{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T09:05:24Z","timestamp":1772442324927,"version":"3.50.1"},"reference-count":19,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Opponent modeling is crucial in intelligent game domains for analyzing and predicting adversary behaviors. Prevailing methods for opponent style modeling often suffer from insufficient feature construction, failing to capture the inherent spatiotemporal dynamics of strategic styles.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study proposes a novel opponent style representation learning method founded on spatiotemporal features. The approach synergistically integrates handcrafted features with those autonomously extracted by a neural network to model spatial characteristics, while a temporal network captures stylistic evolution. We introduce PyFeatNet, a pyramid-structured feature network, for efficient multi-scale spatial feature extraction from a structured feature map. Temporal modeling is enhanced through a self-supervised contrastive learning framework based on a Gated Recurrent Unit (GRU), which maximizes mutual information between context and future states. Furthermore, a composite loss function incorporating Noise Contrastive Estimation and a cosine-based divergence term is designed to explicitly maximize the separation between different style representations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed model achieves a remarkable opponent style recognition accuracy of 97.19%. Ablation studies confirm the individual contributions of the feature channel fusion pyramid and the contrastive learning mechanism, demonstrating that their removal leads to significant performance degradation. The model also exhibits fast convergence and low computational overhead, providing strong support for the real-time assessment of opponent styles.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.7717\/peerj-cs.3616","type":"journal-article","created":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T08:27:36Z","timestamp":1772440056000},"page":"e3616","source":"Crossref","is-referenced-by-count":0,"title":["Opponent style representation learning method based on spatio-temporal features"],"prefix":"10.7717","volume":"12","author":[{"given":"Kai","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinpeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shichen","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianhao","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"4443","published-online":{"date-parts":[[2026,3,2]]},"reference":[{"issue":"5","key":"10.7717\/peerj-cs.3616\/ref-1","doi-asserted-by":"publisher","first-page":"104221","DOI":"10.1016\/j.cose.2024.104221","article-title":"A bio-inspired optimal feature with convolutional GhostNet based squeeze excited deep-scale capsule network for intrusion detection","volume":"150","author":"Ammannamma","year":"2025","journal-title":"Computers and Security"},{"issue":"2","key":"10.7717\/peerj-cs.3616\/ref-2","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1109\/TCIAIG.2009.2029084","article-title":"Rapid and reliable adaptation of video game AI","volume":"1","author":"Bakkes","year":"2009","journal-title":"IEEE Transactions on Computational Intelligence and AI in Games"},{"issue":"4","key":"10.7717\/peerj-cs.3616\/ref-3","doi-asserted-by":"publisher","first-page":"111639","DOI":"10.1016\/j.knosys.2024.111639","article-title":"Echo state network and classical statistical techniques for time series forecasting: a review","volume":"293","author":"Cardoso","year":"2024","journal-title":"Knowledge-Based Systems"},{"key":"10.7717\/peerj-cs.3616\/ref-4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.16300\/j.cnki.1000-3630.23112402","article-title":"Children\u2019s emotional speech recognition technology based on Attention-LSTM","volume":"43","author":"Chenyang","year":"2024","journal-title":"SXJS"},{"key":"10.7717\/peerj-cs.3616\/ref-5","first-page":"2414","article-title":"Image style transfer using convolutional neural networks","author":"Gatys","year":"2016"},{"issue":"1","key":"10.7717\/peerj-cs.3616\/ref-6","doi-asserted-by":"publisher","first-page":"128645","DOI":"10.1016\/j.neucom.2024.128645","article-title":"A comprehensive survey on contrastive learning","volume":"610","author":"Hu","year":"2024","journal-title":"Neurocomputing"},{"issue":"1","key":"10.7717\/peerj-cs.3616\/ref-7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TG.2019.2896986","article-title":"Deep