SportsNGEN: Sustained Generation of Multi-player Sports Gameplay
- URL: http://arxiv.org/abs/2403.12977v1
- Date: Sat, 10 Feb 2024 01:16:21 GMT
- Title: SportsNGEN: Sustained Generation of Multi-player Sports Gameplay
- Authors: Lachlan Thorpe, Lewis Bawden, Karanjot Vendal, John Bronskill, Richard E. Turner,
- Abstract summary: We present a transformer decoder based model, SportsNGEN, that is trained on sports player and ball tracking sequences.
We train and evaluate SportsNGEN on a large database of professional tennis tracking data.
In addition, a generic version of SportsNGEN can be customized to a specific player by fine-tuning on match data that includes that player.
- Score: 19.80390059667457
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We present a transformer decoder based model, SportsNGEN, that is trained on sports player and ball tracking sequences that is capable of generating realistic and sustained gameplay. We train and evaluate SportsNGEN on a large database of professional tennis tracking data and demonstrate that by combining the generated simulations with a shot classifier and logic to start and end rallies, the system is capable of simulating an entire tennis match. In addition, a generic version of SportsNGEN can be customized to a specific player by fine-tuning on match data that includes that player. We show that our model is well calibrated and can be used to derive insights for coaches and broadcasters by evaluating counterfactual or what if options. Finally, we show qualitative results indicating the same approach works for football.
Related papers
- MatchTime: Towards Automatic Soccer Game Commentary Generation [52.431010585268865]
We consider constructing an automatic soccer game commentary model to improve the audiences' viewing experience.
First, observing the prevalent video-text misalignment in existing datasets, we manually annotate timestamps for 49 matches.
Second, we propose a multi-modal temporal alignment pipeline to automatically correct and filter the existing dataset at scale.
Third, based on our curated dataset, we train an automatic commentary generation model, named MatchVoice.
arXiv Detail & Related papers (2024-06-26T17:57:25Z) - Ball Trajectory Inference from Multi-Agent Sports Contexts Using Set
Transformer and Hierarchical Bi-LSTM [18.884300680050316]
This paper proposes an inference framework of ball trajectory from player trajectories as a cost-efficient alternative to ball tracking.
The experimental results show that our model provides natural and accurate trajectories as well as admissible player ball possession at the same time.
We suggest several practical applications of our framework including missing trajectory imputation, semi-automated pass annotation, automated zoom-in for match broadcasting, and calculating possession-wise running performance metrics.
arXiv Detail & Related papers (2023-06-14T02:19:59Z) - Who You Play Affects How You Play: Predicting Sports Performance Using
Graph Attention Networks With Temporal Convolution [29.478765505215538]
This study presents a novel deep learning method, called GATv2-GCN, for predicting player performance in sports.
We use a graph attention network to capture the attention that each player pays to each other, allowing for more accurate modeling.
We evaluate the performance of our model using real-world sports data, demonstrating its effectiveness in predicting player performance.
arXiv Detail & Related papers (2023-03-29T14:48:51Z) - Promptable Game Models: Text-Guided Game Simulation via Masked Diffusion
Models [68.85478477006178]
We present a Promptable Game Model (PGM) for neural video game simulators.
It allows a user to play the game by prompting it with high- and low-level action sequences.
Most captivatingly, our PGM unlocks the director's mode, where the game is played by specifying goals for the agents in the form of a prompt.
Our method significantly outperforms existing neural video game simulators in terms of rendering quality and unlocks applications beyond the capabilities of the current state of the art.
arXiv Detail & Related papers (2023-03-23T17:43:17Z) - CLIP-ReIdent: Contrastive Training for Player Re-Identification [0.0]
We investigate whether it is possible to transfer the out-standing zero-shot performance of pre-trained CLIP models to the domain of player re-identification.
Unlike previous work, our approach is entirely class-agnostic and benefits from large-scale pre-training.
arXiv Detail & Related papers (2023-03-21T13:55:27Z) - Understanding why shooters shoot -- An AI-powered engine for basketball
performance profiling [70.54015529131325]
Basketball is dictated by many variables, such as playstyle and game dynamics.
It is crucial that the performance profiles can reflect the diverse playstyles.
We present a tool that can visualize player performance profiles in a timely manner.
arXiv Detail & Related papers (2023-03-17T01:13:18Z) - Graph Neural Networks to Predict Sports Outcomes [0.0]
We introduce a sport-agnostic graph-based representation of game states.
We then use our proposed graph representation as input to graph neural networks to predict sports outcomes.
arXiv Detail & Related papers (2022-07-28T14:45:02Z) - A Survey on Video Action Recognition in Sports: Datasets, Methods and
Applications [60.3327085463545]
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, diving and badminton.
We develop a toolbox using PaddlePaddle, which supports football, basketball, table tennis and figure skating action recognition.
arXiv Detail & Related papers (2022-06-02T13:19:36Z) - SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in
Soccer Videos [62.686484228479095]
We propose a novel dataset for multiple object tracking composed of 200 sequences of 30s each.
The dataset is fully annotated with bounding boxes and tracklet IDs.
Our analysis shows that multiple player, referee and ball tracking in soccer videos is far from being solved.
arXiv Detail & Related papers (2022-04-14T12:22:12Z) - AI-enabled Prediction of eSports Player Performance Using the Data from
Heterogeneous Sensors [12.071865017583502]
We report on an Artificial Intelligence (AI) enabled solution for predicting the eSports player in-game performance using exclusively the data from sensors.
The player performance is assessed from the game logs in a multiplayer game for each moment of time using a recurrent neural network.
The proposed solution has a number of promising applications for Pro eSports teams as well as a learning tool for amateur players.
arXiv Detail & Related papers (2020-12-07T07:31:53Z) - Game Plan: What AI can do for Football, and What Football can do for AI [83.79507996785838]
Predictive and prescriptive football analytics require new developments and progress at the intersection of statistical learning, game theory, and computer vision.
We illustrate that football analytics is a game changer of tremendous value, in terms of not only changing the game of football itself, but also in terms of what this domain can mean for the field of AI.
arXiv Detail & Related papers (2020-11-18T10:26:02Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.