval with deep representation learning. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 499-509. https://dx.doi.org/10.1145/3292500.3330927 9781450362016 https://hdl.handle.net/10356/148149 10.1145/3292500.3330927 2-s2.0-85071194963 499 509 en START-UP GRANT © 2019 Association for Computing Machinery (ACM). All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering::Information systems::Database management Similar Play Retrieval Deep Learning Wang, Zheng Long, Cheng Cong, Gao Ju, Ce Effective and efficient sports play retrieval with deep representation learning |
| title | Effective and efficient sports play retrieval with deep representation learning |
| title_full | Effective and efficient sports play retrieval with deep representation learning |
| title_fullStr | Effective and efficient sports play retrieval with deep representation learning |
| title_full_unstemmed | Effective and efficient sports play retrieval with deep representation learning |
| title_short | Effective and efficient sports play retrieval with deep representation learning |
| title_sort | effective and efficient sports play retrieval with deep representation learning |
| topic | Engineering::Computer science and engineering::Information systems::Database management Similar Play Retrieval Deep Learning |
| url | https://hdl.handle.net/10356/148149 |
| work_keys_str_mv | AT wangzheng effectiveandefficientsportsplayretrievalwithdeeprepresentationlearning AT longcheng effectiveandefficientsportsplayretrievalwithdeeprepresentationlearning AT conggao effectiveandefficientsportsplayretrievalwithdeeprepresentationlearning AT juce effectiveandefficientsportsplayretrievalwithdeeprepresentationlearning |