learning for video game playing","volume":"12","author":"Justesen","year":"2020","journal-title":"IEEE Transactions on Games"},{"key":"10.7717\/peerj-cs.3616\/ref-8","first-page":"884","article-title":"Hierarchical reinforcement learning with opponent modeling for distributed multi-agent cooperation","volume-title":"2022 IEEE 42nd International Conference on Distributed Computing Systems (ICDCS). IEEE","author":"Liang","year":"2022"},{"key":"10.7717\/peerj-cs.3616\/ref-9","doi-asserted-by":"publisher","first-page":"111","DOI":"10.13880\/j.cnki.65-1174\/n.2025.23.003","article-title":"Sentiment analysis model of Chinese commentary text based on self-attention and TextCNN-BiLSTM","volume":"43","author":"Long","year":"2025","journal-title":"Journal of Shihezi University (Natural Science)"},{"key":"10.7717\/peerj-cs.3616\/ref-10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412.03068","article-title":"UTSD: unified time series diffusion model","author":"Ma","year":"2024"},{"key":"10.7717\/peerj-cs.3616\/ref-11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203.03691","article-title":"HyperMixer: an MLP-based low cost alternative to transformers","author":"Mai","year":"2023"},{"issue":"1","key":"10.7717\/peerj-cs.3616\/ref-12","doi-asserted-by":"publisher","first-page":"2","DOI":"10.3390\/bdcc9010002","article-title":"MobileNet-HeX: Heterogeneous ensemble of MobileNet eXperts for efficient and scalable vision model optimization","volume":"9","author":"Pintelas","year":"2025","journal-title":"Big Data and Cognitive Computing"},{"issue":"3","key":"10.7717\/peerj-cs.3616\/ref-13","doi-asserted-by":"publisher","first-page":"758","DOI":"10.5755\/j01.itc.53.3.35101","article-title":"Detecting the medical plant association from PubMed using hypergraph-based clustering with dominating set","volume":"53","author":"Sampath","year":"2024","journal-title":"Information Technology and Control"},{"issue":"1","key":"10.7717\/peerj-cs.3616\/ref-14","doi-asserted-by":"publisher","first-page":"215","DOI":"10.5755\/j01.itc.52.1.32008","article-title":"Deep learning based cardiovascular disease risk factor prediction among type 2 diabetes mellitus patients","volume":"52","author":"Selvarathi","year":"2023","journal-title":"Information Technology and Control"},{"issue":"3","key":"10.7717\/peerj-cs.3616\/ref-15","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/s42979-025-03786-9","article-title":"Wavelet transform based gated-recurrent unit deep learning approach for power output of solar photovoltaic system forecasting","volume":"6","author":"Singh","year":"2025","journal-title":"SN Computer Science"},{"key":"10.7717\/peerj-cs.3616\/ref-16","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1145\/3205455.3205578","article-title":"Evolving simple programs for playing atari games","author":"Wilson","year":"2018"},{"key":"10.7717\/peerj-cs.3616\/ref-17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2503.03302","article-title":"Differential machine learning for time series prediction","author":"Yadav","year":"2025"},{"key":"10.7717\/peerj-cs.3616\/ref-18","doi-asserted-by":"publisher","first-page":"1004","DOI":"10.16383\/j.aas.c210127","article-title":"An opponent modeling and strategy integration framework for Texas Hold\u2019em","volume":"48","author":"Zhang","year":"2022","journal-title":"zdhxb"},{"issue":"13","key":"10.7717\/peerj-cs.3616\/ref-19","doi-asserted-by":"publisher","first-page":"7203","DOI":"10.1007\/s00521-024-09455-x","article-title":"From mimic to counteract: a two-stage reinforcement learning algorithm for Google research football","volume":"36","author":"Zhao","year":"2024","journal-title":"Neural Computing and Applications"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3616.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3616.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3616.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3616.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T08:27:41Z","timestamp":1772440061000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3616"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,2]]},"references-count":19,"alternative-id":["10.7717\/peerj-cs.3616"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3616","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,2]]},"article-number":"e3616"}}