Round Outcome Prediction in VALORANT Using Tactical Features from Video Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918164011417600 |
|---|---|
| author | Hayakawa, Nirai Shimari, Kazumasa Yamasaki, Kazuma Hoshikawa, Hirotatsu Tsuchida, Rikuto Matsumoto, Kenichi |
| author_facet | Hayakawa, Nirai Shimari, Kazumasa Yamasaki, Kazuma Hoshikawa, Hirotatsu Tsuchida, Rikuto Matsumoto, Kenichi |
| contents | Recently, research on predicting match outcomes in esports has been actively conducted, but much of it is based on match log data and statistical information. This research targets the FPS game VALORANT, which requires complex strategies, and aims to build a round outcome prediction model by analyzing minimap information in match footage. Specifically, based on the video recognition model TimeSformer, we attempt to improve prediction accuracy by incorporating detailed tactical features extracted from minimap information, such as character position information and other in-game events. This paper reports preliminary results showing that a model trained on a dataset augmented with such tactical event labels achieved approximately 81% prediction accuracy, especially from the middle phases of a round onward, significantly outperforming a model trained on a dataset with the minimap information itself. This suggests that leveraging tactical features from match footage is highly effective for predicting round outcomes in VALORANT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_17199 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Round Outcome Prediction in VALORANT Using Tactical Features from Video Analysis Hayakawa, Nirai Shimari, Kazumasa Yamasaki, Kazuma Hoshikawa, Hirotatsu Tsuchida, Rikuto Matsumoto, Kenichi Computer Vision and Pattern Recognition Artificial Intelligence Recently, research on predicting match outcomes in esports has been actively conducted, but much of it is based on match log data and statistical information. This research targets the FPS game VALORANT, which requires complex strategies, and aims to build a round outcome prediction model by analyzing minimap information in match footage. Specifically, based on the video recognition model TimeSformer, we attempt to improve prediction accuracy by incorporating detailed tactical features extracted from minimap information, such as character position information and other in-game events. This paper reports preliminary results showing that a model trained on a dataset augmented with such tactical event labels achieved approximately 81% prediction accuracy, especially from the middle phases of a round onward, significantly outperforming a model trained on a dataset with the minimap information itself. This suggests that leveraging tactical features from match footage is highly effective for predicting round outcomes in VALORANT. |
| title | Round Outcome Prediction in VALORANT Using Tactical Features from Video Analysis |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2510.17199 |